OBJECTIVES: To assess the performance, generalizability, and computational efficiency of instruction-tuned Large Language Model Meta AI (LLaMA)-2 and LLaMA-3 models compared to bidirectional encoder representations from transformers (BERT) for clinical information extraction (IE) tasks, specifically named entity recognition (NER) and relation extraction (RE). MATERIALS AND METHODS: We developed a comprehensive annotated corpus of 1588 clinical notes from 4 data sources-UT Physicians (UTP) (1342 notes), Transcribed Medical Transcription Sample Reports and Examples (MTSamples) (146), Medical Information Mart for Intensive Care (MIMIC)-III (50), and Informatics for Integrating Biology and the Bedside (i2b2) (50), capturing 4 clinical entities (problems, tests, medications, other treatments) and 16 modifiers (eg, negation, certainty). Large Language Model Meta AI-2 and LLaMA-3 were instruction-tuned for clinical NER and RE, and their performance was benchmarked against BERT. RESULTS: Large Language Model Meta AI models consistently outperformed BERT across datasets. In data-rich settings (eg, UTP), LLaMA achieved marginal gains (approximately 1% improvement for NER and 1.5%-3.7% for RE). Under limited data conditions (eg, MTSamples, MIMIC-III) and on the unseen i2b2 dataset, LLaMA-3-70B improved F1 scores by over 7% for NER and 4% for RE. However, performance gains came with increased computational costs, with LLaMA models requiring more memory and Graphics Processing Unit (GPU) hours and running up to 28 times slower than BERT. DISCUSSION: While LLaMA models offer enhanced performance, their higher computational demands and slower throughput highlight the need to balance performance with practical resource constraints. Application-specific considerations are essential when choosing between LLMs and BERT for clinical IE. CONCLUSION: Instruction-tuned LLaMA models show promise for clinical NER and RE tasks. However, the tradeoff between improved performance and increased computational cost must be carefully evaluated. We release our Kiwi package (https://kiwi.clinicalnlp.org/) to facilitate the application of both LLaMA and BERT models in clinical IE applications.

Knowledge graph (KG) contrastive learning (CL) has garnered significant attention in the realm of recommendation systems. However, existing models often employ random masking for graph enhancement, which can introduce sampling bias and impede interpretability. Furthermore, the KG-UIG information imbalance can lead to the neglect of critical information in the user-item interaction graph (UIG) by the model. To address these challenges, we propose a novel model, diffusion-augmented graph CL (DAGCL). This model leverages a graph diffusion mechanism for data enhancement in CL, thereby ensuring that the generated diffusion graph closely resembles the original UIG and avoiding the pitfalls associated with random sampling. Additionally, DAGCL enhances the impact of UIG on predictive accuracy by implementing both intragraph and intergraph CL (GCL), effectively mitigating the information imbalance between KGs and UIG. The model also leverages the structural characteristics of the UIG to construct a structural diffusion graph, which is integrated with the information diffusion graph to produce a comprehensive diffusion representation-further enhancing the model's robustness against sampling noise and semantic dilution by preserving essential interaction patterns and structural features in the augmented graph. Experimental results across three real-world datasets demonstrate that our proposed model outperforms state-of-the-art models significantly.

As large language models are increasingly deployed in cloud environments, privacy concerns have become a significant issue. To address this challenge, we present THOR, a non-interactive framework for secure transformer inference using homomorphic encryption. We first propose efficient matrix multiplication algorithms based on diagonal-major encoding and compact ciphertext packing. We extend these basic algorithms to support plaintext-ciphertext matrix multiplication (PC-MM) using parallel submatrix computation and ciphertext-ciphertext multiplication (CC-MM) with a baby-step giant-step strategy. We also design efficient evaluation strategies for non-linear functions such as softmax, LayerNorm, GELU, and Tanh, by integrating advanced approximation techniques with adaptive iterative methods. Our matrix multiplication algorithms outperform state-of-the-art methods, achieving up to 5.3X speedup in PC-MM for ℝ 768 X 768 X ℝ768X128 over BOLT (Pang et al., IEEE S&P 2024) and 9.7X in CC-MM for 12X (ℝ64X128 X ℝ128X128) over Powerformer (Park et al., Preprint). THOR enables secure inference on the BERT-base model with 128 tokens in 10 minutes on a single GPU, while maintaining comparable accuracy on GLUE tasks.

Many federated learning scenarios encounter label noises in the client-side datasets. The resulting degradation in global model performance raises the urgent need to address label noise. This paper proposes FedClean – a novel general robust label noise correction for federated learning. FedClean first uses the local centralized noisy label learning to select clean samples to train a global model. Then, it employs a two-stage correction scheme to correct the noisy labels from two distinct perspectives of local noisy label learning and the global model. FedClean also proposes a novel model aggregation method, further reducing the impact of label noises. FedClean neither assumes the existence of clean clients nor the specific noise distributions, showing the maximum versatility. Extensive experimental results show that FedClean effectively identifies and rectifies label noises even if all clients exhibit label noises, which outperforms the state-of-the-art noise-label learning methods for federated learning.

Federated Learning (FL) enables collaborative model training across institutions without sharing raw data. However, gradient sharing still risks privacy leakage, such as gradient inversion attacks. Homomorphic Encryption (HE) can secure aggregation but often incurs prohibitive computational and communication overhead. Existing HE-based FL methods sit at two extremes: encrypting all gradients for full privacy at high cost, or partially encrypting gradients to save resources while exposing vulnerabilities. We present **DictPFL**, a practical framework that achieves full gradient protection with minimal overhead. DictPFL encrypts every transmitted gradient while keeping non-transmitted parameters local, preserving privacy without heavy computation. It introduces two key modules: **Decompose-for-Partial-Encrypt (DePE)**, which decomposes model weights into a static dictionary and an updatable lookup table—only the latter is encrypted and aggregated, while the static dictionary remains local and requires neither sharing nor encryption; and **Prune-for-Minimum-Encrypt (PrME)**, which applies encryption-aware pruning to minimize encrypted parameters via consistent, history-guided masks. Experiments show that DictPFL reduces communication cost by 402-748$\times$ and accelerates training by 28-65$\times$ compared to fully encrypted FL, while outperforming state-of-the-art selective encryption methods by 51-155$\times$ in overhead and 4-19$\times$ in speed. Remarkably, DictPFL’s runtime is within 2$\times$ of plaintext FL, demonstrating, for the first time, that HE-based private federated learning is practical for real-world deployment. The code is publicly available at https://github.com/UCF-ML-Research/DictPFL.

Deep-learning models like Variational AutoEncoder have enabled low dimensional cellular embedding representation for large-scale single-cell transcriptomes and shown great flexibility in downstream tasks. However, biologically meaningful latent space is usually missing if no specific structure is designed. Here, we engineered a novel interpretable generative transcriptional program (iGTP) framework that could model the importance of transcriptional program (TP) space and protein-protein interactions (PPI) between different biological states. We demonstrated the performance of iGTP in a diverse biological context using gene ontology, canonical pathway, and different PPI curation. iGTP not only elucidated the ground truth of cellular responses but also surpassed other deep learning models and traditional bioinformatics methods in functional enrichment tasks. By integrating the latent layer with a graph neural network framework, iGTP could effectively infer cellular responses to perturbations. Lastly, we applied iGTP TP embeddings with a latent diffusion model to accurately generate cell embeddings for specific cell types and states. We anticipate that iGTP will offer insights at both PPI and TP levels and holds promise for predicting responses to novel perturbations.

Polygenic risk scores (PRS) are widely used to assess genetic susceptibility in Alzheimer's disease (AD) research. However, the rapid expansion of PRS studies has led to dataset-specific biases-stemming from factors like population makeup, genotyping methods, and analysis pipelines-that result in inconsistent variant prioritization and limit generalizability and reproducibility. To address these challenges, we propose a transductive learning framework that integrates multiple PRS datasets for more robust risk variant prioritization, incorporating genome-wide association study (GWAS) priority scores as biologically informed priors. Additionally, we introduce BrainGeneBot, an AI-driven tool leveraging generative pretrained transformers with retrieval-augmented generation technology to streamline genomic analyses in AD, including the STRING for protein interaction analysis, Enrichr for gene set enrichment, ClinVar for genetic variant interpretation, and Biopython for conducting literature searches. We apply our approach to publicly available AD datasets from the PGS Catalog and conduct further analyses to validate its efficacy. In parallel, we perform conventional unsupervised rank aggregation as a baseline. The transductive learning approach not only verifies high-risk variants identified by traditional methods but also reveals unique insights that better correlate with GWAS signals. Our framework streamlines data retrieval and interpretation, effectively prioritizing genetic variants in multiple PRS studies. Moreover, BrainGeneBot facilitates the discovery of biologically meaningful insights to enhance PRS interpretability and applicability in AD research, supporting the development of precise AD interventions and treatments. Our approach provides a robust framework for AD genetic research, improving data accessibility, accelerating discoveries, and refining genetic insights.

OBJECTIVE: This study evaluates the integration of electronic health records (EHRs) and natural language processing (NLP) with large language models (LLMs) to enhance healthcare data management and patient care, focusing on using advanced language models to create secure, Health Insurance Portability and Accountability Act-compliant synthetic patient notes for global biomedical research. MATERIALS AND METHODS: The study used de-identified and re-identified versions of the MIMIC III dataset with GPT-3.5, GPT-4, and Mistral 7B to generate synthetic clinical notes. Text generation employed templates and keyword extraction for contextually relevant notes, with One-shot generation for comparison. Privacy was assessed by analyzing protected health information (PHI) occurrence and co-occurrence, while utility was evaluated by training an ICD-9 coder using synthetic notes. Text quality was measured using ROUGE (Recall-Oriented Understudy for Gisting Evaluation) and cosine similarity metrics to compare synthetic notes with source notes for semantic similarity. RESULTS: The analysis of PHI occurrence and text utility via the ICD-9 coding task showed that the keyword-based method had low risk and good performance. One-shot generation exhibited the highest PHI exposure and PHI co-occurrence, particularly in geographic location and date categories. The Normalized One-shot method achieved the highest classification accuracy. Re-identified data consistently outperformed de-identified data. DISCUSSION: Privacy analysis revealed a critical balance between data utility and privacy protection, influencing future data use and sharing. CONCLUSION: This study shows that keyword-based methods can create synthetic clinical notes that protect privacy while retaining data usability, potentially improving clinical data sharing. The use of dummy PHIs to counter privacy attacks may offer better utility and privacy than traditional de-identification.

OBJECTIVES: Primary graft dysfunction (PGD) is an essential outcome after the heart transplant, which causes severe complications and symptoms for recipients. The in advance prediction of PGD can help the transplant physician better manage the risks of PGD occurrence for patients. Domain experts have identified some important risk factors leading to PGD. However, a widely accepted PGD prediction method is lacking from a computational perspective. In this work, we focus on the prediction of PGD after heart transplant with machine learning (ML). MATERIALS AND METHODS: With the strong power of artificial intelligence, we propose to design a ML algorithm to precisely predict the PGD with the donor and recipient features. Moreover, we apply the computational method to automatically identify important features and interactions between them. RESULTS: To evaluate the effectiveness of the ML algorithm in PGD prediction, we curated a PGD patients' cohort from the United Network for Organ Sharing database, which contains 8008 recipients. 5 commonly used ML models are used for performance comparison. The multi-layer perceptron model achieves superior performance, as measured by area under the receiver operating characteristic curve (AUROC), at 0.868. We identify the top 20 important features and interactions between donors and recipients. Clinical analyses are conducted on the identified features and interactions. DISCUSSION: We summarize the contributions of this work from three aspects including methodology, clinical analysis, and insights. We discuss the limitations of this work on data, model, and real-world implementation perspectives. Additionally, we further discuss the future directions to extend this work to more organ types and diseases. CONCLUSION: In summary, ML has promising applications in PGD prediction as a computational tool for clinical study. We can also use the ML model to help us identify and discover new risk factors and interactions between donor and recipient.

OBJECTIVE: Common Data Elements (CDEs) standardize data collection and sharing across studies, enhancing data interoperability and improving research reproducibility. However, implementing CDEs presents challenges due to the broad range and variety of data elements. This study aims to develop a CDE mapping tool to bridge the gap between local data elements and National Institutes of Health (NIH) CDEs. METHODS: We propose CDEMapper, a large language model (LLM)-powered mapping tool designed to assist in mapping local data elements to NIH CDEs. CDEMapper has 3 core modules: (1) CDE indexing and embeddings. NIH CDEs were indexed and embedded to support semantic search; (2) CDE recommendations. The tool combines Elasticsearch (BM25 methods) with GPT services to recommend candidate CDEs and their permissible values; and (3) Human review. Users review and select the best match for their data elements and value sets. We evaluate the tool's recommendation accuracy and usability against manual annotations and testing. RESULTS: CDEMapper offers a publicly available, LLM-powered, and intuitive user interface that consolidates essential and advanced mapping services into a streamlined pipeline. The evaluation results demonstrated that the augmented BM25 with GPT embeddings and a GPT ranker achieved the overall best performance. The usability test also highlighted the effectiveness and efficiency of our tool. DISCUSSIONS AND CONCLUSIONS: This work opens up the potential of using LLMs to assist with CDE mapping when aligning local data elements with NIH CDEs. Additionally, this effort helps researchers better understand the gaps between their data elements and NIH CDEs while promoting CDE reusability.

Crowdsourcing offers an efficient means of gathering labeled data and training machine learning models. However, the exposure of crowd workers to potential privacy breaches during data collection diminishes their willingness to participate. This paper proposes TsIFedCrowd, a novel incentive mechanism within the federated learning paradigm, aimed at mitigating privacy risks for crowd workers while achieving high-quality crowdsourced data and learning models at minimal expense. TsIFedCrowd enables clients to retain privacy-sensitive data locally, requiring only the upload of trained models to the server, which aggregates them into a global model. By modeling the federated crowdsourcing process as a two-stage Stackelberg game, TsIFedCrowd incentivizes workers to complete tasks with heightened quality and efficiency. It also provides a timeliness selection mechanism, which makes TsIFedCrowd suitable for both real-time crowdsourcing, where the generation time of task results (data) needs to meet the established requirements of the application, and non-real-time crowdsourcing. TsIFedCrowd mandates clients to complete federated crowdsourcing tasks while maximizing utility for both clients and the server, achieved through Nash equilibrium resolution. TsIFedCrowd is also extended to the multiple heterogeneous federated crowdsourcing scenario. Extensive experiments demonstrate TsIFedCrowd’s effectiveness in ensuring incentive fairness and universality, accelerating convergence speed, and budget savings. Real-world crowdsourcing tasks further validate its efficacy.

SUMMARY: The vast generation of genetic data poses a significant challenge in efficiently uncovering valuable knowledge. Introducing GENEVIC, an AI-driven chat framework that tackles this challenge by bridging the gap between genetic data generation and biomedical knowledge discovery. Leveraging generative AI, notably ChatGPT, it serves as a biologist's "copilot." It automates the analysis, retrieval, and visualization of customized domain-specific genetic information, and integrates functionalities to generate protein interaction networks, enrich gene sets, and search scientific literature from PubMed, Google Scholar, and arXiv, making it a comprehensive tool for biomedical research. In its pilot phase, GENEVIC is assessed using a curated database that ranks genetic variants associated with Alzheimer's disease, schizophrenia, and cognition, based on their effect weights from the Polygenic Score (PGS) Catalog, thus enabling researchers to prioritize genetic variants in complex diseases. GENEVIC's operation is user-friendly, accessible without any specialized training, secured by Azure OpenAI's HIPAA-compliant infrastructure, and evaluated for its efficacy through real-time query testing. As a prototype, GENEVIC is set to advance genetic research, enabling informed biomedical decisions. AVAILABILITY AND IMPLEMENTATION: GENEVIC is publicly accessible at https://genevicanath2024.streamlit.app. The underlying code is open-source and available via GitHub at https://github.com/bsml320/GENEVIC.git (also at https://github.com/anath2110/GENEVIC.git).

BACKGROUND: The potential benefits of drug combination synergy in cancer medicine are significant, yet the risks must be carefully managed due to the possibility of increased toxicity. Although artificial intelligence applications have demonstrated notable success in predicting drug combination synergy, several key challenges persist: (1) Existing models often predict average synergy values across a restricted range of testing dosages, neglecting crucial dose amounts and the mechanisms of action of the drugs involved. (2) Many graph-based models rely on static protein-protein interactions, failing to adapt to dynamic and higher-order relationships. These limitations constrain the applicability of current methods. RESULTS: We introduce SAFER, a Sub-hypergraph Attention-based graph model, addressing these issues by incorporating complex relationships among biological knowledge networks and considering dosing effects on subject-specific networks. SAFER outperformed previous models on the benchmark and the independent test set. The analysis of subgraph attention weight for the lung cancer cell line highlighted JAK-STAT signaling pathway, PRDM12, ZNF781, and CDC5L that have been implicated in lung fibrosis. CONCLUSIONS: SAFER presents an interpretable framework designed to identify drug-responsive signals. Tailored for comprehending dose effects on subject-specific molecular contexts, our model uniquely captures dose-level drug combination responses. This capability unlocks previously inaccessible avenues of investigation compared to earlier models. Furthermore, the SAFER framework can be leveraged by future inquiries to investigate molecular networks that uniquely characterize individual patients and can be applied to prioritize personalized effective treatment based on safe dose combinations.

Crowdsourcing provides a cost-effective labeling solution for the acquisition of labeled training samples for machine learning by employing workers on the Internet. A common approach to improving the label quality is to employ a truth inference method to infer integrated labels for samples from their multiple noisy labels obtained from different crowd workers. Although the quality of integrated labels is significantly improved compared with that of the original noisy ones, it still cannot completely eliminate the noises inevitably existing in the integrated labels. To further improve the label quality, this paper proposes a novel label noise correction method for crowdsourcing based on dynamic resampling (DRNC). DRNC first divides the dataset with inferred labels into a clean set and a noisy set through a filter. According to a certain proportion, the clean set and the noisy set are resampled to train multiple heterogeneous classifiers, which form an ensemble classifier . Then, the dataset is divided by the ensemble classifier into a new sub-noisy set and a sub-clean set. The whole process repeats multiple rounds, generating multiple sub-clean sets. Finally, these sub-clean sets are used to train classifiers, which jointly correct the wrong labels in the dataset by voting. Experimental results on 25 simulated and 4 real-world datasets consistently show that the proposed DRNC averagely improves the quality of labels as well as the quality of learned models in the range of 1 to 10 percentage points, compared with four state-of-the-art crowdsourcing noise correction methods.

OBJECTIVES: Heart failure (HF) impacts millions of patients worldwide, yet the variability in treatment responses remains a major challenge for healthcare professionals. The current treatment strategies, largely derived from population based evidence, often fail to consider the unique characteristics of individual patients, resulting in suboptimal outcomes. This study aims to develop computational models that are patient-specific in predicting treatment outcomes, by utilizing a large Electronic Health Records (EHR) database. The goal is to improve drug response predictions by identifying specific HF patient subgroups that are likely to benefit from existing HF medications. MATERIALS AND METHODS: A novel, graph-based model capable of predicting treatment responses, combining Graph Neural Network and Transformer was developed. This method differs from conventional approaches by transforming a patient's EHR data into a graph structure. By defining patient subgroups based on this representation via K-Means Clustering, we were able to enhance the performance of drug response predictions. RESULTS: Leveraging EHR data from 11 627 Mayo Clinic HF patients, our model significantly outperformed traditional models in predicting drug response using NT-proBNP as a HF biomarker across five medication categories (best RMSE of 0.0043). Four distinct patient subgroups were identified with differential characteristics and outcomes, demonstrating superior predictive capabilities over existing HF subtypes (best mean RMSE of 0.0032). DISCUSSION: These results highlight the power of graph-based modeling of EHR in improving HF treatment strategies. The stratification of patients sheds light on particular patient segments that could benefit more significantly from tailored response predictions. CONCLUSIONS: Longitudinal EHR data have the potential to enhance personalized prognostic predictions through the application of graph-based AI techniques.

IMPORTANCE: The study highlights the potential of large language models, specifically GPT-3.5 and GPT-4, in processing complex clinical data and extracting meaningful information with minimal training data. By developing and refining prompt-based strategies, we can significantly enhance the models' performance, making them viable tools for clinical NER tasks and possibly reducing the reliance on extensive annotated datasets. OBJECTIVES: This study quantifies the capabilities of GPT-3.5 and GPT-4 for clinical named entity recognition (NER) tasks and proposes task-specific prompts to improve their performance. MATERIALS AND METHODS: We evaluated these models on 2 clinical NER tasks: (1) to extract medical problems, treatments, and tests from clinical notes in the MTSamples corpus, following the 2010 i2b2 concept extraction shared task, and (2) to identify nervous system disorder-related adverse events from safety reports in the vaccine adverse event reporting system (VAERS). To improve the GPT models' performance, we developed a clinical task-specific prompt framework that includes (1) baseline prompts with task description and format specification, (2) annotation guideline-based prompts, (3) error analysis-based instructions, and (4) annotated samples for few-shot learning. We assessed each prompt's effectiveness and compared the models to BioClinicalBERT. RESULTS: Using baseline prompts, GPT-3.5 and GPT-4 achieved relaxed F1 scores of 0.634, 0.804 for MTSamples and 0.301, 0.593 for VAERS. Additional prompt components consistently improved model performance. When all 4 components were used, GPT-3.5 and GPT-4 achieved relaxed F1 socres of 0.794, 0.861 for MTSamples and 0.676, 0.736 for VAERS, demonstrating the effectiveness of our prompt framework. Although these results trail BioClinicalBERT (F1 of 0.901 for the MTSamples dataset and 0.802 for the VAERS), it is very promising considering few training samples are needed. DISCUSSION: The study's findings suggest a promising direction in leveraging LLMs for clinical NER tasks. However, while the performance of GPT models improved with task-specific prompts, there's a need for further development and refinement. LLMs like GPT-4 show potential in achieving close performance to state-of-the-art models like BioClinicalBERT, but they still require careful prompt engineering and understanding of task-specific knowledge. The study also underscores the importance of evaluation schemas that accurately reflect the capabilities and performance of LLMs in clinical settings. CONCLUSION: While direct application of GPT models to clinical NER tasks falls short of optimal performance, our task-specific prompt framework, incorporating medical knowledge and training samples, significantly enhances GPT models' feasibility for potential clinical applications.

OBJECTIVES: The rapid expansion of biomedical literature necessitates automated techniques to discern relationships between biomedical concepts from extensive free text. Such techniques facilitate the development of detailed knowledge bases and highlight research deficiencies. The LitCoin Natural Language Processing (NLP) challenge, organized by the National Center for Advancing Translational Science, aims to evaluate such potential and provides a manually annotated corpus for methodology development and benchmarking. MATERIALS AND METHODS: For the named entity recognition (NER) task, we utilized ensemble learning to merge predictions from three domain-specific models, namely BioBERT, PubMedBERT, and BioM-ELECTRA, devised a rule-driven detection method for cell line and taxonomy names and annotated 70 more abstracts as additional corpus. We further finetuned the T0pp model, with 11 billion parameters, to boost the performance on relation extraction and leveraged entites' location information (eg, title, background) to enhance novelty prediction performance in relation extraction (RE). RESULTS: Our pioneering NLP system designed for this challenge secured first place in Phase I-NER and second place in Phase II-relation extraction and novelty prediction, outpacing over 200 teams. We tested OpenAI ChatGPT 3.5 and ChatGPT 4 in a Zero-Shot setting using the same test set, revealing that our finetuned model considerably surpasses these broad-spectrum large language models. DISCUSSION AND CONCLUSION: Our outcomes depict a robust NLP system excelling in NER and RE across various biomedical entities, emphasizing that task-specific models remain superior to generic large ones. Such insights are valuable for endeavors like knowledge graph development and hypothesis formulation in biomedical research.

Increasing genetic and phenotypic data size is critical for understanding the genetic determinants of diseases. Evidently, establishing practical means for collaboration and data sharing among institutions is a fundamental methodological barrier for performing high-powered studies. As the sample sizes become more heterogeneous, complex statistical approaches, such as generalized linear mixed effects models, must be used to correct for the confounders that may bias results. On another front, due to the privacy concerns around Protected Health Information (PHI), genetic information is restrictively protected by sharing according to regulations such as Health Insurance Portability and Accountability Act (HIPAA). This limits data sharing among institutions and hampers efforts around executing high-powered collaborative studies. Federated approaches are promising to alleviate the issues around privacy and performance, since sensitive data never leaves the local sites. Motivated by these, we developed FedGMMAT, a federated genetic association testing tool that utilizes a federated statistical testing approach for efficient association tests that can correct for confounding fixed and additive polygenic random effects among different collaborating sites. Genetic data is never shared among collaborating sites, and the intermediate statistics are protected by encryption. Using simulated and real datasets, we demonstrate FedGMMAT can achieve the virtually same results as pooled analysis under a privacy-preserving framework with practical resource requirements.

The exponential growth in scholarly publications necessitates advanced tools for efficient article retrieval, especially in interdisciplinary fields where diverse terminologies are used to describe similar research. Traditional keyword-based search engines often fall short in assisting users who may not be familiar with specific terminologies. To address this, we present a knowledge graph based paper search engine for biomedical research to enhance the user experience in discovering relevant queries and articles. The system, dubbed DiscoverPath, employs Named Entity Recognition (NER) and part-of-speech (POS) tagging to extract terminologies and relationships from article abstracts to create a KG. To reduce information overload, DiscoverPath presents users with a focused subgraph containing the queried entity and its neighboring nodes and incorporates a query recommendation system enabling users to iteratively refine their queries. The system is equipped with an accessible Graphical User Interface that provides an intuitive visualization of the KG, query recommendations, and detailed article information, enabling efficient article retrieval, thus fostering interdisciplinary knowledge exploration. DiscoverPath is open-sourced at https://github.com/ynchuang/DiscoverPath with a demo video at Youtube.

Stroke is one of the leading causes of death worldwide, and its mortality rate is drastically higher for patients who suffer recurrent strokes. Motivated by the recent success of graph learning methods on medical tasks, we introduce a graph representation framework for stroke recurrence prediction (GraSReP) based on patient data. In a nutshell, GraSReP sequentially consists of: i) a procedure for converting tabular, time-series patient data to a series of graphs, ii) a graph deep learning architecture that provides embeddings for the patients and, iii) a random forest classifier that predicts the patients’ risk of recurrent stroke based on these graph embeddings. We demonstrate GraSReP’s effectiveness for predicting recurrent strokes using real-world electronic health records, and discuss how it can be leveraged for the efficient application of preventive care.

Alzheimer's disease (AD) is one of the most challenging neurodegenerative diseases because of its complicated and progressive mechanisms, and multiple risk factors. Increasing research evidence demonstrates that genetics may be a key factor responsible for the occurrence of the disease. Although previous reports identified quite a few AD-associated genes, they were mostly limited owing to patient sample size and selection bias. There is a lack of comprehensive research aimed to identify AD-associated risk mutations systematically. To address this challenge, we hereby construct a large-scale AD mutation and co-mutation framework ('AD-Syn-Net'), and propose deep learning models named Deep-SMCI and Deep-CMCI configured with fully connected layers that are capable of predicting cognitive impairment of subjects effectively based on genetic mutation and co-mutation profiles. Next, we apply the customized frameworks to data sets to evaluate the importance scores of the mutations and identified mutation effectors and co-mutation combination vulnerabilities contributing to cognitive impairment. Furthermore, we evaluate the influence of mutation pairs on the network architecture to dissect the genetic organization of AD and identify novel co-mutations that could be responsible for dementia, laying a solid foundation for proposing future targeted therapy for AD precision medicine. Our deep learning model codes are available open access here: https://github.com/Pan-Bio/AD-mutation-effectors.

The rapid improvements in genomic sequencing technology have led to the proliferation of locally collected genomic datasets. Given the sensitivity of genomic data, it is crucial to conduct collaborative studies while preserving the privacy of the individuals. However, before starting any collaborative research effort, the quality of the data needs to be assessed. One of the essential steps of the quality control process is population stratification: identifying the presence of genetic difference in individuals due to subpopulations. One of the common methods used to group genomes of individuals based on ancestry is principal component analysis (PCA). In this article, we propose a privacy-preserving framework which utilizes PCA to assign individuals to populations across multiple collaborators as part of the population stratification step. In our proposed client-server-based scheme, we initially let the server train a global PCA model on a publicly available genomic dataset which contains individuals from multiple populations. The global PCA model is later used to reduce the dimensionality of the local data by each collaborator (client). After adding noise to achieve local differential privacy (LDP), the collaborators send metadata (in the form of their local PCA outputs) about their research datasets to the server, which then aligns the local PCA results to identify the genetic differences among collaborators' datasets. Our results on real genomic data show that the proposed framework can perform population stratification analysis with high accuracy while preserving the privacy of the research participants.

MOTIVATION: Genome-wide association studies (GWAS) benefit from the increasing availability of genomic data and cross-institution collaborations. However, sharing data across institutional boundaries jeopardizes medical data confidentiality and patient privacy. While modern cryptographic techniques provide formal secure guarantees, the substantial communication and computational overheads hinder the practical application of large-scale collaborative GWAS. RESULTS: This work introduces an efficient framework for conducting collaborative GWAS on distributed datasets, maintaining data privacy without compromising the accuracy of the results. We propose a novel two-step strategy aimed at reducing communication and computational overheads, and we employ iterative and sampling techniques to ensure accurate results. We instantiate our approach using logistic regression, a commonly used statistical method for identifying associations between genetic markers and the phenotype of interest. We evaluate our proposed methods using two real genomic datasets and demonstrate their robustness in the presence of between-study heterogeneity and skewed phenotype distributions using a variety of experimental settings. The empirical results show the efficiency and applicability of the proposed method and the promise for its application for large-scale collaborative GWAS. AVAILABILITY AND IMPLEMENTATION: The source code and data are available at https://github.com/amioamo/TDS.

BACKGROUND: Alzheimer's disease (AD) is a progressive neurological disorder with no specific curative medications. Sophisticated clinical skills are crucial to optimize treatment regimens given the multiple coexisting comorbidities in the patient population. OBJECTIVE: Here, we propose a study to leverage reinforcement learning (RL) to learn the clinicians' decisions for AD patients based on the longitude data from electronic health records. METHODS: In this study, we selected 1736 patients from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. We focused on the two most frequent concomitant diseases-depression, and hypertension, thus creating 5 data cohorts (ie, Whole Data, AD, AD-Hypertension, AD-Depression, and AD-Depression-Hypertension). We modeled the treatment learning into an RL problem by defining states, actions, and rewards. We built a regression model and decision tree to generate multiple states, used six combinations of medications (ie, cholinesterase inhibitors, memantine, memantine-cholinesterase inhibitors, hypertension drugs, supplements, or no drugs) as actions, and Mini-Mental State Exam (MMSE) scores as rewards. RESULTS: Given the proper dataset, the RL model can generate an optimal policy (regimen plan) that outperforms the clinician's treatment regimen. Optimal policies (ie, policy iteration and Q-learning) had lower rewards than the clinician's policy (mean -3.03 and -2.93 vs. -2.93, respectively) for smaller datasets but had higher rewards for larger datasets (mean -4.68 and -2.82 vs. -4.57, respectively). CONCLUSIONS: Our results highlight the potential of using RL to generate the optimal treatment based on the patients' longitude records. Our work can lead the path towards developing RL-based decision support systems that could help manage AD with comorbidities.

OBJECTIVE: Social determinants of health (SDoH) play critical roles in health outcomes and well-being. Understanding the interplay of SDoH and health outcomes is critical to reducing healthcare inequalities and transforming a "sick care" system into a "health-promoting" system. To address the SDOH terminology gap and better embed relevant elements in advanced biomedical informatics, we propose an SDoH ontology (SDoHO), which represents fundamental SDoH factors and their relationships in a standardized and measurable way. MATERIAL AND METHODS: Drawing on the content of existing ontologies relevant to certain aspects of SDoH, we used a top-down approach to formally model classes, relationships, and constraints based on multiple SDoH-related resources. Expert review and coverage evaluation, using a bottom-up approach employing clinical notes data and a national survey, were performed. RESULTS: We constructed the SDoHO with 708 classes, 106 object properties, and 20 data properties, with 1,561 logical axioms and 976 declaration axioms in the current version. Three experts achieved 0.967 agreement in the semantic evaluation of the ontology. A comparison between the coverage of the ontology and SDOH concepts in 2 sets of clinical notes and a national survey instrument also showed satisfactory results. DISCUSSION: SDoHO could potentially play an essential role in providing a foundation for a comprehensive understanding of the associations between SDoH and health outcomes and paving the way for health equity across populations. CONCLUSION: SDoHO has well-designed hierarchies, practical objective properties, and versatile functionalities, and the comprehensive semantic and coverage evaluation achieved promising performance compared to the existing ontologies relevant to SDoH.

OBJECTIVE: We aimed to develop a distributed, immutable, and highly available cross-cloud blockchain system to facilitate federated data analysis activities among multiple institutions. MATERIALS AND METHODS: We preprocessed 9166 COVID-19 Structured Query Language (SQL) code, summary statistics, and user activity logs, from the GitHub repository of the Reliable Response Data Discovery for COVID-19 (R2D2) Consortium. The repository collected local summary statistics from participating institutions and aggregated the global result to a COVID-19-related clinical query, previously posted by clinicians on a website. We developed both on-chain and off-chain components to store/query these activity logs and their associated queries/results on a blockchain for immutability, transparency, and high availability of research communication. We measured run-time efficiency of contract deployment, network transactions, and confirmed the accuracy of recorded logs compared to a centralized baseline solution. RESULTS: The smart contract deployment took 4.5 s on an average. The time to record an activity log on blockchain was slightly over 2 s, versus 5-9 s for baseline. For querying, each query took on an average less than 0.4 s on blockchain, versus around 2.1 s for baseline. DISCUSSION: The low deployment, recording, and querying times confirm the feasibility of our cross-cloud, blockchain-based federated data analysis system. We have yet to evaluate the system on a larger network with multiple nodes per cloud, to consider how to accommodate a surge in activities, and to investigate methods to lower querying time as the blockchain grows. CONCLUSION: Blockchain technology can be used to support federated data analysis among multiple institutions.

BACKGROUND: Estimation of genetic relatedness, or kinship, is used occasionally for recreational purposes and in forensic applications. While numerous methods were developed to estimate kinship, they suffer from high computational requirements and often make an untenable assumption of homogeneous population ancestry of the samples. Moreover, genetic privacy is generally overlooked in the usage of kinship estimation methods. There can be ethical concerns about finding unknown familial relationships in third-party databases. Similar ethical concerns may arise while estimating and reporting sensitive population-level statistics such as inbreeding coefficients for the concerns around marginalization and stigmatization. RESULTS: Here, we present SIGFRIED, which makes use of existing reference panels with a projection-based approach that simplifies kinship estimation in the admixed populations. We use simulated and real datasets to demonstrate the accuracy and efficiency of kinship estimation. We present a secure federated kinship estimation framework and implement a secure kinship estimator using homomorphic encryption-based primitives for computing relatedness between samples in two different sites while genotype data are kept confidential. Source code and documentation for our methods can be found at https://doi.org/10.5281/zenodo.7053352. CONCLUSIONS: Analysis of relatedness is fundamentally important for identifying relatives, in association studies, and for estimation of population-level estimates of inbreeding. As the awareness of individual and group genomic privacy is growing, privacy-preserving methods for the estimation of relatedness are needed. Presented methods alleviate the ethical and privacy concerns in the analysis of relatedness in admixed, historically isolated and underrepresented populations. SHORT ABSTRACT: Genetic relatedness is a central quantity used for finding relatives in databases, correcting biases in genome wide association studies and for estimating population-level statistics. Methods for estimating genetic relatedness have high computational requirements, and occasionally do not consider individuals from admixed ancestries. Furthermore, the ethical concerns around using genetic data and calculating relatedness are not considered. We present a projection-based approach that can efficiently and accurately estimate kinship. We implement our method using encryption-based techniques that provide provable security guarantees to protect genetic data while kinship statistics are computed among multiple sites.

MOTIVATION: Evaluating the blood-brain barrier (BBB) permeability of drug molecules is a critical step in brain drug development. Traditional methods for the evaluation require complicated in vitro or in vivo testing. Alternatively, in silico predictions based on machine learning have proved to be a cost-efficient way to complement the in vitro and in vivo methods. However, the performance of the established models has been limited by their incapability of dealing with the interactions between drugs and proteins, which play an important role in the mechanism behind the BBB penetrating behaviors. To address this limitation, we employed the relational graph convolutional network (RGCN) to handle the drug-protein interactions as well as the properties of each individual drug. RESULTS: The RGCN model achieved an overall accuracy of 0.872, an area under the receiver operating characteristic (AUROC) of 0.919 and an area under the precision-recall curve (AUPRC) of 0.838 for the testing dataset with the drug-protein interactions and the Mordred descriptors as the input. Introducing drug-drug similarity to connect structurally similar drugs in the data graph further improved the testing results, giving an overall accuracy of 0.876, an AUROC of 0.926 and an AUPRC of 0.865. In particular, the RGCN model was found to greatly outperform the LightGBM base model when evaluated with the drugs whose BBB penetration was dependent on drug-protein interactions. Our model is expected to provide high-confidence predictions of BBB permeability for drug prioritization in the experimental screening of BBB-penetrating drugs. AVAILABILITY AND IMPLEMENTATION: The data and the codes are freely available at https://github.com/dingyan20/BBB-Penetration-Prediction. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

BACKGROUND: Model card reports aim to provide informative and transparent description of machine learning models to stakeholders. This report document is of interest to the National Institutes of Health's Bridge2AI initiative to address the FAIR challenges with artificial intelligence-based machine learning models for biomedical research. We present our early undertaking in developing an ontology for capturing the conceptual-level information embedded in model card reports. RESULTS: Sourcing from existing ontologies and developing the core framework, we generated the Model Card Report Ontology. Our development efforts yielded an OWL2-based artifact that represents and formalizes model card report information. The current release of this ontology utilizes standard concepts and properties from OBO Foundry ontologies. Also, the software reasoner indicated no logical inconsistencies with the ontology. With sample model cards of machine learning models for bioinformatics research (HIV social networks and adverse outcome prediction for stent implantation), we showed the coverage and usefulness of our model in transforming static model card reports to a computable format for machine-based processing. CONCLUSIONS: The benefit of our work is that it utilizes expansive and standard terminologies and scientific rigor promoted by biomedical ontologists, as well as, generating an avenue to make model cards machine-readable using semantic web technology. Our future goal is to assess the veracity of our model and later expand the model to include additional concepts to address terminological gaps. We discuss tools and software that will utilize our ontology for potential application services.

BACKGROUND: Sequencing of thousands of samples provides genetic variants with allele frequencies spanning a very large spectrum and gives invaluable insight into genetic determinants of diseases. Protecting the genetic privacy of participants is challenging as only a few rare variants can easily re-identify an individual among millions. In certain cases, there are policy barriers against sharing genetic data from indigenous populations and stigmatizing conditions. RESULTS: We present SVAT, a method for secure outsourcing of variant annotation and aggregation, which are two basic steps in variant interpretation and detection of causal variants. SVAT uses homomorphic encryption to encrypt the data at the client-side. The data always stays encrypted while it is stored, in-transit, and most importantly while it is analyzed. SVAT makes use of a vectorized data representation to convert annotation and aggregation into efficient vectorized operations in a single framework. Also, SVAT utilizes a secure re-encryption approach so that multiple disparate genotype datasets can be combined for federated aggregation and secure computation of allele frequencies on the aggregated dataset. CONCLUSIONS: Overall, SVAT provides a secure, flexible, and practical framework for privacy-aware outsourcing of annotation, filtering, and aggregation of genetic variants. SVAT is publicly available for download from https://github.com/harmancilab/SVAT .

BACKGROUND: The decreasing cost of DNA sequencing has led to a great increase in our knowledge about genetic variation. While population-scale projects bring important insight into genotype-phenotype relationships, the cost of performing whole-genome sequencing on large samples is still prohibitive. In-silico genotype imputation coupled with genotyping-by-arrays is a cost-effective and accurate alternative for genotyping of common and uncommon variants. Imputation methods compare the genotypes of the typed variants with the large population-specific reference panels and estimate the genotypes of untyped variants by making use of the linkage disequilibrium patterns. Most accurate imputation methods are based on the Li-Stephens hidden Markov model, HMM, that treats the sequence of each chromosome as a mosaic of the haplotypes from the reference panel. RESULTS: Here we assess the accuracy of vicinity-based HMMs, where each untyped variant is imputed using the typed variants in a small window around itself (as small as 1 centimorgan). Locality-based imputation is used recently by machine learning-based genotype imputation approaches. We assess how the parameters of the vicinity-based HMMs impact the imputation accuracy in a comprehensive set of benchmarks and show that vicinity-based HMMs can accurately impute common and uncommon variants. CONCLUSIONS: Our results indicate that locality-based imputation models can be effectively used for genotype imputation. The parameter settings that we identified can be used in future methods and vicinity-based HMMs can be used for re-structuring and parallelizing new imputation methods. The source code for the vicinity-based HMM implementations is publicly available at https://github.com/harmancilab/LoHaMMer .

Technological advancements in data science have offered us affordable storage and efficient algorithms to query a large volume of data. Our health records are a significant part of this data, which is pivotal for healthcare providers and can be utilized in our well-being. The clinical note in electronic health records is one such category that collects a patient’s complete medical information during different timesteps of patient care available in the form of free-texts. Thus, these unstructured textual notes contain events from a patient’s admission to discharge, which can prove to be significant for future medical decisions. However, since these texts also contain sensitive information about the patient and the attending medical professionals, such notes cannot be shared publicly. This privacy issue has thwarted timely discoveries on this plethora of untapped information. Therefore, in this work, we intend to generate synthetic medical texts from a private or sanitized (de-identified) clinical text corpus and analyze their utility rigorously in different metrics and levels. Experimental results promote the applicability of our generated data as it achieves more than 80\% accuracy in different pragmatic classification problems and matches (or outperforms) the original text data.

Concerns regarding inappropriate leakage of sensitive personal information as well as unauthorized data use are increasing with the growth of genomic data repositories. Therefore, privacy and security of genomic data have become increasingly important and need to be studied. With many proposed protection techniques, their applicability in support of biomedical research should be well understood. For this purpose, we have organized a community effort in the past 8 years through the integrating data for analysis, anonymization and sharing consortium to address this practical challenge. In this article, we summarize our experience from these competitions, report lessons learned from the events in 2020/2021 as examples, and discuss potential future research directions in this emerging field.

Multi-task learning (MTL) refers to the paradigm of learning multiple related tasks together. In contrast, in single-task learning (STL) each individual task is learned independently. MTL often leads to better trained models because they can leverage the commonalities among related tasks. However, because MTL algorithms can "leak" information from different models across different tasks, MTL poses a potential security risk. Specifically, an adversary may participate in the MTL process through one task and thereby acquire the model information for another task. The previously proposed privacy-preserving MTL methods protect data instances rather than models, and some of them may underperform in comparison with STL methods. In this paper, we propose a privacy-preserving MTL framework to prevent information from each model leaking to other models based on a perturbation of the covariance matrix of the model matrix. We study two popular MTL approaches for instantiation, namely, learning the low-rank and group-sparse patterns of the model matrix. Our algorithms can be guaranteed not to underperform compared with STL methods. We build our methods based upon tools for differential privacy, and privacy guarantees, utility bounds are provided, and heterogeneous privacy budgets are considered. The experiments demonstrate that our algorithms outperform the baseline methods constructed by existing privacy-preserving MTL methods on the proposed model-protection problem.

Providing provenance in scientific workflows is essential for reproducibility and auditability purposes. In this work, we propose a framework that verifies the correctness of the aggregate statistics obtained as a result of a genome-wide association study (GWAS) conducted by a researcher while protecting individuals' privacy in the researcher's dataset. In GWAS, the goal of the researcher is to identify highly associated point mutations (variants) with a given phenotype. The researcher publishes the workflow of the conducted study, its output, and associated metadata. They keep the research dataset private while providing, as part of the metadata, a partial noisy dataset (that achieves local differential privacy). To check the correctness of the workflow output, a verifier makes use of the workflow, its metadata, and results of another GWAS (conducted using publicly available datasets) to distinguish between correct statistics and incorrect ones. For evaluation, we use real genomic data and show that the correctness of the workflow output can be verified with high accuracy even when the aggregate statistics of a small number of variants are provided. We also quantify the privacy leakage due to the provided workflow and its associated metadata and show that the additional privacy risk due to the provided metadata does not increase the existing privacy risk due to sharing of the research results. Thus, our results show that the workflow output (i.e., research results) can be verified with high confidence in a privacy-preserving way. We believe that this work will be a valuable step towards providing provenance in a privacy-preserving way while providing guarantees to the users about the correctness of the results.

The Cox proportional hazards model is a popular semi-parametric model for survival analysis. In this paper, we aim at developing a federated algorithm for the Cox proportional hazards model over vertically partitioned data (i.e., data from the same patient are stored at different institutions). We propose a novel algorithm, namely VERTICOX, to obtain the global model parameters in a distributed fashion based on the Alternating Direction Method of Multipliers (ADMM) framework. The proposed model computes intermediary statistics and exchanges them to calculate the global model without collecting individual patient-level data. We demonstrate that our algorithm achieves equivalent accuracy for the estimation of model parameters and statistics to that of its centralized realization. The proposed algorithm converges linearly under the ADMM framework. Its computational complexity and communication costs are polynomially and linearly associated with the number of subjects, respectively. Experimental results show that VERTICOX can achieve accurate model parameter estimation to support federated survival analysis over vertically distributed data by saving bandwidth and avoiding exchange of information about individual patients. The source code for VERTICOX is available at: https://github.com/daiwenrui/VERTICOX.

In this work, we propose a novel problem formulation for de-identification of unstructured clinical text. We formulate the de-identification problem as a sequence to sequence learning problem instead of a token classification problem. Our approach is inspired by the recent state-of -the-art performance of sequence to sequence learning models for named entity recognition. Early experimentation of our proposed approach achieved 98.91% recall rate on i2b2 dataset. This performance is comparable to current state-of-the-art models for unstructured clinical text de-identification.

Digitization of healthcare records contributed to a large volume of functional scientific data that can help researchers to understand the behaviour of many diseases. However, the privacy implications of this data, particularly genomics data, have surfaced recently as the collection, dissemination, and analysis of human genomics data is highly sensitive. There have been multiple privacy attacks relying on the uniqueness of the human genome that reveals a participant or a certain group’s presence in a dataset. Therefore, the current data sharing policies have ruled out any public dissemination and adopted precautionary measures prior to genomics data release, which hinders timely scientific innovation. In this article, we investigate an approach that only releases the statistics from genomic data rather than the whole dataset and propose a generalized Differentially Private mechanism for Genome-wide Association Studies (GWAS). Our method provides a quantifiable privacy guarantee that adds noise to the intermediate outputs but ensures satisfactory accuracy of the private results. Furthermore, the proposed method offers multiple adjustable parameters that the data owners can set based on the optimal privacy requirements. These variables are presented as equalizers that balance between the privacy and utility of the GWAS. The method also incorporates Online Bin Packing technique [1], which further bounds the privacy loss linearly, growing according to the number of open bins and scales with the incoming queries. Finally, we implemented and benchmarked our approach using seven different GWAS studies to test the performance of the proposed methods. The experimental results demonstrate that for 1,000 arbitrary online queries, our algorithms are more than 80% accurate with reasonable privacy loss and exceed the state-of-the-art approaches on multiple studies (i.e., EigenStrat, LMM, TDT).

OBJECTIVE: Clinical trials are an essential part of the effort to find safe and effective prevention and treatment for COVID-19. Given the rapid growth of COVID-19 clinical trials, there is an urgent need for a better clinical trial information retrieval tool that supports searching by specifying criteria, including both eligibility criteria and structured trial information. MATERIALS AND METHODS: We built a linked graph for registered COVID-19 clinical trials: the COVID-19 Trial Graph, to facilitate retrieval of clinical trials. Natural language processing tools were leveraged to extract and normalize the clinical trial information from both their eligibility criteria free texts and structured information from ClinicalTrials.gov. We linked the extracted data using the COVID-19 Trial Graph and imported it to a graph database, which supports both querying and visualization. We evaluated trial graph using case queries and graph embedding. RESULTS: The graph currently (as of October 5, 2020) contains 3392 registered COVID-19 clinical trials, with 17 480 nodes and 65 236 relationships. Manual evaluation of case queries found high precision and recall scores on retrieving relevant clinical trials searching from both eligibility criteria and trial-structured information. We observed clustering in clinical trials via graph embedding, which also showed superiority over the baseline (0.870 vs 0.820) in evaluating whether a trial can complete its recruitment successfully. CONCLUSIONS: The COVID-19 Trial Graph is a novel representation of clinical trials that allows diverse search queries and provides a graph-based visualization of COVID-19 clinical trials. High-dimensional vectors mapped by graph embedding for clinical trials would be potentially beneficial for many downstream applications, such as trial end recruitment status prediction and trial similarity comparison. Our methodology also is generalizable to other clinical trials.

OBJECTIVE: To utilize, in an individual and institutional privacy-preserving manner, electronic health record (EHR) data from 202 hospitals by analyzing answers to COVID-19-related questions and posting these answers online. MATERIALS AND METHODS: We developed a distributed, federated network of 12 health systems that harmonized their EHRs and submitted aggregate answers to consortia questions posted at https://www.covid19questions.org. Our consortium developed processes and implemented distributed algorithms to produce answers to a variety of questions. We were able to generate counts, descriptive statistics, and build a multivariate, iterative regression model without centralizing individual-level data. RESULTS: Our public website contains answers to various clinical questions, a web form for users to ask questions in natural language, and a list of items that are currently pending responses. The results show, for example, that patients who were taking angiotensin-converting enzyme inhibitors and angiotensin II receptor blockers, within the year before admission, had lower unadjusted in-hospital mortality rates. We also showed that, when adjusted for, age, sex, and ethnicity were not significantly associated with mortality. We demonstrated that it is possible to answer questions about COVID-19 using EHR data from systems that have different policies and must follow various regulations, without moving data out of their health systems. DISCUSSION AND CONCLUSIONS: We present an alternative or a complement to centralized COVID-19 registries of EHR data. We can use multivariate distributed logistic regression on observations recorded in the process of care to generate results without transferring individual-level data outside the health systems.

OBJECTIVE: Drug combination screening has advantages in identifying cancer treatment options with higher efficacy without degradation in terms of safety. A key challenge is that the accumulated number of observations in in-vitro drug responses varies greatly among different cancer types, where some tissues are more understudied than the others. Thus, we aim to develop a drug synergy prediction model for understudied tissues as a way of overcoming data scarcity problems. MATERIALS AND METHODS: We collected a comprehensive set of genetic, molecular, phenotypic features for cancer cell lines. We developed a drug synergy prediction model based on multitask deep neural networks to integrate multimodal input and multiple output. We also utilized transfer learning from data-rich tissues to data-poor tissues. RESULTS: We showed improved accuracy in predicting synergy in both data-rich tissues and understudied tissues. In data-rich tissue, the prediction model accuracy was 0.9577 AUROC for binarized classification task and 174.3 mean squared error for regression task. We observed that an adequate transfer learning strategy significantly increases accuracy in the understudied tissues. CONCLUSIONS: Our synergy prediction model can be used to rank synergistic drug combinations in understudied tissues and thus help to prioritize future in-vitro experiments. Code is available at https://github.com/yejinjkim/synergy-transfer.

OBJECTIVE: : Developing clinical natural language processing systems often requires access to many clinical documents, which are not widely available to the public due to privacy and security concerns. To address this challenge, we propose to develop methods to generate synthetic clinical notes and evaluate their utility in real clinical natural language processing tasks. MATERIALS AND METHODS: : We implemented 4 state-of-the-art text generation models, namely CharRNN, SegGAN, GPT-2, and CTRL, to generate clinical text for the History and Present Illness section. We then manually annotated clinical entities for randomly selected 500 History and Present Illness notes generated from the best-performing algorithm. To compare the utility of natural and synthetic corpora, we trained named entity recognition (NER) models from all 3 corpora and evaluated their performance on 2 independent natural corpora. RESULTS: : Our evaluation shows GPT-2 achieved the best BLEU (bilingual evaluation understudy) score (with a BLEU-2 of 0.92). NER models trained on synthetic corpus generated by GPT-2 showed slightly better performance on 2 independent corpora: strict F1 scores of 0.709 and 0.748, respectively, when compared with the NER models trained on natural corpus (F1 scores of 0.706 and 0.737, respectively), indicating the good utility of synthetic corpora in clinical NER model development. In addition, we also demonstrated that an augmented method that combines both natural and synthetic corpora achieved better performance than that uses the natural corpus only. CONCLUSIONS: : Recent advances in text generation have made it possible to generate synthetic clinical notes that could be useful for training NER models for information extraction from natural clinical notes, thus lowering the privacy concern and increasing data availability. Further investigation is needed to apply this technology to practice.

Deep learning models trained on large-scale data have achieved encouraging performance in many real-world tasks. Meanwhile, publishing those models trained on sensitive datasets, such as medical records, could pose serious privacy concerns. To counter these issues, one of the current state-of-the-art approaches is Private Aggregation of Teacher Ensembles, or PATE, which achieved promising results in preserving the utility of the model while providing a strong privacy guarantee. PATE combines an ensemble of "teacher models" trained on sensitive data and transfers the knowledge to a "student" model through the noisy aggregation of teachers' votes for labeling unlabeled public data which the student model will be trained on. However, the knowledge or voted labels learned by the student are noisy due to private aggregation. Learning directly from noisy labels can significantly impact the accuracy of the student model. In this paper, we propose the PATE++mechanism, which combines the current advanced noisy label training mechanisms co-teaching(+) with the original PATE framework to enhance its accuracy. A novel structure of Generative Adversarial Nets with one generator and two discriminators is developed in order to integrate them effectively. Furthermore, we discuss the intrinsic limitations of the "update-by-disagreement" method in the co-teaching+mechanism and develop a novel noisy label detection mechanism for semi-supervised model training to further improve student model performance when training with noisy labels. We evaluate our method on Fashion-MNIST and SVHN to show the improvements on the original PATE on all measures.

Clinical trials often require that patients meet eligibility criteria (e.g., have specific conditions) to ensure the safety and the effectiveness of studies. However, retrieving eligible patients for a trial from the electronic health record (EHR) database remains a challenging task for clinicians since it requires not only medical knowledge about eligibility criteria, but also an adequate understanding of structured query language (SQL). In this paper, we introduce a new dataset that includes the first-of-its-kind eligibility-criteria corpus and the corresponding queries for criteria-to-sql (Criteria2SQL), a task translating the eligibility criteria to executable SQL queries. Compared to existing datasets, the queries in the dataset here are derived from the eligibility criteria of clinical trials and include Order-sensitive, Counting-based, and Boolean-type cases which are not seen before. In addition to the dataset, we propose a novel neural semantic parser as a strong baseline model. Extensive experiments show that the proposed parser outperforms existing state-of-the-art general-purpose text-to-sql models while highlighting the challenges presented by the new dataset. The uniqueness and the diversity of the dataset leave a lot of research opportunities for future improvement.

OBJECTIVE: Survival analysis is the cornerstone of many healthcare applications in which the "survival" probability (eg, time free from a certain disease, time to death) of a group of patients is computed to guide clinical decisions. It is widely used in biomedical research and healthcare applications. However, frequent sharing of exact survival curves may reveal information about the individual patients, as an adversary may infer the presence of a person of interest as a participant of a study or of a particular group. Therefore, it is imperative to develop methods to protect patient privacy in survival analysis. MATERIALS AND METHODS: We develop a framework based on the formal model of differential privacy, which provides provable privacy protection against a knowledgeable adversary. We show the performance of privacy-protecting solutions for the widely used Kaplan-Meier nonparametric survival model. RESULTS: We empirically evaluated the usefulness of our privacy-protecting framework and the reduced privacy risk for a popular epidemiology dataset and a synthetic dataset. Results show that our methods significantly reduce the privacy risk when compared with their nonprivate counterparts, while retaining the utility of the survival curves. DISCUSSION: The proposed framework demonstrates the feasibility of conducting privacy-protecting survival analyses. We discuss future research directions to further enhance the usefulness of our proposed solutions in biomedical research applications. CONCLUSION: The results suggest that our proposed privacy-protection methods provide strong privacy protections while preserving the usefulness of survival analyses.

Large observational data networks that leverage routine clinical practice data in electronic health records (EHRs) are critical resources for research on coronavirus disease 2019 (COVID-19). Data normalization is a key challenge for the secondary use of EHRs for COVID-19 research across institutions. In this study, we addressed the challenge of automating the normalization of COVID-19 diagnostic tests, which are critical data elements, but for which controlled terminology terms were published after clinical implementation. We developed a simple but effective rule-based tool called COVID-19 TestNorm to automatically normalize local COVID-19 testing names to standard LOINC (Logical Observation Identifiers Names and Codes) codes. COVID-19 TestNorm was developed and evaluated using 568 test names collected from 8 healthcare systems. Our results show that it could achieve an accuracy of 97.4% on an independent test set. COVID-19 TestNorm is available as an open-source package for developers and as an online Web application for end users (https://clamp.uth.edu/covid/loinc.php). We believe that it will be a useful tool to support secondary use of EHRs for research on COVID-19.

OBJECTIVE: Recent studies on electronic health records (EHRs) started to learn deep generative models and synthesize a huge amount of realistic records, in order to address significant privacy issues surrounding the EHR. However, most of them only focus on structured records about patients' independent visits, rather than on chronological clinical records. In this article, we aim to learn and synthesize realistic sequences of EHRs based on the generative autoencoder. MATERIALS AND METHODS: We propose a dual adversarial autoencoder (DAAE), which learns set-valued sequences of medical entities, by combining a recurrent autoencoder with 2 generative adversarial networks (GANs). DAAE improves the mode coverage and quality of generated sequences by adversarially learning both the continuous latent distribution and the discrete data distribution. Using the MIMIC-III (Medical Information Mart for Intensive Care-III) and UT Physicians clinical databases, we evaluated the performances of DAAE in terms of predictive modeling, plausibility, and privacy preservation. RESULTS: Our generated sequences of EHRs showed the comparable performances to real data for a predictive modeling task, and achieved the best score in plausibility evaluation conducted by medical experts among all baseline models. In addition, differentially private optimization of our model enables to generate synthetic sequences without increasing the privacy leakage of patients' data. CONCLUSIONS: DAAE can effectively synthesize sequential EHRs by addressing its main challenges: the synthetic records should be realistic enough not to be distinguished from the real records, and they should cover all the training patients to reproduce the performance of specific downstream tasks.

Global pandemics call for large and diverse healthcare data to study various risk factors, treatment options, and disease progression patterns. Despite the enormous efforts of many large data consortium initiatives, scientific community still lacks a secure and privacy-preserving infrastructure to support auditable data sharing and facilitate automated and legally compliant federated analysis on an international scale. Existing health informatics systems do not incorporate the latest progress in modern security and federated machine learning algorithms, which are poised to offer solutions. An international group of passionate researchers came together with a joint mission to solve the problem with our finest models and tools. The SCOR Consortium has developed a ready-to-deploy secure infrastructure using world-class privacy and security technologies to reconcile the privacy/utility conflicts. We hope our effort will make a change and accelerate research in future pandemics with broad and diverse samples on an international scale.

Scientific collaborations benefit from sharing information and data from distributed sources, but protecting privacy is a major concern. Researchers, funders, and the public in general are getting increasingly worried about the potential leakage of private data. Advanced security methods have been developed to protect the storage and computation of sensitive data in a distributed setting. However, they do not protect against information leakage from the outcomes of data analyses. To address this aspect, studies on differential privacy (a state-of-the-art privacy protection framework) demonstrated encouraging results, but most of them do not apply to distributed scenarios. Combining security and privacy methodologies is a natural way to tackle the problem, but naive solutions may lead to poor analytical performance. In this paper, we introduce a novel strategy that combines differential privacy methods and homomorphic encryption techniques to achieve the best of both worlds. Using logistic regression (a popular model in biomedicine), we demonstrated the practicability of building secure and privacy-preserving models with high efficiency (less than 3 min) and good accuracy [<;1% of difference in the area under the receiver operating characteristic curve (AUC) against the global model] using a few real-world datasets.

Tensor factorization has been demonstrated as an efficient approach for computational phenotyping, where massive electronic health records (EHRs) are converted to concise and meaningful clinical concepts. While distributing the tensor factorization tasks to local sites can avoid direct data sharing, it still requires the exchange of intermediary results which could reveal sensitive patient information. Therefore, the challenge is how to jointly decompose the tensor under rigorous and principled privacy constraints, while still support the model's interpretability. We propose DPFact, a privacy-preserving collaborative tensor factorization method for computational phenotyping using EHR. It embeds advanced privacy-preserving mechanisms with collaborative learning. Hospitals can keep their EHR database private but also collaboratively learn meaningful clinical concepts by sharing differentially private intermediary results. Moreover, DPFact solves the heterogeneous patient population using a structured sparsity term. In our framework, each hospital decomposes its local tensors and sends the updated intermediary results with output perturbation every several iterations to a semi-trusted server which generates the phenotypes. The evaluation on both real-world and synthetic datasets demonstrated that under strict privacy constraints, our method is more accurate and communication-efficient than state-of-the-art baseline methods.

Genomic data hold salient information about the characteristics of a living organism. Throughout the past decade, pinnacle developments have given us more accurate and inexpensive methods to retrieve genome sequences of humans. However, with the advancement of genomic research, there is a growing privacy concern regarding the collection, storage and analysis of such sensitive human data. Recent results show that given some background information, it is possible for an adversary to reidentify an individual from a specific genomic data set. This can reveal the current association or future susceptibility of some diseases for that individual (and sometimes the kinship between individuals) resulting in a privacy violation. Regardless of these risks, our genomic data hold much importance in analyzing the well-being of us and the future generation. Thus, in this article, we discuss the different privacy and security-related problems revolving around human genomic data. In addition, we will explore some of the cardinal cryptographic concepts, which can bring efficacy in secure and private genomic data computation. This article will relate the gaps between these two research areas-Cryptography and Genomics.

Machine learning applications are intensively utilized in various science fields, and increasingly the biomedical and healthcare sector. Applying predictive modeling to biomedical data introduces privacy and security concerns requiring additional protection to prevent accidental disclosure or leakage of sensitive patient information. Significant advancements in secure computing methods have emerged in recent years, however, many of which require substantial computational and/or communication overheads, which might hinder their adoption in biomedical applications. In this work, we propose SecureLR, a novel framework allowing researchers to leverage both the computational and storage capacity of Public Cloud Servers to conduct learning and predictions on biomedical data without compromising data security or efficiency. Our model builds upon homomorphic encryption methodologies with hardware-based security reinforcement through Software Guard Extensions (SGX), and our implementation demonstrates a practical hybrid cryptographic solution to address important concerns in conducting machine learning with public clouds.

Recent studies demonstrate that effective healthcare can benefit from using the human genomic information. Consequently, many institutions are using statistical analysis of genomic data, which are mostly based on genome-wide association studies (GWAS). GWAS analyze genome sequence variations in order to identify genetic risk factors for diseases. These studies often require pooling data from different sources together in order to unravel statistical patterns, and relationships between genetic variants and diseases. Here, the primary challenge is to fulfill one major objective: accessing multiple genomic data repositories for collaborative research in a privacy-preserving manner. Due to the privacy concerns regarding the genomic data, multi-jurisdictional laws and policies of cross-border genomic data sharing are enforced among different countries. In this article, we present SAFETY, a hybrid framework, which can securely perform GWAS on federated genomic datasets using homomorphic encryption and recently introduced secure hardware component of Intel Software Guard Extensions to ensure high efficiency and privacy at the same time. Different experimental settings show the efficacy and applicability of such hybrid framework in secure conduction of GWAS. To the best of our knowledge, this hybrid use of homomorphic encryption along with Intel SGX is not proposed to this date. SAFETY is up to 4.82 times faster than the best existing secure computation technique.

Here present three articles on the private preservation of genome or electronic health record (EHR) data. Three articles focus on the algorithm developing for the analysis of GWAS and EHR-based phenotyping as well as electrocardiogram (ECG)-based disease recognition and classification. Here also include an article developing an algorithm for repositioning of old drugs for their new applications. The articles in this special section proposed several computational model and simulation methods to address diverse medical and healthcare issues which will be helpful to the promotion of the cross-disciplinary researches on the translational medicine and healthcare.

Homomorphic Encryption (HE) is a powerful cryptographic primitive to address privacy and security issues in outsourcing computation on sensitive data to an untrusted computation environment. Comparing to secure Multi-Party Computation (MPC), HE has advantages in supporting non-interactive operations and saving on communication costs. However, it has not come up with an optimal solution for modern learning frameworks, partially due to a lack of efficient matrix computation mechanisms. In this work, we present a practical solution to encrypt a matrix homomorphically and perform arithmetic operations on encrypted matrices. Our solution includes a novel matrix encoding method and an efficient evaluation strategy for basic matrix operations such as addition, multiplication, and transposition. We also explain how to encrypt more than one matrix in a single ciphertext, yielding better amortized performance. Our solution is generic in the sense that it can be applied to most of the existing HE schemes. It also achieves reasonable performance for practical use; for example, our implementation takes 9.21 seconds to multiply two encrypted square matrices of order 64 and 2.56 seconds to transpose a square matrix of order 64. Our secure matrix computation mechanism has a wide applicability to our new framework E2DM, which stands for encrypted data and encrypted model. To the best of our knowledge, this is the first work that supports secure evaluation of the prediction phase based on both encrypted data and encrypted model, whereas previous work only supported applying a plain model to encrypted data. As a benchmark, we report an experimental result to classify handwritten images using convolutional neural networks (CNN). Our implementation on the MNIST dataset takes 28.59 seconds to compute ten likelihoods of 64 input images simultaneously, yielding an amortized rate of 0.45 seconds per image.

For the purpose of research, organizations often need to share and link data belonging to a single individual while protecting her privacy. This problem, referred to as privacy preserving record linkage (PPRL), has been investigated by researchers. Most PPRL works focus on deterministic linkages where the identifying attributes of two records must be equal in order to declare them to belong to the same individual. Moreover, most of these methods require the active participation of a trusted third party (TTP). If this TTP is compromised, it makes the data from all participating parties vulnerable to information leakage. The proposed work improves upon the existing methods in two ways. First, we propose a protocol which does not require two records to have an exact match on identifying attributes in order to be declared as belonging to the same individual. Second, we investigate probabilistic PPRL in the two-party setting without resorting to any TTP. We use Bloom filters for probabilistic matching and Yao's garbled circuit to perform the computation needed for the matching on encrypted data. To alleviate the computation and communication overhead of Yao's protocol, we leverage data blocking methods and optimize the computation. We provide a security proof of our method and experimentally evaluate the performance gained on large benchmark datasets.

Gaining knowledge and actionable insights from complex, high-dimensional and heterogeneous biomedical data remains a key challenge in transforming health care. Various types of data have been emerging in modern biomedical research, including electronic health records, imaging, -omics, sensor data and text, which are complex, heterogeneous, poorly annotated and generally unstructured. Traditional data mining and statistical learning approaches typically need to first perform feature engineering to obtain effective and more robust features from those data, and then build prediction or clustering models on top of them. There are lots of challenges on both steps in a scenario of complicated data and lacking of sufficient domain knowledge. The latest advances in deep learning technologies provide new effective paradigms to obtain end-to-end learning models from complex data. In this article, we review the recent literature on applying deep learning technologies to advance the health care domain. Based on the analyzed work, we suggest that deep learning approaches could be the vehicle for translating big biomedical data into improved human health. However, we also note limitations and needs for improved methods development and applications, especially in terms of ease-of-understanding for domain experts and citizen scientists. We discuss such challenges and suggest developing holistic and meaningful interpretable architectures to bridge deep learning models and human interpretability.

The three papers included this special section were presented at the 3rd International Workshop on Genome Privacy and Security (GenoPri) in 2016. GenoPri’16 was collocated with the American Medical Informatics Association Annual Fall Symposium (AMIA), a premier medical informatics venue.

Privacy concern in data sharing especially for health data gains particularly increasing attention nowadays. Now some patients agree to open their information for research use, which gives rise to a new question of how to effectively use the public information to better understand the private dataset without breaching privacy. In this paper, we specialize this question as selecting an optimal subset of the public dataset for M-estimators in the framework of differential privacy (DP) in [1]. From a perspective of non-interactive learning, we first construct the weighted private density estimation from the hybrid datasets under DP. Along the same line as [2], we analyze the accuracy of the DP M-estimators based on the hybrid datasets. Our main contributions are (i) we find that the bias-variance tradeoff in the performance of our M-estimators can be characterized in the sample size of the released dataset; (2) based on this finding, we develop an algorithm to select the optimal subset of the public dataset to release under DP. Our simulation studies and application to the real datasets confirm our findings and set a guideline in the real application.

Differential diagnosis is detection of one disease among similar diseases using evidence such as pathologic tests. A Partially Observed Markov Decision Process (POMDP) formulates the complex differential diagnosis process into a probabilistic decision-making model. However, differential diagnosis is not often fully formulated as POMDP because model construction does not consider the cost (or time) to finish the diagnosis process, or the practical convention on clinical tests. We propose a Diagnostic Tree (DiagTree), a new framework for diagnosing diseases, which combines several tests to reduce the diagnosis time and to incorporate real-world constraints into discrete optimization. DiagTree consists of multiple tests in internal nodes and posterior probabilities ("confidences") that the patient suffers the disease listed at each leaf node. The confidences are computed after a series of test results is applied in internal nodes. DiagTree is built to maximize the confidences at leaf nodes and to minimize the decision process time. We formulate this problem as integer programming and solve it by the Branch-and-Bound method and a greedy approach. We apply DiagTree to immunohistochemistry profiles to detect lymphoid neoplasms. We evaluate the accuracy and cost of the diagnosis rules from DiagTree compared to those obtained using rules that clinicians derived from their experience. DiagTree detected diseases with high accuracy and also reduced the diagnosis cost (or time) compared to the existing rules of clinicians. DiagTree can support clinicians by suggesting a simple diagnosis process with high accuracy and low cost among test candidates.

The study of patients in Intensive Care Units (ICUs) is a crucial task in critical care research which has significant implications both in identifying clinical risk factors and defining institutional guidances. The mortality study of ICU patients is of particular interest because it provides useful indications to healthcare institutions for improving patients experience, internal policies, and procedures (e.g. allocation of resources). To this end, many research works have been focused on the length of stay (LOS) for ICU patients as a feature for studying the mortality. In this work, we propose a novel mortality study based on the notion of burstiness, where the temporal information of patients longitudinal data is taken into consideration. The burstiness of temporal data is a popular measure in network analysis and time-series anomaly detection, where high values of burstiness indicate presence of rapidly occurring events in short time periods (i.e. burst). Our intuition is that these bursts may relate to possible complications in the patient's medical condition and hence provide indications on the mortality. Compared to the LOS, the burstiness parameter captures the temporality of the medical events providing information about the overall dynamic of the patients condition. To the best of our knowledge, we are the first to apply the burstiness measure in the clinical research domain. Our preliminary results on a real dataset show that patients with high values of burstiness tend to have higher mortality rate compared to patients with more regular medical events. Overall, our study shows promising results and provides useful insights for developing predictive models on temporal data and advancing modern critical care medicine.

Tensor factorization models offer an effective approach to convert massive electronic health records into meaningful clinical concepts (phenotypes) for data analysis. These models need a large amount of diverse samples to avoid population bias. An open challenge is how to derive phenotypes jointly across multiple hospitals, in which direct patient-level data sharing is not possible (e.g., due to institutional policies). In this paper, we developed a novel solution to enable federated tensor factorization for computational phenotyping without sharing patient-level data. We developed secure data harmonization and federated computation procedures based on alternating direction method of multipliers (ADMM). Using this method, the multiple hospitals iteratively update tensors and transfer secure summarized information to a central server, and the server aggregates the information to generate phenotypes. We demonstrated with real medical datasets that our method resembles the centralized training model (based on combined datasets) in terms of accuracy and phenotypes discovery while respecting privacy.

Motivation: We introduce PRINCESS, a privacy-preserving international collaboration framework for analyzing rare disease genetic data that are distributed across different continents. PRINCESS leverages Software Guard Extensions (SGX) and hardware for trustworthy computation. Unlike a traditional international collaboration model, where individual-level patient DNA are physically centralized at a single site, PRINCESS performs a secure and distributed computation over encrypted data, fulfilling institutional policies and regulations for protected health information. Results: To demonstrate PRINCESS' performance and feasibility, we conducted a family-based allelic association study for Kawasaki Disease, with data hosted in three different continents. The experimental results show that PRINCESS provides secure and accurate analyses much faster than alternative solutions, such as homomorphic encryption and garbled circuits (over 40 000× faster). Availability and Implementation: https://github.com/achenfengb/PRINCESS_opensource. Contact: [email protected]. Supplementary information: Supplementary data are available at Bioinformatics online.

MOTIVATION: Inappropriate disclosure of human genomes may put the privacy of study subjects and of their family members at risk. Existing privacy-preserving mechanisms for Genome-Wide Association Studies (GWAS) mainly focus on protecting individual information in case-control studies. Protecting privacy in family-based studies is more difficult. The transmission disequilibrium test (TDT) is a powerful family-based association test employed in many rare disease studies. It gathers information about families (most frequently involving parents, affected children and their siblings). It is important to develop privacy-preserving approaches to disclose TDT statistics with a guarantee that the risk of family 're-identification' stays below a pre-specified risk threshold. 'Re-identification' in this context means that an attacker can infer that the presence of a family in a study. METHODS: In the context of protecting family-level privacy, we developed and evaluated a suite of differentially private (DP) mechanisms for TDT. They include Laplace mechanisms based on the TDT test statistic, P-values, projected P-values and exponential mechanisms based on the TDT test statistic and the shortest Hamming distance (SHD) score. RESULTS: Using simulation studies with a small cohort and a large one, we showed that that the exponential mechanism based on the SHD score preserves the highest utility and privacy among all proposed DP methods. We provide a guideline on applying our DP TDT in a real dataset in analyzing Kawasaki disease with 187 families and 906 SNPs. There are some limitations, including: (1) the performance of our implementation is slow for real-time results generation and (2) handling missing data is still challenging. AVAILABILITY AND IMPLEMENTATION: The software dpTDT is available in https://github.com/mwgrassgreen/dpTDT. CONTACT: [email protected]. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

The Global Alliance for Genomics and Health (GA4GH) created the Beacon Project as a means of testing the willingness of data holders to share genetic data in the simplest technical context-a query for the presence of a specified nucleotide at a given position within a chromosome. Each participating site (or "beacon") is responsible for assuring that genomic data are exposed through the Beacon service only with the permission of the individual to whom the data pertains and in accordance with the GA4GH policy and standards.While recognizing the inference risks associated with large-scale data aggregation, and the fact that some beacons contain sensitive phenotypic associations that increase privacy risk, the GA4GH adjudged the risk of re-identification based on the binary yes/no allele-presence query responses as acceptable. However, recent work demonstrated that, given a beacon with specific characteristics (including relatively small sample size and an adversary who possesses an individual's whole genome sequence), the individual's membership in a beacon can be inferred through repeated queries for variants present in the individual's genome.In this paper, we propose three practical strategies for reducing re-identification risks in beacons. The first two strategies manipulate the beacon such that the presence of rare alleles is obscured; the third strategy budgets the number of accesses per user for each individual genome. Using a beacon containing data from the 1000 Genomes Project, we demonstrate that the proposed strategies can effectively reduce re-identification risk in beacon-like datasets.

Dictionary learning has emerged as a promising alternative to the conventional hybrid coding framework. However, the rigid structure of sequential training and prediction degrades its performance in scalable video coding. This paper proposes a progressive dictionary learning framework with hierarchical predictive structure for scalable video coding, especially in low bitrate region. For pyramidal layers, sparse representation based on spatio-temporal dictionary is adopted to improve the coding efficiency of enhancement layers with a guarantee of reconstruction performance. The overcomplete dictionary is trained to adaptively capture local structures along motion trajectories as well as exploit the correlations between the neighboring layers of resolutions. Furthermore, progressive dictionary learning is developed to enable the scalability in temporal domain and restrict the error propagation in a closed-loop predictor. Under the hierarchical predictive structure, online learning is leveraged to guarantee the training and prediction performance with an improved convergence rate. To accommodate with the state-of-the-art scalable extension of H.264/AVC and latest High Efficiency Video Coding (HEVC), standardized codec cores are utilized to encode the base and enhancement layers. Experimental results show that the proposed method outperforms the latest scalable extension of HEVC and HEVC simulcast over extensive test sequences with various resolutions.

Applications of genomic studies are spreading rapidly in many domains of science and technology such as healthcare, biomedical research, direct-to-consumer services, and legal and forensic. However, there are a number of obstacles that make it hard to access and process a big genomic database for these applications. First, sequencing genomic sequence is a time consuming and expensive process. Second, it requires large-scale computation and storage systems to process genomic sequences. Third, genomic databases are often owned by different organizations, and thus, not available for public usage. Cloud computing paradigm can be leveraged to facilitate the creation and sharing of big genomic databases for these applications. Genomic data owners can outsource their databases in a centralized cloud server to ease the access of their databases. However, data owners are reluctant to adopt this model, as it requires outsourcing the data to an untrusted cloud service provider that may cause data breaches. In this paper, we propose a privacy-preserving model for outsourcing genomic data to a cloud. The proposed model enables query processing while providing privacy protection of genomic databases. Privacy of the individuals is guaranteed by permuting and adding fake genomic records in the database. These techniques allow cloud to evaluate count and top-k queries securely and efficiently. Experimental results demonstrate that a count and a top-k query over 40 Single Nucleotide Polymorphisms (SNPs) in a database of 20 000 records takes around 100 and 150 s, respectively.

MOTIVATION: Genome-wide association studies (GWAS) have been widely used in discovering the association between genotypes and phenotypes. Human genome data contain valuable but highly sensitive information. Unprotected disclosure of such information might put individual's privacy at risk. It is important to protect human genome data. Exact logistic regression is a bias-reduction method based on a penalized likelihood to discover rare variants that are associated with disease susceptibility. We propose the HEALER framework to facilitate secure rare variants analysis with a small sample size. RESULTS: We target at the algorithm design aiming at reducing the computational and storage costs to learn a homomorphic exact logistic regression model (i.e. evaluate P-values of coefficients), where the circuit depth is proportional to the logarithmic scale of data size. We evaluate the algorithm performance using rare Kawasaki Disease datasets. AVAILABILITY AND IMPLEMENTATION: Download HEALER at http://research.ucsd-dbmi.org/HEALER/ CONTACT: [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

OBJECTIVE: To develop an accurate logistic regression (LR) algorithm to support federated data analysis of vertically partitioned distributed data sets. MATERIAL AND METHODS: We propose a novel technique that solves the binary LR problem by dual optimization to obtain a global solution for vertically partitioned data. We evaluated this new method, VERTIcal Grid lOgistic regression (VERTIGO), in artificial and real-world medical classification problems in terms of the area under the receiver operating characteristic curve, calibration, and computational complexity. We assumed that the institutions could "align" patient records (through patient identifiers or hashed "privacy-protecting" identifiers), and also that they both had access to the values for the dependent variable in the LR model (eg, that if the model predicts death, both institutions would have the same information about death). RESULTS: The solution derived by VERTIGO has the same estimated parameters as the solution derived by applying classical LR. The same is true for discrimination and calibration over both simulated and real data sets. In addition, the computational cost of VERTIGO is not prohibitive in practice. DISCUSSION: There is a technical challenge in scaling up federated LR for vertically partitioned data. When the number of patients m is large, our algorithm has to invert a large Hessian matrix. This is an expensive operation of time complexity O(m(3)) that may require large amounts of memory for storage and exchange of information. The algorithm may also not work well when the number of observations in each class is highly imbalanced. CONCLUSION: The proposed VERTIGO algorithm can generate accurate global models to support federated data analysis of vertically partitioned data.

Differential privacy has recently become a de facto standard for private statistical data release. Many algorithms have been proposed to generate differentially private histograms or synthetic data. However, most of them focus on "one-time" release of a static dataset and do not adequately address the increasing need of releasing series of dynamic datasets in real time. A straightforward application of existing histogram methods on each snapshot of such dynamic datasets will incur high accumulated error due to the composibility of differential privacy and correlations or overlapping users between the snapshots. In this paper, we address the problem of releasing series of dynamic datasets in real time with differential privacy, using a novel adaptive distance-based sampling approach. Our first method, DSFT, uses a fixed distance threshold and releases a differentially private histogram only when the current snapshot is sufficiently different from the previous one, i.e., with a distance greater than a predefined threshold. Our second method, DSAT, further improves DSFT and uses a dynamic threshold adaptively adjusted by a feedback control mechanism to capture the data dynamics. Extensive experiments on real and synthetic datasets demonstrate that our approach achieves better utility than baseline methods and existing state-of-the-art methods.

Matrix factorization is one of the fundamental techniques for analyzing latent relationship between two entities. Especially, it is used for recommendation for its high accuracy. Efficient parallel SGD matrix factorization algorithms have been developed for large matrices to speed up the convergence of factorization. However, most of them are designed for a shared-memory environment thus fail to factorize a large matrix that is too big to fit in memory, and their performances are also unreliable when the matrix is skewed.

Biomedical Informatics is a growing interdisciplinary field in which research topics and citation trends have been evolving rapidly in recent years. To analyze these data in a fast, reproducible manner, automation of certain processes is needed. JAMIA is a "generalist" journal for biomedical informatics. Its articles reflect the wide range of topics in informatics. In this study, we retrieved Medical Subject Headings (MeSH) terms and citations of JAMIA articles published between 2009 and 2014. We use tensors (i.e., multidimensional arrays) to represent the interaction among topics, time and citations, and applied tensor decomposition to automate the analysis. The trends represented by tensors were then carefully interpreted and the results were compared with previous findings based on manual topic analysis. A list of most cited JAMIA articles, their topics, and publication trends over recent years is presented. The analyses confirmed previous studies and showed that, from 2012 to 2014, the number of articles related to MeSH terms Methods, Organization & Administration, and Algorithms increased significantly both in number of publications and citations. Citation trends varied widely by topic, with Natural Language Processing having a large number of citations in particular years, and Medical Record Systems, Computerized remaining a very popular topic in all years.

OBJECTIVE: The Cox proportional hazards model is a widely used method for analyzing survival data. To achieve sufficient statistical power in a survival analysis, it usually requires a large amount of data. Data sharing across institutions could be a potential workaround for providing this added power. METHODS AND MATERIALS: The authors develop a web service for distributed Cox model learning (WebDISCO), which focuses on the proof-of-concept and algorithm development for federated survival analysis. The sensitive patient-level data can be processed locally and only the less-sensitive intermediate statistics are exchanged to build a global Cox model. Mathematical derivation shows that the proposed distributed algorithm is identical to the centralized Cox model. RESULTS: The authors evaluated the proposed framework at the University of California, San Diego (UCSD), Emory, and Duke. The experimental results show that both distributed and centralized models result in near-identical model coefficients with differences in the range [Formula: see text] to [Formula: see text]. The results confirm the mathematical derivation and show that the implementation of the distributed model can achieve the same results as the centralized implementation. LIMITATION: The proposed method serves as a proof of concept, in which a publicly available dataset was used to evaluate the performance. The authors do not intend to suggest that this method can resolve policy and engineering issues related to the federated use of institutional data, but they should serve as evidence of the technical feasibility of the proposed approach.Conclusions WebDISCO (Web-based Distributed Cox Regression Model; https://webdisco.ucsd-dbmi.org:8443/cox/) provides a proof-of-concept web service that implements a distributed algorithm to conduct distributed survival analysis without sharing patient level data.

BACKGROUND: Centralized and federated models for sharing data in research networks currently exist. To build multivariate data analysis for centralized networks, transfer of patient-level data to a central computation resource is necessary. The authors implemented distributed multivariate models for federated networks in which patient-level data is kept at each site and data exchange policies are managed in a study-centric manner. OBJECTIVE: The objective was to implement infrastructure that supports the functionality of some existing research networks (e.g., cohort discovery, workflow management, and estimation of multivariate analytic models on centralized data) while adding additional important new features, such as algorithms for distributed iterative multivariate models, a graphical interface for multivariate model specification, synchronous and asynchronous response to network queries, investigator-initiated studies, and study-based control of staff, protocols, and data sharing policies. MATERIALS AND METHODS: Based on the requirements gathered from statisticians, administrators, and investigators from multiple institutions, the authors developed infrastructure and tools to support multisite comparative effectiveness studies using web services for multivariate statistical estimation in the SCANNER federated network. RESULTS: The authors implemented massively parallel (map-reduce) computation methods and a new policy management system to enable each study initiated by network participants to define the ways in which data may be processed, managed, queried, and shared. The authors illustrated the use of these systems among institutions with highly different policies and operating under different state laws. DISCUSSION AND CONCLUSION: Federated research networks need not limit distributed query functionality to count queries, cohort discovery, or independently estimated analytic models. Multivariate analyses can be efficiently and securely conducted without patient-level data transport, allowing institutions with strict local data storage requirements to participate in sophisticated analyses based on federated research networks.

OBJECTIVE: To propose a new approach to privacy preserving data selection, which helps the data users access human genomic datasets efficiently without undermining patients' privacy. METHODS: Our idea is to let each data owner publish a set of differentially-private pilot data, on which a data user can test-run arbitrary association-test algorithms, including those not known to the data owner a priori. We developed a suite of new techniques, including a pilot-data generation approach that leverages the linkage disequilibrium in the human genome to preserve both the utility of the data and the privacy of the patients, and a utility evaluation method that helps the user assess the value of the real data from its pilot version with high confidence. RESULTS: We evaluated our approach on real human genomic data using four popular association tests. Our study shows that the proposed approach can help data users make the right choices in most cases. CONCLUSIONS: Even though the pilot data cannot be directly used for scientific discovery, it provides a useful indication of which datasets are more likely to be useful to data users, who can therefore approach the appropriate data owners to gain access to the data.

Summary form only given. This paper proposes a novel multiscale online dictionary learning algorithm with double sparsity structure for scalable video coding. Along hierarchical structures on the feature set by wavelet transform, the search space of online learning is optimized to sub-blocks for hierarchical sparsity. The group sparsity is exploited on lowest sub-band in the base layer to obtain the low-frequency sub-dictionary and sparse coefficient. We also designed cross-scale decomposition and reconstruction, for which the recovery error can be bounded. The dictionary is updated by stochastic gradient descent to optimize the expected cost. Hierarchical high-frequency information is predicted from a pre-learned corresponding sub-dictionary pairs for scalable coding. We demonstrated that the proposed algorithm can achieve scalable signal to noise ratio (SNR).

Differential privacy has recently emerged in private statistical data release as one of the strongest privacy guarantees. Most of the existing techniques that generate differentially private histograms or synthetic data only work well for single dimensional or low-dimensional histograms. They become problematic for high dimensional and large domain data due to increased perturbation error and computation complexity. In this paper, we propose DPCopula, a differentially private data synthesization technique using Copula functions for multi-dimensional data. The core of our method is to compute a differentially private copula function from which we can sample synthetic data. Copula functions are used to describe the dependence between multivariate random vectors and allow us to build the multivariate joint distribution using one-dimensional marginal distributions. We present two methods for estimating the parameters of the copula functions with differential privacy: maximum likelihood estimation and Kendall's τ estimation. We present formal proofs for the privacy guarantee as well as the convergence property of our methods. Extensive experiments using both real datasets and synthetic datasets demonstrate that DPCopula generates highly accurate synthetic multi-dimensional data with significantly better utility than state-of-the-art techniques.

The database of genotypes and phenotypes (dbGaP) developed by the National Center for Biotechnology Information (NCBI) is a resource that contains information on various genome-wide association studies (GWAS) and is currently available via NCBI's dbGaP Entrez interface. The database is an important resource, providing GWAS data that can be used for new exploratory research or cross-study validation by authorized users. However, finding studies relevant to a particular phenotype of interest is challenging, as phenotype information is presented in a non-standardized way. To address this issue, we developed PhenDisco (phenotype discoverer), a new information retrieval system for dbGaP. PhenDisco consists of two main components: (1) text processing tools that standardize phenotype variables and study metadata, and (2) information retrieval tools that support queries from users and return ranked results. In a preliminary comparison involving 18 search scenarios, PhenDisco showed promising performance for both unranked and ranked search comparisons with dbGaP's search engine Entrez. The system can be accessed at http://pfindr.net.

BACKGROUND AND OBJECTIVE: Short-read sequencing is becoming the standard of practice for the study of structural variants associated with disease. However, with the growth of sequence data largely surpassing reasonable storage capability, the biomedical community is challenged with the management, transfer, archiving, and storage of sequence data. METHODS: We developed Hierarchical mUlti-reference Genome cOmpression (HUGO), a novel compression algorithm for aligned reads in the sorted Sequence Alignment/Map (SAM) format. We first aligned short reads against a reference genome and stored exactly mapped reads for compression. For the inexact mapped or unmapped reads, we realigned them against different reference genomes using an adaptive scheme by gradually shortening the read length. Regarding the base quality value, we offer lossy and lossless compression mechanisms. The lossy compression mechanism for the base quality values uses k-means clustering, where a user can adjust the balance between decompression quality and compression rate. The lossless compression can be produced by setting k (the number of clusters) to the number of different quality values. RESULTS: The proposed method produced a compression ratio in the range 0.5-0.65, which corresponds to 35-50% storage savings based on experimental datasets. The proposed approach achieved 15% more storage savings over CRAM and comparable compression ratio with Samcomp (CRAM and Samcomp are two of the state-of-the-art genome compression algorithms). The software is freely available at https://sourceforge.net/projects/hierachicaldnac/with a General Public License (GPL) license. LIMITATION: Our method requires having different reference genomes and prolongs the execution time for additional alignments. CONCLUSIONS: The proposed multi-reference-based compression algorithm for aligned reads outperforms existing single-reference based algorithms.

Differential privacy has recently emerged in private statistical data release as one of the strongest privacy guarantees. Releasing synthetic data that mimic original data with Differential privacy provides a promising way for privacy preserving data sharing and analytics while providing a rigorous privacy guarantee. However, to this date there is no open-source tools that allow users to generate differentially private synthetic data, in particular, for high dimensional and large domain data. Most of the existing techniques that generate differentially private histograms or synthetic data only work well for single dimensional or low-dimensional histograms. They become problematic for high dimensional and large domain data due to increased perturbation error and computation complexity. We propose DPSynthesizer, a toolkit for differentially private data synthesization. The core of DPSynthesizer is DPCopula designed for high-dimensional and large-domain data. DPCopula computes a differentially private copula function from which synthetic data can be sampled. Copula functions are used to describe the dependence between multivariate random vectors and allow us to build the multivariate joint distribution using one-dimensional marginal distributions. DPSynthesizer also implements a set of state-of-the-art methods for building differentially private histograms, suitable for low-dimensional data, from which synthetic data can be generated. We will demonstrate the system using DPCopula as well as other methods with various data sets and show the feasibility, utility, and efficiency of various methods.

Detecting generic object categories in images and videos are a fundamental issue in computer vision. However, it faces the challenges from inter and intraclass diversity, as well as distortions caused by viewpoints, poses, deformations, and so on. To solve object variations, this paper constructs a structure kernel and proposes a multiscale part-based model incorporating the discriminative power of kernels. The structure kernel would measure the resemblance of part-based objects in three aspects: 1) the global similarity term to measure the resemblance of the global visual appearance of relevant objects; 2) the part similarity term to measure the resemblance of the visual appearance of distinctive parts; and 3) the spatial similarity term to measure the resemblance of the spatial layout of parts. In essence, the deformation of parts in the structure kernel is penalized in a multiscale space with respect to horizontal displacement, vertical displacement, and scale difference. Part similarities are combined with different weights, which are optimized efficiently to maximize the intraclass similarities and minimize the interclass similarities by the normalized stochastic gradient ascent algorithm. In addition, the parameters of the structure kernel are learned during the training process with regard to the distribution of the data in a more discriminative way. With flexible part sizes on scale and displacement, it can be more robust to the intraclass variations, poses, and viewpoints. Theoretical analysis and experimental evaluations demonstrate that the proposed multiscale part-based representation model with structure kernel exhibits accurate and robust performance, and outperforms state-of-the-art object classification approaches.

Identifying drug-drug interactions is an important and challenging problem in computational biology and healthcare research. There are accurate, structured but limited domain knowledge and noisy, unstructured but abundant textual information available for building predictive models. The difficulty lies in mining the true patterns embedded in text data and developing efficient and effective ways to combine heterogenous types of information. We demonstrate a novel approach of leveraging augmented text-mining features to build a logistic regression model with improved prediction performance (in terms of discrimination and calibration). Our model based on synthesized features significantly outperforms the model trained with only structured features (AUC: 96% vs. 91%, Sensitivity: 90% vs. 82% and Specificity: 88% vs. 81%). Along with the quantitative results, we also show learned "latent topics", an intermediary result of our text mining module, and discuss their implications.

Previous reference-based compression on DNA sequences do not fully exploit the intrinsic statistics by merely concerning the approximate matches. In this paper, an adaptive difference distribution-based coding framework is proposed by the fragments of nucleotides with a hierarchical tree structure. To keep the distribution of difference sequence from the reference and target sequences concentrated, the sub-fragment size and matching offset for predicting are flexible to the stepped size structure. The matching with approximate repeats in reference will be imposed with the Hamming-like weighted distance measure function in a local region closed to the current fragment, such that the accuracy of matching and the overhead of describing matching offset can be balanced. A well-designed coding scheme will make compact both the difference sequence and the additional parameters, e.g. sub-fragment size and matching offset. Experimental results show that the proposed scheme achieves 150% compression improvement in comparison with the best reference-based compressor GReEn.

In this paper, we develop a novel genome compression framework based on distributed source coding (DSC)[3], which is specially tailored to the need of miniaturized devices. At the encoder side, subsequences with adaptive code length can be compressed flexibly through either low complexity DSC based syndrome coding or hash coding with the decision determined by the existence of variations between source and reference known from the decoder feedback. Moreover, to tackle the variations between source and reference at the decoder, we carefully designed a factor graph based low-density parity-check (LDPC) decoder, which automatically detects insertion, deletion and substitution.

UNLABELLED: WebGLORE is a free web service that enables privacy-preserving construction of a global logistic regression model from distributed datasets that are sensitive. It only transfers aggregated local statistics (from participants) through Hypertext Transfer Protocol Secure to a trusted server, where the global model is synthesized. WebGLORE seamlessly integrates AJAX, JAVA Applet/Servlet and PHP technologies to provide an easy-to-use web service for biomedical researchers to break down policy barriers during information exchange. AVAILABILITY AND IMPLEMENTATION: http://dbmi-engine.ucsd.edu/webglore3/. WebGLORE can be used under the terms of GNU general public license as published by the Free Software Foundation.

OBJECTIVES: We present SHARE, a new system for statistical health information release with differential privacy. We present two case studies that evaluate the software on real medical datasets and demonstrate the feasibility and utility of applying the differential privacy framework on biomedical data. MATERIALS AND METHODS: SHARE releases statistical information in electronic health records with differential privacy, a strong privacy framework for statistical data release. It includes a number of state-of-the-art methods for releasing multidimensional histograms and longitudinal patterns. We performed a variety of experiments on two real datasets, the surveillance, epidemiology and end results (SEER) breast cancer dataset and the Emory electronic medical record (EeMR) dataset, to demonstrate the feasibility and utility of SHARE. RESULTS: Experimental results indicate that SHARE can deal with heterogeneous data present in medical data, and that the released statistics are useful. The Kullback-Leibler divergence between the released multidimensional histograms and the original data distribution is below 0.5 and 0.01 for seven-dimensional and three-dimensional data cubes generated from the SEER dataset, respectively. The relative error for longitudinal pattern queries on the EeMR dataset varies between 0 and 0.3. While the results are promising, they also suggest that challenges remain in applying statistical data release using the differential privacy framework for higher dimensional data. CONCLUSIONS: SHARE is one of the first systems to provide a mechanism for custodians to release differentially private aggregate statistics for a variety of use cases in the medical domain. This proof-of-concept system is intended to be applied to large-scale medical data warehouses.

OBJECTIVE: Privacy-preserving data publishing addresses the problem of disclosing sensitive data when mining for useful information. Among existing privacy models, ε-differential privacy provides one of the strongest privacy guarantees and makes no assumptions about an adversary's background knowledge. All existing solutions that ensure ε-differential privacy handle the problem of disclosing relational and set-valued data in a privacy-preserving manner separately. In this paper, we propose an algorithm that considers both relational and set-valued data in differentially private disclosure of healthcare data. METHODS: The proposed approach makes a simple yet fundamental switch in differentially private algorithm design: instead of listing all possible records (ie, a contingency table) for noise addition, records are generalized before noise addition. The algorithm first generalizes the raw data in a probabilistic way, and then adds noise to guarantee ε-differential privacy. RESULTS: We showed that the disclosed data could be used effectively to build a decision tree induction classifier. Experimental results demonstrated that the proposed algorithm is scalable and performs better than existing solutions for classification analysis. LIMITATION: The resulting utility may degrade when the output domain size is very large, making it potentially inappropriate to generate synthetic data for large health databases. CONCLUSIONS: Unlike existing techniques, the proposed algorithm allows the disclosure of health data containing both relational and set-valued data in a differentially private manner, and can retain essential information for discriminative analysis.

This paper proposes a novel model on intra coding for High Efficiency Video Coding (HEVC), which simultaneously predicts blocks of pixels with optimal rate distortion. It utilizes the spatial statistical correlation for the optimal prediction based on 2-D contexts, in addition to formulating the data-driven structural interdependences to make the prediction error coherent with the probability distribution, which is desirable for successful transform and coding. The structured set prediction model incorporates a max-margin Markov network (M3N) to regulate and optimize multiple block predictions. The model parameters are learned by discriminating the actual pixel value from other possible estimates to maximize the margin (i.e., decision boundary bandwidth). Compared to existing methods that focus on minimizing prediction error, the M3N-based model adaptively maintains the coherence for a set of predictions. Specifically, the proposed model concurrently optimizes a set of predictions by associating the loss for individual blocks to the joint distribution of succeeding discrete cosine transform coefficients. When the sample size grows, the prediction error is asymptotically upper bounded by the training error under the decomposable loss function. As an internal step, we optimize the underlying Markov network structure to find states that achieve the maximal energy using expectation propagation. For validation, we integrate the proposed model into HEVC for optimal mode selection on rate-distortion optimization. The proposed prediction model obtains up to 2.85% bit rate reduction and achieves better visual quality in comparison to the HEVC intra coding.

Object recognition is a fundamental problem in computer vision. Part-based models offer a sparse, flexible representation of objects, but suffer from difficulties in training and often use standard kernels. In this paper, we propose a positive definite kernel called "structure kernel", which measures the similarity of two part-based represented objects. The structure kernel has three terms: 1) the global term that measures the global visual similarity of two objects; 2) the part term that measures the visual similarity of corresponding parts; 3) the spatial term that measures the spatial similarity of geometric configuration of parts. The contribution of this paper is to generalize the discriminant capability of local kernels to complex part-based object models. Experimental results show that the proposed kernel exhibit higher accuracy than state-of-art approaches using standard kernels.

This paper addresses the problem of advanced silhouette tracking with no prior information, and proposes shape-oriented segmentation together with graph matching corroboration. In terms of unified energy minimization, the shape-oriented graph cut in segmentation exploits the shape information by penalizing the feature points in alignment with shape-oriented map of adjacent frames. While reducing the temporal inconsistencies and improve the accuracy of segmentation, the energy model of graph matching is further designed to compensate the validity of segmentation. To be concrete, it is involved with structural matching cost and unmatched penalty cost to deal with occlusion during tracking. The effectiveness of the proposed scheme is shown with experiments on challenging real-world image sequences.

OBJECTIVE: Competing tools are available online to assess the risk of developing certain conditions of interest, such as cardiovascular disease. While predictive models have been developed and validated on data from cohort studies, little attention has been paid to ensure the reliability of such predictions for individuals, which is critical for care decisions. The goal was to develop a patient-driven adaptive prediction technique to improve personalized risk estimation for clinical decision support. MATERIAL AND METHODS: A data-driven approach was proposed that utilizes individualized confidence intervals (CIs) to select the most 'appropriate' model from a pool of candidates to assess the individual patient's clinical condition. The method does not require access to the training dataset. This approach was compared with other strategies: the BEST model (the ideal model, which can only be achieved by access to data or knowledge of which population is most similar to the individual), CROSS model, and RANDOM model selection. RESULTS: When evaluated on clinical datasets, the approach significantly outperformed the CROSS model selection strategy in terms of discrimination (p<1e-14) and calibration (p<0.006). The method outperformed the RANDOM model selection strategy in terms of discrimination (p<1e-12), but the improvement did not achieve significance for calibration (p=0.1375). LIMITATIONS: The CI may not always offer enough information to rank the reliability of predictions, and this evaluation was done using aggregation. If a particular individual is very different from those represented in a training set of existing models, the CI may be somewhat misleading. CONCLUSION: This approach has the potential to offer more reliable predictions than those offered by other heuristics for disease risk estimation of individual patients.

OBJECTIVE: Predictive models that generate individualized estimates for medically relevant outcomes are playing increasing roles in clinical care and translational research. However, current methods for calibrating these estimates lose valuable information. Our goal is to develop a new calibration method to conserve as much information as possible, and would compare favorably to existing methods in terms of important performance measures: discrimination and calibration. MATERIAL AND METHODS: We propose an adaptive technique that utilizes individualized confidence intervals (CIs) to calibrate predictions. We evaluate this new method, adaptive calibration of predictions (ACP), in artificial and real-world medical classification problems, in terms of areas under the ROC curves, the Hosmer-Lemeshow goodness-of-fit test, mean squared error, and computational complexity. RESULTS: ACP compared favorably to other calibration methods such as binning, Platt scaling, and isotonic regression. In several experiments, binning, isotonic regression, and Platt scaling failed to improve the calibration of a logistic regression model, whereas ACP consistently improved the calibration while maintaining the same discrimination or even improving it in some experiments. In addition, the ACP algorithm is not computationally expensive. LIMITATIONS: The calculation of CIs for individual predictions may be cumbersome for certain predictive models. ACP is not completely parameter-free: the length of the CI employed may affect its results. CONCLUSIONS: ACP can generate estimates that may be more suitable for individualized predictions than estimates that are calibrated using existing methods. Further studies are necessary to explore the limitations of ACP.

iDASH (integrating data for analysis, anonymization, and sharing) is the newest National Center for Biomedical Computing funded by the NIH. It focuses on algorithms and tools for sharing data in a privacy-preserving manner. Foundational privacy technology research performed within iDASH is coupled with innovative engineering for collaborative tool development and data-sharing capabilities in a private Health Insurance Portability and Accountability Act (HIPAA)-certified cloud. Driving Biological Projects, which span different biological levels (from molecules to individuals to populations) and focus on various health conditions, help guide research and development within this Center. Furthermore, training and dissemination efforts connect the Center with its stakeholders and educate data owners and data consumers on how to share and use clinical and biological data. Through these various mechanisms, iDASH implements its goal of providing biomedical and behavioral researchers with access to data, software, and a high-performance computing environment, thus enabling them to generate and test new hypotheses.

OBJECTIVE: The classification of complex or rare patterns in clinical and genomic data requires the availability of a large, labeled patient set. While methods that operate on large, centralized data sources have been extensively used, little attention has been paid to understanding whether models such as binary logistic regression (LR) can be developed in a distributed manner, allowing researchers to share models without necessarily sharing patient data. MATERIAL AND METHODS: Instead of bringing data to a central repository for computation, we bring computation to the data. The Grid Binary LOgistic REgression (GLORE) model integrates decomposable partial elements or non-privacy sensitive prediction values to obtain model coefficients, the variance-covariance matrix, the goodness-of-fit test statistic, and the area under the receiver operating characteristic (ROC) curve. RESULTS: We conducted experiments on both simulated and clinically relevant data, and compared the computational costs of GLORE with those of a traditional LR model estimated using the combined data. We showed that our results are the same as those of LR to a 10(-15) precision. In addition, GLORE is computationally efficient. LIMITATION: In GLORE, the calculation of coefficient gradients must be synchronized at different sites, which involves some effort to ensure the integrity of communication. Ensuring that the predictors have the same format and meaning across the data sets is necessary. CONCLUSION: The results suggest that GLORE performs as well as LR and allows data to remain protected at their original sites.

Biomedical informatics is a young, highly interdisciplinary field that is evolving quickly. It is important to know which published topics in generalist biomedical informatics journals elicit the most interest from the scientific community, and whether this interest changes over time, so that journals can better serve their readers. It is also important to understand whether free access to biomedical informatics articles impacts their citation rates in a significant way, so authors can make informed decisions about unlock fees, and journal owners and publishers understand the implications of open access. The topics and JAMIA articles from years 2009 and 2010 that have been most cited according to the Web of Science are described. To better understand the effects of free access in article dissemination, the number of citations per month after publication for articles published in 2009 versus 2010 was compared, since there was a significant change in free access to JAMIA articles between those years. Results suggest that there is a positive association between free access and citation rate for JAMIA articles.

We study the problem of short term wind speed prediction, which is a critical factor for effective wind power generation. This is a challenging task due to the complex and stochastic behavior of the wind environment. Observing various periods in the wind speed time series present different patterns, we suggest a nonlinear adaptive framework to model various hidden dynamic processes. The model is essentially data driven, which leverages non-parametric Heteroscdastic Gaussian Process to model relevant patterns for short term prediction. We evaluate our model on two different real world wind speed datasets from National Data Buoy Center. We compare our results to state-of-arts algorithms to show improvement in terms of both Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE).

We improve prior efforts to extract coherent image contents (objects) from complex scenes by exploiting structural and semantic coherency. Generative models like latent Dirichlet allocation (LDA) and its variants are popular methods for unsupervised object segmentation, but they lack comprehensive consideration of structure correlations. Even small amounts of globally distributed noise in the image can negatively effect results. In this paper, we introduce a structure preserving semantic coherent model (SP-SC) to support more comprehensive object segmentation. Our approach combines Euclidean distance, graph distances and structural similarity of homogeneous patches in a unified framework. The method groups structural and semantic coherent patches together thereby overcoming false segmentation due to many kinds of noise and scene complexities. Comparative results in segmentation experiments using standard image data sets show the efficacy of proposed approach.

In real sequence labeling tasks, statistics of many higher order features are not sufficient due to the training data sparseness, very few of them are useful. We describe Sparse Higher Order Conditional Random Fields (SHO-CRFs), which are able to handle local features and sparse higher order features together using a novel tractable exact inference algorithm. Our main insight is that states and transitions with same potential functions can be grouped together, and inference is performed on the grouped states and transitions. Though the complexity is not polynomial, SHO-CRFs are still efficient in practice because of the feature sparseness. Experimental results on optical character recognition and Chinese organization name recognition show that with the same higher order feature set, SHO-CRFs significantly outperform previous approaches.

The ability to quickly compute hand geometry measurements from a freely posed hand offers advantages to biometric identification systems. While hand geometry systems are not new, typical measurements of lengths and widths of fingers and palms require rigid placement of the hand against pegs. Slight deviations in hand position, finger stretch or pressure can yield different measurements. This paper offers novel approaches to computing hand geometry measurements from frontal views of freely posed hands. These approaches offer advantages in hygiene, comfort and reliability. Our algorithms segment the hand from a known background under spot lights and locate feature points along the fingers and wrists. Given a database of 54 hand images, with three different images of the same hand of each subject, our approach uniquely identified a previously unseen hand with an overall accuracy of 92%.

The problem investigated in this paper is the quick identification of free-form 2D objects using a coefficient based indexing technique. We demonstrate that combining implicit polynomial shape descriptors with calibration techniques has the potential to quickly identify images of similar shapes. As a pilot experiment, our approach is evaluated against a small database consisting of 15 images, with three different images from five categories. The index system achieves an overall top-3 matching accuracy of 88.9% comparing to 91.1% of the traditional brutal force method on the same database with a computational cutoff of 67.7%.