Patient2Vec: A Personalized Interpretable Deep Representation of the Longitudinal Electronic Health Record

Abstract

The wide implementation of electronic health record (EHR) systems facilitates the collection of large-scale health data from real clinical settings. Despite the significant increase in adoption of EHR systems, this data remains largely unexplored, but presents a rich data source for knowledge discovery from patient health histories in tasks such as understanding disease correlations and predicting health outcomes. However, the heterogeneity, sparsity, noise, and bias in this data present many complex challenges. This complexity makes it difficult to translate potentially relevant information into machine learning algorithms. In this paper, we propose a computational framework, Patient2Vec, to learn an interpretable deep representation of longitudinal EHR data which is personalized for each patient. To evaluate this approach, we apply it to the prediction of future hospitalizations using real EHR data and compare its predictive performance with baseline methods. Patient2Vec produces a vector space with meaningful structure and it achieves an AUC around 0.799 outperforming baseline methods. In the end, the learned feature importance can be visualized and interpreted at both the individual and population levels to bring clinical insights.

arXiv commentAccepted by IEEE Access

References in corpus (14)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• On the difficulty of training Recurrent Neural Networks
• Scalable and accurate deep learning for electronic health records
• A Structured Self-attentive Sentence Embedding
• Recent Trends in Deep Learning Based Natural Language Processing
• Convolutional Neural Networks for Sentence Classification
• Recurrent Models of Visual Attention
• Learning to Diagnose with LSTM Recurrent Neural Networks
• HDLTex: Hierarchical Deep Learning for Text Classification
• Recurrent Neural Networks for Multivariate Time Series with Missing Values
• Contextual LSTM (CLSTM) models for Large scale NLP tasks
• Deep Learning applied to NLP
• RMDL: Random Multimodel Deep Learning for Classification
• Generative and Discriminative Text Classification with Recurrent Neural Networks

Cited by in corpus (37)

• Text Classification Algorithms: A Survey
• Deep Representation Learning of Patient Data from Electronic Health Records (EHR): A Systematic Review
• A Review on Explainable Artificial Intelligence for Healthcare: Why, How, and When?
• Deep learning for temporal data representation in electronic health records: A systematic review of challenges and methodologies
• TimeSHAP: Explaining Recurrent Models through Sequence Perturbations
• Obesity Prediction with EHR Data: A deep learning approach with interpretable elements
• HMIC: Hierarchical Medical Image Classification, A Deep Learning Approach
• From Explainable to Interpretable Deep Learning for Natural Language Processing in Healthcare: How Far from Reality?
• Multi-Label Clinical Time-Series Generation via Conditional GAN
• Uncertainty-Aware Deep Ensembles for Reliable and Explainable Predictions of Clinical Time Series
• Interpreting a Recurrent Neural Network's Predictions of ICU Mortality Risk
• CEHR-BERT: Incorporating temporal information from structured EHR data to improve prediction tasks
• Network representation learning systematic review: ancestors and current development state
• Online Disease Self-diagnosis with Inductive Heterogeneous Graph Convolutional Networks
• Machine Learning for Administrative Health Records: A Systematic Review of Techniques and Applications
• Unbox the Black-box for the Medical Explainable AI via Multi-modal and Multi-centre Data Fusion: A Mini-Review, Two Showcases and Beyond
• Sequential Interpretability: Methods, Applications, and Future Direction for Understanding Deep Learning Models in the Context of Sequential Data
• Generalized and Transferable Patient Language Representation for Phenotyping with Limited Data
• Language Models Are An Effective Patient Representation Learning Technique For Electronic Health Record Data
• Patient Similarity Analysis with Longitudinal Health Data
• Gender Detection on Social Networks using Ensemble Deep Learning
• Personalized Event Prediction for Electronic Health Records
• Challenges for Reinforcement Learning in Healthcare
• Is In-hospital Meta-information Useful for Abstractive Discharge Summary Generation?
• Explainable Health Risk Predictor with Transformer-based Medicare Claim Encoder
• Efficient Observation Time Window Segmentation for Administrative Data Machine Learning
• Improving Irregularly Sampled Time Series Learning with Dense Descriptors of Time
• Medical Concept Representation Learning from Claims Data and Application to Health Plan Payment Risk Adjustment
• Interpretable Additive Recurrent Neural Networks For Multivariate Clinical Time Series
• Sparse Longitudinal Representations of Electronic Health Record Data for the Early Detection of Chronic Kidney Disease in Diabetic Patients
• Inpatient2Vec: Medical Representation Learning for Inpatients
• Longitudinal patient stratification of electronic health records with flexible adjustment for clinical outcomes
• Diagnosis and Analysis of Celiac Disease and Environmental Enteropathy on Biopsy Images using Deep Learning Approaches
• A Study into patient similarity through representation learning from medical records
• Towards Collaborative Fairness in Federated Learning Under Imbalanced Covariate Shift
• Deep Semi-Supervised Embedded Clustering (DSEC) for Stratification of Heart Failure Patients
• SAVEHR: Self Attention Vector Representations for EHR based Personalized Chronic Disease Onset Prediction and Interpretability