electronic-health-records

This paper presents MedNotes, a multi-agent pipeline for generating source-grounded synthetic clinical notes from longitudinal structured EHR data, achieving high accuracy and improving downstream clinical modeling tasks.

This paper introduces M2G-LLM, a framework that enhances Large Language Models with multimodal graph reasoning via Graph Neural Networks to improve clinical prediction tasks using electronic health records.

This research evaluates the enhancement of opioid use disorder prediction by integrating patient-reported survey data with electronic health records, demonstrating improved performance across multiple machine learning models.

This paper presents a scalable clinical data infrastructure and compares deep learning (TG-CNN) with traditional machine learning models (LASSO and Random Forests) for predicting hospitalization risk in elderly patients with multiple long-term conditions, concluding that LASSO is better suited for clinical deployment due to superior calibration.

The paper proposes structured evidence routing, a router–predictor–reviewer workflow for incident risk prediction from multimodal longitudinal electronic health records, achieving competitive performance with interpretable patient-specific evidence trails.

The paper proposes a Relational Hypergraph Transformer (RHT) architecture for complex multi-table analysis in healthcare, addressing five dimensions of complexity with a unified approach and sparse attention mechanism. It includes formal analysis, open-source implementation, and empirical evaluation on synthetic electronic health records.

ATHENA is a knowledge-guided agentic neural architecture search framework that automates Transformer-based electronic health record modeling by reusing architecture knowledge across hospitals to reduce manual tuning.

This study demonstrates that large language models with institution-specific prompting can recover protected health information missed by existing de-identification systems, enhancing data privacy compliance in electronic health records.

The paper proposes LUNG-KGMM, a knowledge-guided multimodal framework for predicting lung cancer incidence by integrating EHR, radiology data, and clinical guidelines, demonstrating superior performance on the MIMIC dataset and real-world validation.

This Wired article explores how AI could help detect fatty liver disease earlier by analyzing electronic health records and lab reports, potentially enabling prevention and reversal of liver damage.

This paper introduces MiGHT-EHR, a multi-task graph transformer for heterogeneous temporal EHR data, jointly modeling clinical entities, temporal trajectories, and task dependencies. It outperforms state-of-the-art methods on MIMIC-III and MIMIC-IV across drug recommendation, length-of-stay, mortality, and readmission prediction.

This paper proposes Patients-like-me (PLM), a unified LM–GNN framework that integrates local patient semantics with global cohort structure for explainable clinical prediction. It introduces a Variational Expectation-Maximization algorithm and demonstrates state-of-the-art results on MIMIC-III and MIMIC-IV with reference-patient explanations.

This arXiv paper evaluates federated training of tokenized generative event models (GEMs) on ICU EHR data from three health systems, showing that federated learning preserves most centralized performance and improves cross-site transportability compared to conventional supervised models.

This paper introduces xMICD, a method that combines ICD code groupings with pre-trained embedding similarities to create low-dimensional, clinically interpretable patient representations, achieving predictive performance comparable to embedding-based approaches.

A scoping review of 190 studies characterizing end-to-end machine learning pipelines for surgical risk stratification and outcome prediction using EHR data, identifying methodological gaps in preprocessing, evaluation, and explainability.

Proposes a deep neural model combining multi-layer temporal convolutional networks with label-wise attention for medical coding, achieving significant improvements in F1 and recall scores over previous state-of-the-art.

This paper presents a formative study using a two-stage LLM pipeline (Gemini 2.5 Pro and Flash) to detect internal documentation inconsistencies in electronic health records, analyzing 3,000 discharge summaries and proposing a graded ontology for categorizing inconsistencies.

Proposes TRACER, a framework that integrates severity-grounded knowledge graphs and retrieval-augmented generation for trajectory-aware clinical risk prediction, achieving large gains in mortality and readmission prediction on MIMIC-III and MIMIC-IV datasets.

The paper proposes converting multimodal patient data (text, labs, vitals) into a single natural language sequence and fine-tuning LLMs for clinical prediction, achieving comparable or better performance than specialized fusion architectures across three tasks.

LongMedBench is a new benchmark for evaluating LLM-based medical agents on long-horizon clinical decision-making using real EHR data from MIMIC-IV. It includes 335 patients with multiple visits and proposes evaluation suites for fact-based QA, temporal reasoning, and long-horizon decision-making.