A Comprehensive Survey of Electronic Health Record Modeling: From Deep Learning Approaches to Large Language Models

2025-07-17

AI Summary

Electronic health record (EHR) data exhibit heterogeneity, irregular temporal sampling, and strong domain dependency—distinct from computer vision or natural language processing tasks—posing significant challenges for effective AI-driven clinical decision support. This paper presents a systematic survey of deep learning and large language model (LLM) approaches for EHR modeling. We propose, for the first time, a unified five-dimensional taxonomy covering data representation, architectural design, learning paradigms, multimodal fusion, and LLM-specific applications. We innovatively integrate classical deep learning with LLMs, formally defining three emerging directions: EHR foundation models, clinical agents, and EHR-to-text reasoning. Our framework enhances temporal modeling accuracy, cross-institutional generalizability, and interpretability via structured sequential representation learning, joint modeling with clinical knowledge graphs, and synergistic self-supervised, knowledge-enhanced, and multimodal fine-tuning strategies. All methods are open-sourced at https://survey-on-tabular-data.github.io/.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: Human-in-the-loop Machine Learning
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Artificial intelligence (AI) has demonstrated significant potential in transforming healthcare through the analysis and modeling of electronic health records (EHRs). However, the inherent heterogeneity, temporal irregularity, and domain-specific nature of EHR data present unique challenges that differ fundamentally from those in vision and natural language tasks. This survey offers a comprehensive overview of recent advancements at the intersection of deep learning, large language models (LLMs), and EHR modeling. We introduce a unified taxonomy that spans five key design dimensions: data-centric approaches, neural architecture design, learning-focused strategies, multimodal learning, and LLM-based modeling systems. Within each dimension, we review representative methods addressing data quality enhancement, structural and temporal representation, self-supervised learning, and integration with clinical knowledge. We further highlight emerging trends such as foundation models, LLM-driven clinical agents, and EHR-to-text translation for downstream reasoning. Finally, we discuss open challenges in benchmarking, explainability, clinical alignment, and generalization across diverse clinical settings. This survey aims to provide a structured roadmap for advancing AI-driven EHR modeling and clinical decision support. For a comprehensive list of EHR-related methods, kindly refer to https://survey-on-tabular-data.github.io/.

Problem

• Addressing EHR data heterogeneity and temporal irregularity challenges
• Surveying deep learning and LLM advancements in EHR modeling
• Exploring clinical knowledge integration and self-supervised learning methods

Innovation

• Deep learning for EHR data analysis
• Large language models in healthcare
• Multimodal learning with clinical knowledge