Given the severe impact of low bone density (LBD) on public health, and to avoid the potential damage of X-rays-based bone density measurements, this study aimed to develop a scoring system for the mass screening for LBD in women aged 50 years or older, using the basic body check-up items as variables. Five variables, including age, body mass index (BMI), systolic blood pressure (SBP), blood glucose level, and total cholesterol level (TCL), were obtained from medical check-up records of 1525 women aged 50 years or older who had done body examination between 2011 and 2018, and were used to construct a scoring system for the screening for LBD. Multivariate logistic regression was applied to investigate the putative association of the five variables with LBD. A scoring system was derived from the regression model to discriminate persons at risk of LBD from low-risk persons. An artificial neural network (ANN) model was also applied to the same task. Precision, recall,$F1$-score, and c-statistic were adopted as evaluation metrics. Age, BMI, SBP, glucose, and TCL were significantly associated with the risk of LBD. Precision, recall, c-statistic, and$F1$-score of the proposed scoring system were 0.66, 0.83, 0.73, and 0.74, respectively. ANNs achieved better performances in terms of all measurements. This study demonstrates the feasibility of using routine body check-up items to estimate LBD risk. Different from X-rays-based instruments, the scoring system derived from this study may serve as a postcheck-up mass screening tool to enable health practitioners to identify individuals at a risk of LBD efficiently and nonintrusively.

The discovery and repurposing of drugs require a deep understanding of the mechanism of drug action (MODA). Existing computational methods mainly model MODA with the protein-protein interaction (PPI) network. However, the molecular interactions of drugs in the human body are far beyond PPIs. Additionally, the lack of interpretability of these models hinders their practicability. We propose an interpretable deep learning-based path-reasoning framework (iDPath) for drug discovery and repurposing by capturing MODA on by far the most comprehensive multilayer biological network consisting of the complex high-dimensional molecular interactions between genes, proteins and chemicals. Experiments show that iDPath outperforms state-of-the-art machine learning methods on a general drug repurposing task. Further investigations demonstrate that iDPath can identify explicit critical paths that are consistent with clinical evidence. To demonstrate the practical value of iDPath, we apply it to the identification of potential drugs for treating prostate cancer and hypertension. Results show that iDPath can discover new FDA-approved drugs. This research provides a novel interpretable artificial intelligence perspective on drug discovery.

Prognostic prediction is the task of estimating a patient's risk of disease development based on various predictors. Such prediction is important for healthcare practitioners and patients because it reduces preventable harm and costs. As such, a prognostic prediction model is preferred if: 1) it exhibits encouraging performance and 2) it can generate intelligible rules, which enable experts to understand the logic of the model's decision process. However, current studies usually concentrated on only one of the two features. Toward filling this gap, in the present study, we develop a novel knowledge-aware Bayesian model taking into consideration accuracy and transparency simultaneously. Real-world case studies based on four years' territory-wide electronic health records are conducted to test the model. The results show that the proposed model surpasses state-of-the-art prognostic prediction models in accuracy and c-statistic. In addition, the proposed model can generate explainable rules.

Ordinal regression predicts the objects’ labels that exhibit a natural ordering, which is vital to decision-making problems such as credit scoring and clinical diagnosis. In these problems, the ability to explain how the individual features and their interactions affect the decisions is as critical as model performance. Unfortunately, the existing ordinal regression models in the machine learning community aim at improving prediction accuracy rather than explore explainability. To achieve high accuracy while explaining the relationships between the features and the predictions, we propose a new method for ordinal regression problems, namely the Explainable Ordinal Factorization Model (XOFM). XOFM uses piecewise linear functions to approximate the shape functions of individual features, and renders the pairwise features interaction effects as heat-maps. The proposed XOFM captures the nonlinearity in the main effects and ensures the interaction effects’ same flexibility. Therefore, the underlying model yields comparable performance while remaining explainable by explicitly describing the main and interaction effects. To address the potential sparsity problem caused by discretizing the whole feature scale into several sub-intervals, XOFM integrates the Factorization Machines (FMs) to factorize the model parameters. Comprehensive experiments with benchmark real-world and synthetic datasets demonstrate that the proposed XOFM leads to state-of-the-art prediction performance while preserving an easy-to-understand explainability.

OBJECTIVE: To develop an end-to-end deep learning framework based on a protein-protein interaction (PPI) network to make synergistic anticancer drug combination predictions. MATERIALS AND METHODS: We propose a deep learning framework named Graph Convolutional Network for Drug Synergy (GraphSynergy). GraphSynergy adapts a spatial-based Graph Convolutional Network component to encode the high-order topological relationships in the PPI network of protein modules targeted by a pair of drugs, as well as the protein modules associated with a specific cancer cell line. The pharmacological effects of drug combinations are explicitly evaluated by their therapy and toxicity scores. An attention component is also introduced in GraphSynergy, which aims to capture the pivotal proteins that play a part in both PPI network and biomolecular interactions between drug combinations and cancer cell lines. RESULTS: GraphSynergy outperforms the classic and state-of-the-art models in predicting synergistic drug combinations on the 2 latest drug combination datasets. Specifically, GraphSynergy achieves accuracy values of 0.7553 (11.94% improvement compared to DeepSynergy, the latest published drug combination prediction algorithm) and 0.7557 (10.95% improvement compared to DeepSynergy) on DrugCombDB and Oncology-Screen datasets, respectively. Furthermore, the proteins allocated with high contribution weights during the training of GraphSynergy are proved to play a role in view of molecular functions and biological processes, such as transcription and transcription regulation. CONCLUSION: The introduction of topological relations between drug combination and cell line within the PPI network can significantly improve the capability of synergistic drug combination identification.

Journal of the American Medical Informatics Association, ocab162, https://doi.org/10.1093/jamia/ocab162 When this paper was first published, there were a number of formatting problems in the pdf version of the paper, especially affecting the equations. The html version of the paper was correct. These errors were not due to author error, and the publisher apologizes for these errors. These errors have now been corrected online.

How well stations are connected with each other is a critical performance assessment of railway systems. Network analysis is a highly intuitive and interpretable approach to characterizing the physical connectivity of railway systems. However, the physical connectivity is often limited in depicting transportation network dynamics due to the lack of traffic flow information. This paper first comprehensively reviews the physical connectivity metrics and applies these metrics to evaluate the connectivity of China's high-speed railway system. Then, through integrating the real-world network topology and travel demand data, we conduct the first data-driven research on comparing the physical connectivity with the logical connectivity of railway systems. The experiments demonstrate that the physical connectivity metrics cannot well represent the connectivity of railway systems, due to the neglect of the heterogeneous distribution and temporal patterns of the passenger flows.

Disease risk modeling is of great interest to clinicians and healthcare policy makers in reducing preventable harm and associated costs. A disease risk prediction model is preferable if it (1) exhibits superior prediction performance and (2) constructs explainable rules to allow medical professionals to understand why and how the prediction was made. Existing studies usually focus on one of the two features. In this study, we propose a comorbidity network involved end-to-end trained disease risk prediction model. The adoption of side information and the end-to-end framework together ensure both high accuracy and transparency to the model. The prediction performances of the proposed model are demonstrated by using a real case study based on three years of medical histories from the Hong Kong Hospital Authority is considered. Results show that the proposed model exhibits superior prediction performance while learns explainable rules.

The emergence of large-scale social signal data has provided unprecedented opportunities to develop techniques for improving transportation systems. In this paper, we use two types of social signal data, namely, mobile phone data and subway card data, to investigate congestion avoidance routing methodologies in the Beijing subway and San Francisco road networks. The social signal data were used to estimate detailed travel demand information and to target sources of congestion, in order to develop intelligent routing models. We study two fundamental routing scenarios, namely, the shortest path (SP) scenario and the minimum cost (MC) scenario, and propose a hybrid routing model that combines SP routing and MC routing. The hybrid model requires only a small fraction of travelers to take MC routes, but achieves nearly the same effect as MC routing. To apply the proposed routing methodologies in practical situations, we develop an information-releasing framework to suggest routes for a small group of travelers whose route adjustments can significantly improve the efficiency of the transportation networks.