Scalable and accurate deep learning for electronic health records

Abstract

Predictive modeling with electronic health record (EHR) data is anticipated to drive personalized medicine and improve healthcare quality. Constructing predictive statistical models typically requires extraction of curated predictor variables from normalized EHR data, a labor-intensive process that discards the vast majority of information in each patient's record. We propose a representation of patients' entire, raw EHR records based on the Fast Healthcare Interoperability Resources (FHIR) format. We demonstrate that deep learning methods using this representation are capable of accurately predicting multiple medical events from multiple centers without site-specific data harmonization. We validated our approach using de-identified EHR data from two U.S. academic medical centers with 216,221 adult patients hospitalized for at least 24 hours. In the sequential format we propose, this volume of EHR data unrolled into a total of 46,864,534,945 data points, including clinical notes. Deep learning models achieved high accuracy for tasks such as predicting in-hospital mortality (AUROC across sites 0.93-0.94), 30-day unplanned readmission (AUROC 0.75-0.76), prolonged length of stay (AUROC 0.85-0.86), and all of a patient's final discharge diagnoses (frequency-weighted AUROC 0.90). These models outperformed state-of-the-art traditional predictive models in all cases. We also present a case-study of a neural-network attribution system, which illustrates how clinicians can gain some transparency into the predictions. We believe that this approach can be used to create accurate and scalable predictions for a variety of clinical scenarios, complete with explanations that directly highlight evidence in the patient's chart.

Published version from https://www.nature.com/articles/s41746-018-0029-1

References in corpus (2)

• Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis
• Semantic processing of EHR data for clinical research

Cited by in corpus (56)

• Deep learning for time series classification: a review
• An overview of deep learning in medical imaging focusing on MRI
• The role of explainability in creating trustworthy artificial intelligence for health care: a comprehensive survey of the terminology, design choices, and evaluation strategies
• Multitask learning and benchmarking with clinical time series data
• HealthFog: An Ensemble Deep Learning based Smart Healthcare System for Automatic Diagnosis of Heart Diseases in Integrated IoT and Fog Computing Environments
• FedKD: Communication Efficient Federated Learning via Knowledge Distillation
• ChatGPT for Shaping the Future of Dentistry: The Potential of Multi-Modal Large Language Model
• Deep Representation Learning of Patient Data from Electronic Health Records (EHR): A Systematic Review
• A Scalable Discrete-Time Survival Model for Neural Networks
• Machine-Learning-Based Diagnostics of EEG Pathology
• Natural Language Processing for Smart Healthcare
• Deep learning for comprehensive forecasting of Alzheimer's Disease progression
• Deep Representation Learning of Electronic Health Records to Unlock Patient Stratification at Scale
• A Review on Explainable Artificial Intelligence for Healthcare: Why, How, and When?
• TS-CHIEF: A Scalable and Accurate Forest Algorithm for Time Series Classification
• Patient2Vec: A Personalized Interpretable Deep Representation of the Longitudinal Electronic Health Record
• Unmasking Bias in AI: A Systematic Review of Bias Detection and Mitigation Strategies in Electronic Health Record-based Models
• Deep learning for temporal data representation in electronic health records: A systematic review of challenges and methodologies
• Automatic Sleep Staging of EEG Signals: Recent Development, Challenges, and Future Directions
• Evaluation of post-hoc interpretability methods in time-series classification
• S-LIME: Stabilized-LIME for Model Explanation
• Improving Emergency Department ESI Acuity Assignment Using Machine Learning and Clinical Natural Language Processing
• AI, Opacity, and Personal Autonomy
• Quantum kernels for real-world predictions based on electronic health records
• Stratified cross-validation for unbiased and privacy-preserving federated learning
• Med-BERT: pre-trained contextualized embeddings on large-scale structured electronic health records for disease prediction
• Temporal Pointwise Convolutional Networks for Length of Stay Prediction in the Intensive Care Unit
• Analyzing the Role of Model Uncertainty for Electronic Health Records
• Quantum Machine Learning for Digital Health? A Systematic Review
• A Multi-Center Study on the Adaptability of a Shared Foundation Model for Electronic Health Records
• Ten Quick Tips for Deep Learning in Biology
• Interpreting a Recurrent Neural Network's Predictions of ICU Mortality Risk
• Simultaneous Modeling of Multiple Complications for Risk Profiling in Diabetes Care
• Temporal Self-Attention Network for Medical Concept Embedding
• Multimodal spatiotemporal graph neural networks for improved prediction of 30-day all-cause hospital readmission
• GenHPF: General Healthcare Predictive Framework with Multi-task Multi-source Learning
• Identification of Pediatric Respiratory Diseases Using Fine-grained Diagnosis System
• EMERGE: Enhancing Multimodal Electronic Health Records Predictive Modeling with Retrieval-Augmented Generation
• Unveiling the frontiers of deep learning: innovations shaping diverse domains
• Predicting Acute Kidney Injury at Hospital Re-entry Using High-dimensional Electronic Health Record Data
• Survival Function Matching for Calibrated Time-to-Event Predictions
• AI-driven Java Performance Testing: Balancing Result Quality with Testing Time
• Differentiating Viral and Bacterial Infections: A Machine Learning Model Based on Routine Blood Test Values
• Detecting of a Patient's Condition From Clinical Narratives Using Natural Language Representation
• Patient Outcome Predictions Improve Operations at a Large Hospital Network
• MIA-Prognosis: A Deep Learning Framework to Predict Therapy Response
• Predicting future state for adaptive clinical pathway management
• Generalized and Transferable Patient Language Representation for Phenotyping with Limited Data
• A Novel Generative Multi-Task Representation Learning Approach for Predicting Postoperative Complications in Cardiac Surgery Patients
• Mitigating Health Disparities in EHR via Deconfounder
• Deep Semi-Supervised Learning for Time Series Classification
• Health Status Prediction with Local-Global Heterogeneous Behavior Graph
• VBridge: Connecting the Dots Between Features and Data to Explain Healthcare Models
• HyMaTE: A Hybrid Mamba and Transformer Model for EHR Representation Learning
• Enhancing deep learning models for time series classification via knowledge distillation
• Enhancing Time Series Classification with Diversity-Driven Neural Network Ensembles