MiME: Multilevel Medical Embedding of Electronic Health Records for Predictive Healthcare

Abstract

Deep learning models exhibit state-of-the-art performance for many predictive healthcare tasks using electronic health records (EHR) data, but these models typically require training data volume that exceeds the capacity of most healthcare systems. External resources such as medical ontologies are used to bridge the data volume constraint, but this approach is often not directly applicable or useful because of inconsistencies with terminology. To solve the data insufficiency challenge, we leverage the inherent multilevel structure of EHR data and, in particular, the encoded relationships among medical codes. We propose Multilevel Medical Embedding (MiME) which learns the multilevel embedding of EHR data while jointly performing auxiliary prediction tasks that rely on this inherent EHR structure without the need for external labels. We conducted two prediction tasks, heart failure prediction and sequential disease prediction, where MiME outperformed baseline methods in diverse evaluation settings. In particular, MiME consistently outperformed all baselines when predicting heart failure on datasets of different volumes, especially demonstrating the greatest performance improvement (15% relative gain in PR-AUC over the best baseline) on the smallest dataset, demonstrating its ability to effectively model the multilevel structure of EHR data.

arXiv commentAccepted at NIPS 2018

References in corpus (5)

• Adam: A Method for Stochastic Optimization
• Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding
• Hadamard Product for Low-rank Bilinear Pooling
• Clinical Intervention Prediction and Understanding using Deep Networks
• Multi-Task Learning for Mental Health using Social Media Text

Cited by in corpus (18)

• Deep Representation Learning of Patient Data from Electronic Health Records (EHR): A Systematic Review
• Deep learning for temporal data representation in electronic health records: A systematic review of challenges and methodologies
• MIMIC-Extract: A Data Extraction, Preprocessing, and Representation Pipeline for MIMIC-III
• M${}^3$Care: Learning with Missing Modalities in Multimodal Healthcare Data
• Temporal Self-Attention Network for Medical Concept Embedding
• MeSIN: Multilevel Selective and Interactive Network for Medication Recommendation
• Machine Learning for Administrative Health Records: A Systematic Review of Techniques and Applications
• A Deep Learning Pipeline for Patient Diagnosis Prediction Using Electronic Health Records
• Pre-training of Graph Augmented Transformers for Medication Recommendation
• Representation Learning for Electronic Health Records
• Language Models Are An Effective Patient Representation Learning Technique For Electronic Health Record Data
• Modeling Irregular Time Series with Continuous Recurrent Units
• Learning the Graphical Structure of Electronic Health Records with Graph Convolutional Transformer
• MUFASA: Multimodal Fusion Architecture Search for Electronic Health Records
• Inpatient2Vec: Medical Representation Learning for Inpatients
• $\mathtt{MedGraph}:$ Structural and Temporal Representation Learning of Electronic Medical Records
• Self-Supervised Graph Learning with Hyperbolic Embedding for Temporal Health Event Prediction
• UNITE: Uncertainty-based Health Risk Prediction Leveraging Multi-sourced Data