Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis

Abstract

The past decade has seen an explosion in the amount of digital information stored in electronic health records (EHR). While primarily designed for archiving patient clinical information and administrative healthcare tasks, many researchers have found secondary use of these records for various clinical informatics tasks. Over the same period, the machine learning community has seen widespread advances in deep learning techniques, which also have been successfully applied to the vast amount of EHR data. In this paper, we review these deep EHR systems, examining architectures, technical aspects, and clinical applications. We also identify shortcomings of current techniques and discuss avenues of future research for EHR-based deep learning.

Accepted for publication with Journal of Biomedical and Health Informatics: http://ieeexplore.ieee.org/abstract/document/8086133/

References in corpus (5)

• Recurrent Neural Networks for Multivariate Time Series with Missing Values
• Medical Concept Representation Learning from Electronic Health Records and its Application on Heart Failure Prediction
• Distilling Knowledge from Deep Networks with Applications to Healthcare Domain
• Exploiting Task-Oriented Resources to Learn Word Embeddings for Clinical Abbreviation Expansion
• Bidirectional Recurrent Neural Networks for Medical Event Detection in Electronic Health Records

Cited by in corpus (108)

• Scalable and accurate deep learning for electronic health records
• Federated Learning for Internet of Things: A Comprehensive Survey
• ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission
• Human Activity Recognition using Inertial, Physiological and Environmental Sensors: a Comprehensive Survey
• Medical Deep Learning -- A systematic Meta-Review
• A Systematic Review of Natural Language Processing Applied to Radiology Reports
• Hardware Implementation of Deep Network Accelerators Towards Healthcare and Biomedical Applications
• Deep Learning in Pharmacogenomics: From Gene Regulation to Patient Stratification
• Medical Visual Question Answering: A Survey
• Secondary Use of Electronic Health Record: Opportunities and Challenges
• Deep learning for temporal data representation in electronic health records: A systematic review of challenges and methodologies
• DeepSOFA: A Continuous Acuity Score for Critically Ill Patients using Clinically Interpretable Deep Learning
• Comparing Clinical Judgment with MySurgeryRisk Algorithm for Preoperative Risk Assessment: A Pilot Study
• An Empirical Evaluation of Deep Learning for ICD-9 Code Assignment using MIMIC-III Clinical Notes
• Bidirectional Representation Learning from Transformers using Multimodal Electronic Health Record Data to Predict Depression
• SECNLP: A Survey of Embeddings in Clinical Natural Language Processing
• Obesity Prediction with EHR Data: A deep learning approach with interpretable elements
• Zero-shot information extraction from radiological reports using ChatGPT
• Blockchain inspired secure and reliable data exchange architecture for cyber-physical healthcare system 4.0
• A Deep Active Survival Analysis Approach for Precision Treatment Recommendations: Application of Prostate Cancer
• Security and Privacy Issues in Deep Learning
• I-MAD: Interpretable Malware Detector Using Galaxy Transformer
• A Review of Deep Learning Methods for Irregularly Sampled Medical Time Series Data
• Embedded deep learning in ophthalmology: Making ophthalmic imaging smarter
• Temporal Self-Attention Network for Medical Concept Embedding
• Interpretation of machine learning predictions for patient outcomes in electronic health records
• Robust Aggregation for Adaptive Privacy Preserving Federated Learning in Healthcare
• Natural language processing of MIMIC-III clinical notes for identifying diagnosis and procedures with neural networks
• Identification of Pediatric Respiratory Diseases Using Fine-grained Diagnosis System
• RAIM: Recurrent Attentive and Intensive Model of Multimodal Patient Monitoring Data
• Explainable artificial intelligence model to predict acute critical illness from electronic health records
• RAMIE: Retrieval-Augmented Multi-task Information Extraction with Large Language Models on Dietary Supplements
• Machine Learning for Administrative Health Records: A Systematic Review of Techniques and Applications
• Differential Privacy Techniques for Cyber Physical Systems: A Survey
• Meta-learning in healthcare: A survey
• DeepHealth: Review and challenges of artificial intelligence in health informatics
• Preserving Patient Privacy while Training a Predictive Model of In-hospital Mortality
• Deep-Dup: An Adversarial Weight Duplication Attack Framework to Crush Deep Neural Network in Multi-Tenant FPGA
• DeepHammer: Depleting the Intelligence of Deep Neural Networks through Targeted Chain of Bit Flips
• OptiLIME: Optimized LIME Explanations for Diagnostic Computer Algorithms
• Federated Learning for Smart Healthcare: A Survey
• BEHRT: Transformer for Electronic Health Records
• Sequential Interpretability: Methods, Applications, and Future Direction for Understanding Deep Learning Models in the Context of Sequential Data
• Improved Hierarchical Patient Classification with Language Model Pretraining over Clinical Notes
• Unsupervised EHR-based Phenotyping via Matrix and Tensor Decompositions
• Machine Learning and Visualization in Clinical Decision Support: Current State and Future Directions
• Open Set Medical Diagnosis
• POPDx: An Automated Framework for Patient Phenotyping across 392,246 Individuals in the UK Biobank Study
• Mixed Pooling Multi-View Attention Autoencoder for Representation Learning in Healthcare
• All Data Inclusive, Deep Learning Models to Predict Critical Events in the Medical Information Mart for Intensive Care III Database (MIMIC III)
• Bootstrapping Your Own Positive Sample: Contrastive Learning With Electronic Health Record Data
• COPER: Continuous Patient State Perceiver
• Multi-Task Learning for Post-transplant Cause of Death Analysis: A Case Study on Liver Transplant
• Multimodal Machine Learning for Automated ICD Coding
• Representation Learning with Autoencoders for Electronic Health Records: A Comparative Study
• Deep Representation for Patient Visits from Electronic Health Records
• Neural Temporal Point Processes For Modelling Electronic Health Records
• Identify Susceptible Locations in Medical Records via Adversarial Attacks on Deep Predictive Models
• Predicting the Travel Distance of Patients to Access Healthcare using Deep Neural Networks
• RL4health: Crowdsourcing Reinforcement Learning for Knee Replacement Pathway Optimization
• B-HAR: an open-source baseline framework for in depth study of human activity recognition datasets and workflows
• Self-supervised Representation Learning on Electronic Health Records with Graph Kernel Infomax
• Identifying Risk of Opioid Use Disorder for Patients Taking Opioid Medications with Deep Learning
• Interpretable Disease Prediction based on Reinforcement Path Reasoning over Knowledge Graphs
• A Knowledge Graph-based Approach for Exploring the U.S. Opioid Epidemic
• Deep Ensemble Tensor Factorization for Longitudinal Patient Trajectories Classification
• Self-Attention Enhanced Patient Journey Understanding in Healthcare System
• Blood lactate concentration prediction in critical care patients: handling missing values
• Disease phenotyping using deep learning: A diabetes case study
• Transfer Learning in Electronic Health Records through Clinical Concept Embedding
• Empirical Analysis of Zipf's Law, Power Law, and Lognormal Distributions in Medical Discharge Reports
• Multiple Sclerosis Severity Classification From Clinical Text
• A generic rule-based system for clinical trial patient selection
• Machine Learning with Electronic Health Records is vulnerable to Backdoor Trigger Attacks
• Explainable Health Risk Predictor with Transformer-based Medicare Claim Encoder
• A Survey of Techniques All Classifiers Can Learn from Deep Networks: Models, Optimizations, and Regularization
• Deep learning models are not robust against noise in clinical text
• Differentially Private Federated Learning via Inexact ADMM
• Ascle: A Python Natural Language Processing Toolkit for Medical Text Generation
• Sequential Diagnosis Prediction with Transformer and Ontological Representation
• Machine learning applications using diffusion tensor imaging of human brain: A PubMed literature review
• Adversarial Sample Enhanced Domain Adaptation: A Case Study on Predictive Modeling with Electronic Health Records
• Consensus-based Interpretable Deep Neural Networks with Application to Mortality Prediction
• The accuracy vs. coverage trade-off in patient-facing diagnosis models
• Med2Meta: Learning Representations of Medical Concepts with Meta-Embeddings
• A self-attention based deep learning method for lesion attribute detection from CT reports
• An Analysis Of Protected Health Information Leakage In Deep-Learning Based De-Identification Algorithms
• $\mathtt{MedGraph}:$ Structural and Temporal Representation Learning of Electronic Medical Records
• Inpatient2Vec: Medical Representation Learning for Inpatients
• ELMV: an Ensemble-Learning Approach for Analyzing Electrical Health Records with Significant Missing Values
• Unsupervised Annotation of Phenotypic Abnormalities via Semantic Latent Representations on Electronic Health Records
• Patient Outcome and Zero-shot Diagnosis Prediction with Hypernetwork-guided Multitask Learning
• Deep Learning -- A first Meta-Survey of selected Reviews across Scientific Disciplines, their Commonalities, Challenges and Research Impact
• Longitudinal patient stratification of electronic health records with flexible adjustment for clinical outcomes
• Domain Adaptation in Highly Imbalanced and Overlapping Datasets
• TRACE: Early Detection of Chronic Kidney Disease Onset with Transformer-Enhanced Feature Embedding
• Developing a Portable Natural Language Processing Based Phenotyping System
• Temporal Clustering with External Memory Network for Disease Progression Modeling
• Risk factor identification for incident heart failure using neural network distillation and variable selection
• Revealing patterns in HIV viral load data and classifying patients via a novel machine learning cluster summarization method
• MIPO: Mutual Integration of Patient Journey and Medical Ontology for Healthcare Representation Learning
• Investigating Critical Risk Factors in Liver Cancer Prediction
• Analysing Risk of Coronary Heart Disease through Discriminative Neural Networks
• Modeling Treatment Delays for Patients using Feature Label Pairs in a Time Series
• BiteNet: Bidirectional Temporal Encoder Network to Predict Medical Outcomes
• A Literature Review of Recent Graph Embedding Techniques for Biomedical Data
• Deep Semi-Supervised Embedded Clustering (DSEC) for Stratification of Heart Failure Patients
• Temporal Cascade and Structural Modelling of EHRs for Granular Readmission Prediction