A hierarchical multilabel graph attention network method to predict the deterioration paths of chronic hepatitis B patients.

OBJECTIVE: Estimating the deterioration paths of chronic hepatitis B (CHB) patients is critical for physicians' decisions and patient management. A novel, hierarchical multilabel graph attention-based method aims to predict patient deterioration paths more effectively. Applied to a CHB patient data set, it offers strong predictive utilities and clinical value. MATERIALS AND METHODS: The proposed method incorporates patients' responses to medications, diagnosis event sequences, and outcome dependencies to estimate deterioration paths. From the electronic health records maintained by a major healthcare organization in Taiwan, we collect clinical data about 177 959 patients diagnosed with hepatitis B virus infection. We use this sample to evaluate the proposed method's predictive efficacy relative to 9 existing methods, as measured by precision, recall, F-measure, and area under the curve (AUC). RESULTS: We use 20% of the sample as holdouts to test each method's prediction performance. The results indicate that our method consistently and significantly outperforms all benchmark methods. It attains the highest AUC, with a 4.8% improvement over the best-performing benchmark, as well as 20.9% and 11.4% improvements in precision and F-measures, respectively. The comparative results demonstrate that our method is more effective for predicting CHB patients' deterioration paths than existing predictive methods. DISCUSSION AND CONCLUSION: The proposed method underscores the value of patient-medication interactions, temporal sequential patterns of distinct diagnosis, and patient outcome dependencies for capturing dynamics that underpin patient deterioration over time. Its efficacious estimates grant physicians a more holistic view of patient progressions and can enhance their clinical decision-making and patient management.

Predictive Analytics for Care and Management of Patients With Acute Diseases: Deep Learning-Based Method to Predict Crucial Complication Phenotypes.

BACKGROUND: Acute diseases present severe complications that develop rapidly, exhibit distinct phenotypes, and have profound effects on patient outcomes. Predictive analytics can enhance physicians' care and management of patients with acute diseases by predicting crucial complication phenotypes for a timely diagnosis and treatment. However, effective phenotype predictions require several challenges to be overcome. First, patient data collected in the early stages of an acute disease (eg, clinical data and laboratory results) are less informative for predicting phenotypic outcomes. Second, patient data are temporal and heterogeneous; for example, patients receive laboratory tests at different time intervals and frequencies. Third, imbalanced distributions of patient outcomes create additional complexity for predicting complication phenotypes. OBJECTIVE: To predict crucial complication phenotypes among patients with acute diseases, we propose a novel, deep learning-based method that uses recurrent neural network-based sequence embedding to represent disease progression while considering temporal heterogeneities in patient data. Our method incorporates a latent regulator to alleviate data insufficiency constraints by accounting for the underlying mechanisms that are not observed in patient data. The proposed method also includes cost-sensitive learning to address imbalanced outcome distributions in patient data for improved predictions. METHODS: From a major health care organization in Taiwan, we obtained a sample of 10,354 electronic health records that pertained to 6545 patients with peritonitis. The proposed method projects these temporal, heterogeneous, and clinical data into a substantially reduced feature space and then incorporates a latent regulator (latent parameter matrix) to obviate data insufficiencies and account for variations in phenotypic expressions. Moreover, our method employs cost-sensitive learning to further increase the predictive performance. RESULTS: We evaluated the efficacy of the proposed method for predicting two hepatic complication phenotypes in patients with peritonitis: acute hepatic encephalopathy and hepatorenal syndrome. The following three benchmark techniques were evaluated: temporal multiple measurement case-based reasoning (MMCBR), temporal short long-term memory (T-SLTM) networks, and time fusion convolutional neural network (CNN). For acute hepatic encephalopathy predictions, our method attained an area under the curve (AUC) value of 0.82, which outperforms temporal MMCBR by 64%, T-SLTM by 26%, and time fusion CNN by 26%. For hepatorenal syndrome predictions, our method achieved an AUC value of 0.64, which is 29% better than that of temporal MMCBR (0.54). Overall, the evaluation results show that the proposed method significantly outperforms all the benchmarks, as measured by recall, F-measure, and AUC while maintaining comparable precision values. CONCLUSIONS: The proposed method learns a short-term temporal representation from patient data to predict complication phenotypes and offers greater predictive utilities than prevalent data-driven techniques. This method is generalizable and can be applied to different acute disease (illness) scenarios that are characterized by insufficient patient clinical data availability, temporal heterogeneities, and imbalanced distributions of important patient outcomes.

A Deep Learning-Based Unsupervised Method to Impute Missing Values in Patient Records for Improved Management of Cardiovascular Patients.

Physicians increasingly depend on electronic health records (EHRs) to manage their patients. However, many patient records have substantial missing values that pose a fundamental challenge to their clinical use. To address this prevailing challenge, we propose an unsupervised deep learning-based method that can facilitate physicians' use of EHRs to improve their management of cardiovascular patients. By building on the deep autoencoder framework, we develop a novel method to impute missing values in patient records. To demonstrate its clinical applicability and values, we use data from cardiovascular patients and evaluate the proposed method's imputation effectiveness and predictive efficacy, in comparison with six prevalent benchmark techniques. The proposed method can impute missing values and predict important patient outcomes more effectively than all the benchmark techniques. This study reinforces the importance of adequately addressing missing values in patient records. It further illustrates how effective imputations can enable greater predictive efficacy with regard to important patient outcomes, which are crucial to the use of EHRs and health analytics for improved patient management. Supported by the complete data imputed by the proposed method, physicians can make timely patient outcome estimations (predictions) and therapeutic treatment assessments.

A deep learning-based, unsupervised method to impute missing values in electronic health records for improved patient management.

Electronic health records (EHRs) often suffer missing values, for which recent advances in deep learning offer a promising remedy. We develop a deep learning-based, unsupervised method to impute missing values in patient records, then examine its imputation effectiveness and predictive efficacy for peritonitis patient management. Our method builds on a deep autoencoder framework, incorporates missing patterns, accounts for essential relationships in patient data, considers temporal patterns common to patient records, and employs a novel loss function for error calculation and regularization. Using a data set of 27,327 patient records, we perform a comparative evaluation of the proposed method and several prevalent benchmark techniques. The results indicate the greater imputation performance of our method relative to all the benchmark techniques, recording 5.3-15.5% lower imputation errors. Furthermore, the data imputed by the proposed method better predict readmission, length of stay, and mortality than those obtained from any benchmark techniques, achieving 2.7-11.5% improvements in predictive efficacy. The illustrated evaluation indicates the proposed method's viability, imputation effectiveness, and clinical decision support utilities. Overall, our method can reduce imputation biases and be applied to various missing value scenarios clinically, thereby empowering physicians and researchers to better analyze and utilize EHRs for improved patient management.

Predicting hepatocellular carcinoma recurrences: A data-driven multiclass classification method incorporating latent variables.

Hepatocellular carcinoma (HCC), a malignant form of cancer, is frequently treated with surgical resections, which have relatively high recurrence rates. Effective recurrence predictions enable physicians' timely detections and adequate therapeutic measures that can greatly improve patient care and outcomes. Toward that end, predictions of early versus late HCC recurrences should be considered separately to reflect their distinct onset time horizons, clinical causes, underlying clinical etiology, and pathogenesis. We propose a novel Bayesian network-based method to predict different HCC recurrence outcomes by considering the respective recurrence evolution paths. Typical patient information obtained in early stages is insufficiently informative to predict recurrence outcomes accurately, due to the lack of subsequent patient progression information. Our method alleviates such information deficiency constraints by incorporating an independent latent variable, dominant recurrence type, to regulate recurrence outcome predictions (early, late, or no recurrence). We use a real-world HCC data set to evaluate the proposed method, relative to three prevalent benchmark techniques. Overall, the results show that our method consistently and significantly outperforms all the benchmark techniques in terms of accuracy, precision, recall, and F-measures. For increased robustness, we use another data set to perform an out-of-sample evaluation and obtain similar results. This study thus contributes to HCC recurrence research and offers several implications for clinical practice.

A preclustering-based ensemble learning technique for acute appendicitis diagnoses.

OBJECTIVE: Acute appendicitis is a common medical condition, whose effective, timely diagnosis can be difficult. A missed diagnosis not only puts the patient in danger but also requires additional resources for corrective treatments. An acute appendicitis diagnosis constitutes a classification problem, for which a further fundamental challenge pertains to the skewed outcome class distribution of instances in the training sample. A preclustering-based ensemble learning (PEL) technique aims to address the associated imbalanced sample learning problems and thereby support the timely, accurate diagnosis of acute appendicitis. MATERIALS AND METHODS: The proposed PEL technique employs undersampling to reduce the number of majority-class instances in a training sample, uses preclustering to group similar majority-class instances into multiple groups, and selects from each group representative instances to create more balanced samples. The PEL technique thereby reduces potential information loss from random undersampling. It also takes advantage of ensemble learning to improve performance. We empirically evaluate this proposed technique with 574 clinical cases obtained from a comprehensive tertiary hospital in southern Taiwan, using several prevalent techniques and a salient scoring system as benchmarks. RESULTS: The comparative results show that PEL is more effective and less biased than any benchmarks. The proposed PEL technique seems more sensitive to identifying positive acute appendicitis than the commonly used Alvarado scoring system and exhibits higher specificity in identifying negative acute appendicitis. In addition, the sensitivity and specificity values of PEL appear higher than those of the investigated benchmarks that follow the resampling approach. Our analysis suggests PEL benefits from the more representative majority-class instances in the training sample. According to our overall evaluation results, PEL records the best overall performance, and its area under the curve measure reaches 0.619. CONCLUSION: The PEL technique is capable of addressing imbalanced sample learning associated with acute appendicitis diagnosis. Our evaluation results suggest PEL is less biased toward a positive or negative class than the investigated benchmark techniques. In addition, our results indicate the overall effectiveness of the proposed technique, compared with prevalent scoring systems or salient classification techniques that follow the resampling approach.

System for infectious disease information sharing and analysis: design and evaluation.

Motivated by the importance of infectious disease informatics (IDI) and the challenges to IDI system development and data sharing, we design and implement BioPortal, a Web-based IDI system that integrates cross-jurisdictional data to support information sharing, analysis, and visualization in public health. In this paper, we discuss general challenges in IDI, describe BioPortal's architecture and functionalities, and highlight encouraging evaluation results obtained from a controlled experiment that focused on analysis accuracy, task performance efficiency, user information satisfaction, system usability, usefulness, and ease of use.