The rapid growth of digital pathology and advances in self-supervised deep learning have enabled the development of foundational models for various pathology tasks across diverse diseases. While multimodal approaches integrating diverse data sources have emerged, a critical gap remains in the comprehensive integration of whole-slide images (WSIs) with spatial transcriptomics (ST), which is crucial for capturing critical molecular heterogeneity beyond standard hematoxylin & eosin (H&E) staining. We introduce SPADE, a foundation model that integrates histopathology with ST data to guide image representation learning within a unified framework, in effect creating an ST-informed latent space. SPADE leverages a mixture-of-data experts technique, where experts are created via two-stage imaging feature-space clustering using contrastive learning to learn representations of co-registered WSI patches and gene expression profiles. Pre-trained on the comprehensive HEST-1k dataset, SPADE is evaluated on 20 downstream tasks, demonstrating significantly superior few-shot performance compared to baseline models, highlighting the benefits of integrating morphological and molecular information into one latent space. Code and pretrained weights are available at https://github.com/uclabair/SPADE.

Following successful large-vessel recanalization via endovascular thrombectomy (EVT) for acute ischemic stroke (AIS), some patients experience a complication known as no-reflow, defined by persistent microvascular hypoperfusion that undermines tissue recovery and worsens clinical outcomes. Although prompt identification is crucial, standard clinical practice relies on perfusion magnetic resonance imaging (MRI) within 24 hours post-procedure, delaying intervention. In this work, we introduce the first-ever machine learning (ML) framework to predict no-reflow immediately after EVT by leveraging previously unexplored intra-procedural digital subtraction angiography (DSA) sequences and clinical variables. Our retrospective analysis included AIS patients treated at UCLA Medical Center (2011–2024) who achieved favorable mTICI scores (2c or 3) and underwent pre- and post-procedure MRI. No-reflow was defined as a > 15% reduction in relative cerebral blood volume or flow within the infarct core compared to the contralateral hemisphere. From DSA sequences (anteroposterior and lateral views), we extracted statistical and temporal perfusion features from the target downstream territory to train ML classifiers for predicting no-reflow. Our preliminary results demonstrate that this novel method outperformed a clinical-features baseline (AUROC: 0.9330 vs. 0.7768 (p = 0.006)), suggesting that real-time DSA perfusion dynamics may encode clinically relevant information related to microvascular integrity. This approach establishes a preliminary foundation for immediate, accurate no-reflow prediction, enabling clinicians to proactively manage high-risk patients without reliance on delayed imaging, though it warrants validation in larger, independent cohorts.

OBJECTIVES: Mobile health (mHealth) regimens can improve health through the continuous monitoring of biometric parameters paired with appropriate interventions. However, adherence to monitoring tends to decay over time. Our randomized controlled trial sought to determine: (1) if a mobile app with gamification and financial incentives significantly increases adherence to mHealth monitoring in a population of heart failure patients; and (2) if activity data correlate with disease-specific symptoms. MATERIALS AND METHODS: We recruited individuals with heart failure into a prospective 180-day monitoring study with 3 arms. All 3 arms included monitoring with a connected weight scale and an activity tracker. The second arm included an additional mobile app with gamification, and the third arm included the mobile app and a financial incentive awarded based on adherence to mobile monitoring. RESULTS: We recruited 111 heart failure patients into the study. We found that the arm including the financial incentive led to significantly higher adherence to activity tracker (95% vs 72.2%, P = .01) and weight (87.5% vs 69.4%, P = .002) monitoring compared to the arm that included the monitoring devices alone. Furthermore, we found a significant correlation between daily steps and daily symptom severity. DISCUSSION AND CONCLUSION: Our findings indicate that mobile apps with added engagement features can be useful tools for improving adherence over time and may thus increase the impact of mHealth-driven interventions. Additionally, activity tracker data can provide passive monitoring of disease burden that may be used to predict future events.

OBJECTIVES: Longitudinal data in electronic health records (EHRs) represent an individual's clinical history through a sequence of codified concepts, including diagnoses, procedures, medications, and laboratory tests. Generative pretrained transformers (GPT) can leverage this data to predict future events. While fine-tuning of these models can enhance task-specific performance, it becomes costly when applied to many clinical prediction tasks. In contrast, a pretrained foundation model can be used in zero-shot forecasting setting, offering a scalable alternative to fine-tuning separate models for each outcome. MATERIALS AND METHODS: This study presents the first comprehensive analysis of zero-shot forecasting with GPT-based foundational models in EHRs, introducing a novel pipeline that formulates medical concept prediction as a generative modeling task. Unlike supervised approaches requiring extensive labeled data, our method enables the model to forecast the next medical event purely from a pretraining knowledge. We evaluate performance across multiple time horizons and clinical categories, demonstrating model's ability to capture latent temporal dependencies and complex patient trajectories without task supervision. RESULTS: The model's performance in predicting the next medical concept was evaluated using precision and recall metrics, achieving an average top-1 precision of 0.614 and recall of 0.524. For 12 major diagnostic conditions, the model demonstrated strong zero-shot performance, achieving high true positive rates while maintaining low false positives. DISCUSSION: We demonstrate the power of a foundational EHR GPT model in capturing diverse phenotypes and enabling robust, zero-shot forecasting of clinical outcomes. This capability highlights both its versatility across conditions like liver cancer and SLE, and its limitations in more ambiguous settings such as depression, while also revealing meaningful latent clinical structure. CONCLUSION: This capability enhances the versatility of predictive healthcare models and reduces the need for task-specific training, enabling more scalable applications in clinical settings.

Epilepsy is a neurological disorder characterized by seizures that can disrupt a patient’s quality of life. EEG has been used to detect underlying neural activity for diagnosis and treatment. However, standard methods of seizure detection are time-consuming and require manual detection by a trained clinician, with poor inter-clinician agreement. Automated analysis of EEG data offers the potential to improve diagnostic accuracy and reduce manual error. Here, we introduce a transformer-based model pretrained using annotated EEG scalp data that can detect the presence of seizures in a behind-the-ear wearable device setup for the 2023 ICASSP Signal Processing Grand Challenge. Our model has high sensitivity (100%) and a low False Alarm rate (1.78 FA/hr) for seizure detection on a hold-out test set. We also demonstrate how boosting gamma power in preprocessing can improve the performance of ChronoNet, an established EEG abnormality detection model.

The limbus is the junction between the cornea and the sclera and harbors adult stem cells involved in corneal epithelial cells renewal, namely the limbal stem cells (LSCs). Damages to the limbus and/or the LSCs will lead to a loss of the limbal functions, defining limbal stem cell deficiency (LSCD). Clinically, LSCD presents with conjunctival cell invasion into the cornea, corneal scarring, neovascularization, and potential blindness. Recent guidelines have clarified the staging of the disease based on the area involved on the cornea and the use of additional imaging such as in vivo confocal microscopy (IVCM). Several biomarkers of LSC function are evaluated by IVCM on the central cornea, including the basal cell density and morphology, and subbasal nerve density. Evaluation of these biomarkers is time-consuming and remains subjective. Therefore, using a deep learning approach could enhance our diagnosis strategy and efficiency. The current paper demonstrates the performance of a deep learning-based pipeline to first identify clinically relevant images from IVCM volume scans and subsequently use them to classify LSCD severity based on a published grading system. The classification model achieved a test-time accuracy of 74%, and areas under the receiver operating characteristic curve (AUROC) of 0.93, 0.93, 0.94, and 0.87 for control, mild, moderate, and severe, respectively. In order to demonstrate the need to use both cell and nerve images, we also compare models that only use cell scans (68% accuracy) and only nerve scans (69% accuracy). This pilot study shows that the diagnosis of LSCD could be automated to improve diagnostic efficiency and to reduce inter- and intraclinician variability of the process.

One desiderata of topic modeling is to produce interpretable topics. Given a cluster of document-tokens comprising a topic, we can order the topic by counting each word. It is natural to think that each topic could easily be labeled by looking at the words with the highest word count. However, this is not always the case. A human evaluator can often have difficulty identifying a single label that accurately describes the topic as many top words seem unrelated. This paper aims to improve interpretability in topic modeling by providing a novel, outperforming interpretable topic model Our approach combines two previously established subdomains in topic modeling: nonparametric and weakly-supervised topic models. Given a nonparametric topic model, we can include weakly-supervised input using novel modifications to the nonparametric generative model. These modifications lay the groundwork for a compelling setting—one in which most corpora, without any previous supervised or weakly-supervised input, can discover interpretable topics. This setting also presents various challenging sub-problems of which we provide resolutions. Combining nonparametric topic models with weakly-supervised topic models leads to an exciting discovery—a complete, self-contained and outperforming topic model for interpretability.

Bone age assessment (BAA) is clinically important as it can be used to diagnose endocrine and metabolic disorders during child development. Existing deep learning based methods for classifying bone age use the global image as input, or exploit local information by annotating extra bounding boxes or key points. However, training with the global image underutilizes discriminative local information, while providing extra annotations is expensive and subjective. In this paper, we propose an attention-guided approach to automatically localize the discriminative regions for BAA without any extra annotations. Specifically, we first train a classification model to learn the attention maps of the discriminative regions, finding the hand region, the most discriminative region (the carpal bones), and the next most discriminative region (the metacarpal bones). Guided by those attention maps, we then crop the informative local regions from the original image and aggregate different regions for BAA. Instead of taking BAA as a general regression task, which is suboptimal due to the label ambiguity problem in the age label space, we propose using joint age distribution learning and expectation regression, which makes use of the ordinal relationship among hand images with different individual ages and leads to more robust age estimation. Extensive experiments are conducted on the RSNA pediatric bone age data set. Without using extra manual annotations, our method achieves competitive results compared with existing state-of-the-art deep learning-based methods that require manual annotation. Code is available at https://github.com/chenchao666/Bone-Age-Assessment.

Deep neural networks, in particular convolutional networks, have rapidly become a popular choice for analyzing histopathology images. However, training these models relies heavily on a large number of samples manually annotated by experts, which is cumbersome and expensive. In addition, it is difficult to obtain a perfect set of labels due to the variability between expert annotations. This paper presents a novel active learning (AL) framework for histopathology image analysis, named PathAL. To reduce the required number of expert annotations, PathAL selects two groups of unlabeled data in each training iteration: one "informative" sample that requires additional expert annotation, and one "confident predictive" sample that is automatically added to the training set using the model's pseudo-labels. To reduce the impact of the noisy-labeled samples in the training set, PathAL systematically identifies noisy samples and excludes them to improve the generalization of the model. Our model advances the existing AL method for medical image analysis in two ways. First, we present a selection strategy to improve classification performance with fewer manual annotations. Unlike traditional methods focusing only on finding the most uncertain samples with low prediction confidence, we discover a large number of high confidence samples from the unlabeled set and automatically add them for training with assigned pseudo-labels. Second, we design a method to distinguish between noisy samples and hard samples using a heuristic approach. We exclude the noisy samples while preserving the hard samples to improve model performance. Extensive experiments demonstrate that our proposed PathAL framework achieves promising results on a prostate cancer Gleason grading task, obtaining similar performance with 40% fewer annotations compared to the fully supervised learning scenario. An ablation study is provided to analyze the effectiveness of each component in PathAL, and a pathologist reader study is conducted to validate our proposed algorithm.

Limbal stem cell deficiency (LSCD) is a progressive corneal disease that renders the corneal epithelium unable to repair itself, which can lead to the eventual loss of vision. Advances in technology have allowed for the growth of limbal stem cells ex-vivo for the purposes of transplantation. One method used to evaluate the quality of these cultivated cells is cell density, which is typically calculated manually by experts, which is time-consuming and has high inter-rater variability. The goal of this project was to create a tool that automatically calculates cell density from digital images of the cultured cells. Results were compared against annotations from four experts with varying levels of experience. Cell counts had high correlation with expert annotations (r=0.64, p<0.01). When compared to human annotators with lower clinical experience, the algorithm achieved significantly better agreement with highly experienced annotators (r=0.75 vs r=0.19, p<0.01). These results suggest that the automated tool can provide meaningful cell density counts, which can potentially improve annotation consistency and reduce time required for evaluating LSCD cell cultures.

OBJECTIVE: To demonstrate enabling multi-institutional training without centralizing or sharing the underlying physical data via federated learning (FL). MATERIALS AND METHODS: Deep learning models were trained at each participating institution using local clinical data, and an additional model was trained using FL across all of the institutions. RESULTS: We found that the FL model exhibited superior performance and generalizability to the models trained at single institutions, with an overall performance level that was significantly better than that of any of the institutional models alone when evaluated on held-out test sets from each institution and an outside challenge dataset. DISCUSSION: The power of FL was successfully demonstrated across 3 academic institutions while avoiding the privacy risk associated with the transfer and pooling of patient data. CONCLUSION: Federated learning is an effective methodology that merits further study to enable accelerated development of models across institutions, enabling greater generalizability in clinical use.

Recent developments in machine learning algorithms have enabled models to exhibit impressive performance in healthcare tasks using electronic health record (EHR) data. However, the heterogeneous nature and sparsity of EHR data remains challenging. In this work, we present a model that utilizes heterogeneous data and addresses sparsity by representing diagnoses, procedures, and medication codes with temporal Hierarchical Clinical Embeddings combined with Topic modeling (HCET) on clinical notes. HCET aggregates various categories of EHR data and learns inherent structure based on hospital visits for an individual patient. We demonstrate the potential of the approach in the task of predicting depression at various time points prior to a clinical diagnosis. We found that HCET outperformed all baseline methods with a highest improvement of 0.07 in precision-recall area under the curve (PRAUC). Furthermore, applying attention weights across EHR data modalities significantly improved the performance as well as the model's interpretability by revealing the relative weight for each data modality. Our results demonstrate the model's ability to utilize heterogeneous EHR information to predict depression, which may have future implications for screening and early detection.

Advancements in machine learning algorithms have had a beneficial impact on representation learning, classification, and prediction models built using electronic health record (EHR) data. Effort has been put both on increasing models' overall performance as well as improving their interpretability, particularly regarding the decision-making process. In this study, we present a temporal deep learning model to perform bidirectional representation learning on EHR sequences with a transformer architecture to predict future diagnosis of depression. This model is able to aggregate five heterogenous and high-dimensional data sources from the EHR and process them in a temporal manner for chronic disease prediction at various prediction windows. We applied the current trend of pretraining and fine-tuning on EHR data to outperform the current state-of-the-art in chronic disease prediction, and to demonstrate the underlying relation between EHR codes in the sequence. The model generated the highest increases of precision-recall area under the curve (PRAUC) from 0.70 to 0.76 in depression prediction compared to the best baseline model. Furthermore, the self-attention weights in each sequence quantitatively demonstrated the inner relationship between various codes, which improved the model's interpretability. These results demonstrate the model's ability to utilize heterogeneous EHR data to predict depression while achieving high accuracy and interpretability, which may facilitate constructing clinical decision support systems in the future for chronic disease screening and early detection.

Neurodegenerative diseases such as Amyotrophic Lateral Sclerosis (ALS) restrict an individual's ability to fully engage with their surroundings by interrupting crucial cell signaling processes between the brain and the peripheral nervous system. In such cases, brain-computer interfaces (BCI) such as the P300 speller use electroencephalography (EEG) to capture subject brain signals which are decoded to provide an alternate channel for communication. This paper develops new and sophisticated BCI techniques combining language models, probabilistic flashboard design, and optimal scanning techniques which together with smoothing algorithms and word suggestions can be effectively utilized as a form of predictive spelling. Detailed offline simulations based on subject EEG data allowed for testing a variety of methods on a large subject population producing extensive output text including both in vocabulary and out of vocabulary words. Significant performance gains were seen when applying language models to classification and optimizing the interface for stimulus presentation. The results demonstrate that feed-forward techniques with appropriate flashboard design and word completion algorithms can achieve similar or better performance as more complex feedback schemes. Consequently, one can employ lower complexity flashboard as well as control and yet achieve the performance gains offered by more complex techniques

Patients with neuromuscular diseases such as amyotrophic lateral sclerosis can have difficulty communicating because neural signals cannot reach effector muscles. Recent advances in brain-computer interfaces have allowed these patients to communicate by converting neurological signals into computer commands. One common brain-computer interface is the P300 speller, a system that allows these patients to spell out text. Because of the electroencephalogram (EEG) signal variability between patients, it is hard to create a classifier applicable to all patients. Therefore, current methods use an arduous training step personalized for each patient. There have been previous attempts to create a general classifier that works for all subjects, but these attempts have generally resulted in poor accuracies that were insufficient for practical use. This paper presents a novel cross-subject approach for the P300 speller. It uses a language model which adjusts the probabilities of each character based on context to improve classifier performance. Additionally, dynamic stopping allows the system to continually obtain EEG signal from the patient until the system is confident in its character selection. By using these two approaches, we can maintain reasonable selection accuracy, allowing subjects to use the system without an individualized training step.

In this study, we propose the Ductal Instance-Oriented Pipeline (DIOP) that contains a duct-level instance segmentation model, a tissue-level semantic segmentation model, and three-levels of features for diagnostic classification. Based on recent advancements in instance segmentation and the Mask RCNN model, our duct-level segmenter tries to identify each ductal individual inside a microscopic image; then, it extracts tissue-level information from the identified ductal instances. Leveraging three levels of information obtained from these ductal instances and also the histopathology image, the proposed DIOP outperforms previous approaches (both feature-based and CNN-based) in all diagnostic tasks; for the four-way classification task, the DIOP achieves comparable performance to general pathologists in this unique dataset. The proposed DIOP only takes a few seconds to run in the inference time, which could be used interactively on most modern computers. More clinical explorations are needed to study the robustness and generalizability of this system in the future.

MOTIVATION: Mining drug-disease association and related interactions are essential for developing in silico drug repurposing (DR) methods and understanding underlying biological mechanisms. Recently, large-scale biological databases are increasingly available for pharmaceutical research, allowing for deep characterization for molecular informatics and drug discovery. However, DR is challenging due to the molecular heterogeneity of disease and diverse drug-disease associations. Importantly, the complexity of molecular target interactions, such as protein-protein interaction (PPI), remains to be elucidated. DR thus requires deep exploration of a multimodal biological network in an integrative context. RESULTS: In this study, we propose BiFusion, a bipartite graph convolution network model for DR through heterogeneous information fusion. Our approach combines insights of multiscale pharmaceutical information by constructing a multirelational graph of drug-protein, disease-protein and PPIs. Especially, our model introduces protein nodes as a bridge for message passing among diverse biological domains, which provides insights into utilizing PPI for improved DR assessment. Unlike conventional graph convolution networks always assuming the same node attributes in a global graph, our approach models interdomain information fusion with bipartite graph convolution operation. We offered an exploratory analysis for finding novel drug-disease associations. Extensive experiments showed that our approach achieved improved performance than multiple baselines for DR analysis. AVAILABILITY AND IMPLEMENTATION: Source code and preprocessed datasets are at: https://github.com/zcwang0702/BiFusion.

Constructing statistical models using personal sensor data could allow for tracking health status over time, thereby enabling the possibility of early intervention. The goal of this study was to use machine learning algorithms to classify patient-reported outcomes (PROs) using activity tracker data in a cohort of patients with stable ischemic heart disease (SIHD). A population of 182 patients with SIHD were monitored over a period of 12 weeks. Each subject received a Fitbit Charge 2 device to record daily activity data, and each subject completed eight Patient-Reported Outcomes Measurement Information Systems short form at the end of each week as a self-assessment of their health status. Two models were built to classify PRO scores using activity tracker data. The first model treated each week independently, whereas the second used a hidden Markov model (HMM) to take advantage of correlations between successive weeks. Retrospective analysis compared the classification accuracy of the two models and the importance of each feature. In the independent model, a random forest classifier achieved a mean area under curve (AUC) of 0.76 for classifying the physical function PRO. The HMM model achieved significantly better AUCs for all PROs (p < 0.05) other than Fatigue and Sleep Disturbance, with a highest mean AUC of 0.79 for the physical function-short form 10a. Our study demonstrates the ability of activity tracker data to classify health status over time. These results suggest that patient outcomes can be monitored in real time using activity trackers.

Current clinical practice relies on clinical history to determine the time since stroke (TSS) onset. Imaging-based determination of acute stroke onset time could provide critical information to clinicians in deciding stroke treatment options, such as thrombolysis. The patients with unknown or unwitnessed TSS are usually excluded from thrombolysis, even if their symptoms began within the therapeutic window. In this paper, we demonstrate a machine learning approach for TSS classification using routinely acquired imaging sequences. We develop imaging features from the magnetic resonance (MR) images and train machine learning models to classify the TSS. We also propose a deep-learning model to extract hidden representations for the MR perfusion-weighted images and demonstrate classification improvement by incorporating these additional deep features. The cross-validation results show that our best classifier achieved an area under the curve of 0.765, with a sensitivity of 0.788 and a negative predictive value of 0.609, outperforming existing methods. We show that the features generated by our deep-learning algorithm correlate with the MR imaging features, and validate the robustness of the model on imaging parameter variations (e.g., year of imaging). This paper advances magnetic resonance imaging analysis one-step-closer to an operational decision support tool for stroke treatment guidance.

Prostate cancer is the most common and second most deadly form of cancer in men in the United States. The classification of prostate cancers based on Gleason grading using histological images is important in risk assessment and treatment planning for patients. Here, we demonstrate a new region-based convolutional neural network framework for multi-task prediction using an epithelial network head and a grading network head. Compared with a single-task model, our multi-task model can provide complementary contextual information, which contributes to better performance. Our model is achieved a state-of-the-art performance in epithelial cells detection and Gleason grading tasks simultaneously. Using fivefold cross-validation, our model is achieved an epithelial cells detection accuracy of 99.07% with an average area under the curve of 0.998. As for Gleason grading, our model is obtained a mean intersection over union of 79.56% and an overall pixel accuracy of 89.40%.

Telemedicine has been used to remotely diagnose and treat patients, yet previously applied telemonitoring approaches have been fraught with adherence issues. The primary goal of this study was to evaluate the adherence rates using a consumer-grade continuous-time heart rate and activity tracker in a mid-risk cardiovascular patient population. As a secondary analysis, we show the ability to utilize the information provided by this device to identify information about a patient's state by correlating tracker information with patient-reported outcome survey scores. We showed that using continuous-time activity trackers with heart rate monitors can be effective in a telemonitoring application, as patients had a high level of adherence (90.0% median usage) and low attrition (0.09% decrease per day) over a 90-day period. Furthermore, data collected correlated significantly with clinically relevant patient surveys (r2=0.15 for PROMIS global health scores, p < .00001), and therefore might provide an effective signal for identifying patients in need of intervention.

Topic modeling has increasingly attracted interests from researchers. Common methods of topic modeling usually produce a collection of unlabeled topics where each topic is depicted by a distribution of words. Associating semantic meaning with these word distributions is not always straightforward. Traditionally, this task is left to human interpretation. Manually labeling the topics is unfortunately not always easy, as topics generated by unsupervised learning methods do not necessarily align well with our prior knowledge in the subject domains. Currently, two approaches to solve this issue exist. The first is a post-processing procedure that assigns each topic with a label from the prior knowledge base that is semantically closest to the word distribution of the topic. The second is a supervised topic modeling approach that restricts the topics to a predefined set whose word distributions are provided beforehand. Neither approach is ideal, as the former may produce labels that do not accurately describe the word distributions, and the latter lacks the ability to detect unknown topics that are crucial to enrich our knowledge base. Our goal in this paper is to introduce a semisupervised Latent Dirichlet allocation (LDA) model, Source-LDA, which incorporates prior knowledge to guide the topic modeling process to improve both the quality of the resulting topics and of the topic labeling. We accomplish this by integrating existing labeled knowledge sources representing known potential topics into a probabilistic topic model. These knowledge sources are translated into a distribution and used to set the hyperparameters of the Dirichlet generated distribution over words. This approach ensures that the topic inference process is consistent with existing knowledge, and simultaneously, allows for discovery of new topics. The results show improved topic generation and increased accuracy in topic labeling when compared to those obtained using various labeling approaches based off LDA.

Perfusion magnetic resonance (MR) images are often used in the assessment of acute ischemic stroke to distinguish between salvageable tissue and infarcted core. Deconvolution methods such as singular value decomposition have been used to approximate model-based perfusion parameters from these images. However, studies have shown that these existing deconvolution algorithms can introduce distortions that may negatively influence the utility of these parameter maps. There is limited previous work on utilizing machine learning algorithms to estimate perfusion parameters. In this work, we present a novel bi-input convolutional neural network (bi-CNN) to approximate four perfusion parameters without using an explicit deconvolution method. These bi-CNNs produced good approximations for all four parameters, with relative average root-mean-square errors (ARMSEs) ≤ 5% of the maximum values. We further demonstrate the utility of the estimated perfusion maps for quantifying the salvageable tissue volume in stroke, with more than 80% agreement with the ground truth. These results show that deep learning techniques are a promising tool for perfusion parameter estimation without requiring a standard deconvolution process.

Given the increasing emphasis on delivering high-quality, cost-efficient healthcare, improved methodologies are needed to measure the accuracy and utility of ordered diagnostic examinations in achieving the appropriate diagnosis. Here, we present a data-driven approach for performing automated quality assessment of radiologic interpretations using other clinical information (e.g., pathology) as a reference standard for individual radiologists, subspecialty sections, imaging modalities, and entire departments. Downstream diagnostic conclusions from the electronic medical record are utilized as "truth" to which upstream diagnoses generated by radiology are compared. The described system automatically extracts and compares patient medical data to characterize concordance between clinical sources. Initial results are presented in the context of breast imaging, matching 18 101 radiologic interpretations with 301 pathology diagnoses and achieving a precision and recall of 84% and 92%, respectively. The presented data-driven method highlights the challenges of integrating multiple data sources and the application of information extraction tools to facilitate healthcare quality improvement.

Patient portals have the potential to provide content that is specifically tailored to a patient's information needs based on diagnoses and other factors. In this work, we conducted a survey of 41 lung cancer patients at an outpatient lung cancer clinic at the medical center of the University of California Los Angeles, to gain insight into these perceived information needs and opinions on the design of a portal to fulfill them. We found that patients requested access to information related to diagnosis and imaging, with more than half of the patients reporting that they did not anticipate an increase in anxiety due to access to medical record information via a portal. We also found that patient educational background did not lead to a significant difference in desires for explanations of reports and definitions of terms.

OBJECTIVE: With the increased routine use of advanced imaging in clinical diagnosis and treatment, it has become imperative to provide patients with a means to view and understand their imaging studies. We illustrate the feasibility of a patient portal that automatically structures and integrates radiology reports with corresponding imaging studies according to several information orientations tailored for the layperson. METHODS: The imaging patient portal is composed of an image processing module for the creation of a timeline that illustrates the progression of disease, a natural language processing module to extract salient concepts from radiology reports (73% accuracy, F1 score of 0.67), and an interactive user interface navigable by an imaging findings list. The portal was developed as a Java-based web application and is demonstrated for patients with brain cancer. RESULTS AND DISCUSSION: The system was exhibited at an international radiology conference to solicit feedback from a diverse group of healthcare professionals. There was wide support for educating patients about their imaging studies, and an appreciation for the informatics tools used to simplify images and reports for consumer interpretation. Primary concerns included the possibility of patients misunderstanding their results, as well as worries regarding accidental improper disclosure of medical information. CONCLUSIONS: Radiologic imaging composes a significant amount of the evidence used to make diagnostic and treatment decisions, yet there are few tools for explaining this information to patients. The proposed radiology patient portal provides a framework for organizing radiologic results into several information orientations to support patient education.

Imaging has become a prevalent tool in the diagnosis and treatment of many diseases, providing a unique in vivo, multi-scale view of anatomic and physiologic processes. With the increased use of imaging and its progressive technical advances, the role of imaging informatics is now evolving--from one of managing images, to one of integrating the full scope of clinical information needed to contextualize and link observations across phenotypic and genotypic scales. Several challenges exist for imaging informatics, including the need for methods to transform clinical imaging studies and associated data into structured information that can be organized and analyzed. We examine some of these challenges in establishing imaging-based observational databases that can support the creation of comprehensive disease models. The development of these databases and ensuing models can aid in medical decision making and knowledge discovery and ultimately, transform the use of imaging to support individually-tailored patient care.

Clinical narrative in the medical record provides perhaps the most detailed account of a patient's history. However, this information is documented in free-text, which makes it challenging to analyze. Efforts to index unstructured clinical narrative often focus on identifying predefined concepts from clinical terminologies. Less studied is the problem of analyzing the text as a whole to create temporal indices that capture relationships between learned clinical events. Topic models provide a method for analyzing large corpora of text to discover semantically related clusters of words. This work presents a topic model tailored to the clinical reporting environment that allows for individual patient timelines. Results show the model is able to identify patterns of clinical events in a cohort of brain cancer patients.