Deep Representation Learning of Patient Data from Electronic Health Records (EHR): A Systematic Review

Abstract

Patient representation learning refers to learning a dense mathematical representation of a patient that encodes meaningful information from Electronic Health Records (EHRs). This is generally performed using advanced deep learning methods. This study presents a systematic review of this field and provides both qualitative and quantitative analyses from a methodological perspective. We identified studies developing patient representations from EHRs with deep learning methods from MEDLINE, EMBASE, Scopus, the Association for Computing Machinery (ACM) Digital Library, and Institute of Electrical and Electronics Engineers (IEEE) Xplore Digital Library. After screening 363 articles, 49 papers were included for a comprehensive data collection. We noticed a typical workflow starting with feeding raw data, applying deep learning models, and ending with clinical outcome predictions as evaluations of the learned representations. Specifically, learning representations from structured EHR data was dominant (37 out of 49 studies). Recurrent Neural Networks were widely applied as the deep learning architecture (LSTM: 13 studies, GRU: 11 studies). Disease prediction was the most common application and evaluation (31 studies). Benchmark datasets were mostly unavailable (28 studies) due to privacy concerns of EHR data, and code availability was assured in 20 studies. We show the importance and feasibility of learning comprehensive representations of patient EHR data through a systematic review. Advances in patient representation learning techniques will be essential for powering patient-level EHR analyses. Future work will still be devoted to leveraging the richness and potential of available EHR data. Knowledge distillation and advanced learning techniques will be exploited to assist the capability of learning patient representation further.

References in corpus (29)

• Distributed Representations of Words and Phrases and their Compositionality
• Sequence to Sequence Learning with Neural Networks
• UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Scalable and accurate deep learning for electronic health records
• Tutorial on Variational Autoencoders
• Federated Optimization:Distributed Optimization Beyond the Datacenter
• Dipole: Diagnosis Prediction in Healthcare via Attention-based Bidirectional Recurrent Neural Networks
• On Tensors, Sparsity, and Nonnegative Factorizations
• Doctor AI: Predicting Clinical Events via Recurrent Neural Networks
• Patient2Vec: A Personalized Interpretable Deep Representation of the Longitudinal Electronic Health Record
• MiME: Multilevel Medical Embedding of Electronic Health Records for Predictive Healthcare
• Federated Tensor Factorization for Computational Phenotyping
• Federated Learning for Healthcare Informatics
• Med-BERT: pre-trained contextualized embeddings on large-scale structured electronic health records for disease prediction
• Learning Tasks for Multitask Learning: Heterogenous Patient Populations in the ICU
• Deep EHR: Chronic Disease Prediction Using Medical Notes
• Patient representation learning and interpretable evaluation using clinical notes
• Exploiting Convolutional Neural Network for Risk Prediction with Medical Feature Embedding
• Improved Hierarchical Patient Classification with Language Model Pretraining over Clinical Notes
• Effective Representations of Clinical Notes
• Language Models Are An Effective Patient Representation Learning Technique For Electronic Health Record Data
• Generalized and Transferable Patient Language Representation for Phenotyping with Limited Data
• Learning Hierarchical Representations of Electronic Health Records for Clinical Outcome Prediction
• Representation Learning with Autoencoders for Electronic Health Records: A Comparative Study
• Two-stage Federated Phenotyping and Patient Representation Learning
• Unsupervised Representation for EHR Signals and Codes as Patient Status Vector
• Unsupervised patient representations from clinical notes with interpretable classification decisions
• $\mathtt{MedGraph}:$ Structural and Temporal Representation Learning of Electronic Medical Records

Cited by in corpus (12)

• Deep learning for temporal data representation in electronic health records: A systematic review of challenges and methodologies
• Ethical Framework for Harnessing the Power of AI in Healthcare and Beyond
• A Multimodal Transformer: Fusing Clinical Notes with Structured EHR Data for Interpretable In-Hospital Mortality Prediction
• Meta-learning in healthcare: A survey
• Self-supervised learning-based general laboratory progress pretrained model for cardiovascular event detection
• Generalized and Transferable Patient Language Representation for Phenotyping with Limited Data
• PRISM: Mitigating EHR Data Sparsity via Learning from Missing Feature Calibrated Prototype Patient Representations
• Machine Learning for Multimodal Electronic Health Records-based Research: Challenges and Perspectives
• Will Large Language Models Transform Clinical Prediction?
• Explainable Health Risk Predictor with Transformer-based Medicare Claim Encoder
• Dual Model Deep Learning for Alzheimer Prognostication
• A Study into patient similarity through representation learning from medical records