Skip to content
Review Open access

HealthFlow: automating electronic health record analysis via a strategically self-evolving multi-agent framework

Aug 2026 · npj Digital Medicine · Vol 9 · 1 citation · 68 references
Medicine Computer Science

TL;DR

HealthFlow is presented, a multi-agent framework that converts prior EHR analyses into structured, governed experience for planning under dataset-specific and methodological constraints and consistently outperforms strong baselines in generating valid clinical artifacts and completing complex EHR analysis pipelines.

Abstract

Electronic health records (EHRs) are a rich source of real-world clinical data, but turning them into valid analyses remains slow, brittle, and expert-intensive. Although recent AI agents can answer medical questions and use tools, automating full EHR workflows remains difficult because small planning or execution errors can invalidate otherwise plausible analyses. Here we present HealthFlow, a multi-agent framework that converts prior EHR analyses into structured, governed experience for planning under dataset-specific and methodological constraints. We also introduce EHRFlowBench, a rigorously curated benchmark of EHR analysis tasks derived from 51,280 peer-reviewed papers. Across EHRFlowBench and four established benchmarks (MedAgentBoard, MedAgentsBench, HLE, and CureBench), HealthFlow consistently outperforms strong baselines in generating valid clinical artifacts and completing complex EHR analysis pipelines. These results show that governed reuse of prior analytical experience improves robustness in health data science and opens a promising path to automating open-ended EHR analysis.

Read PDF

Similar papers

EHR-RobustGym: Benchmarking and Training Agents for Robust Clinical Reasoning

In hospital workflows, electronic health records (EHRs) are often noisy, and may not contain the evidence needed to confirm events or measurements referenced in a clinical query. Even when database retrieval succeeds, clinical agents can overlook such discrepancies and return plausible but unsupported answers. We intro...

Yi-Tong Qiao, Yan-Cheng Jin, Lei Liu et al. · 0 citations
#artificial intelligence Preprint Oct 2026

MedHarnessBench: A Unified Benchmark for Healthcare Agent Evaluation

Healthcare agents must transform longitudinal clinical evidence into reliable actions through heterogeneous tools and stateful workflows, conditions under which model-centric systems may lose context, misuse tools, fail to verify consequential transitions, or cross authorization boundaries. Existing medical-agent bench...

Rui Tang, Hong-Qiu Wang · 0 citations

EHR2Trace: Auditable EHR Data Infrastructure for Patient World Models and Clinical Agents

Patient world models and clinical agents aim to predict changes in patients'health and support clinical work. Developing these systems requires reliable histories of patient conditions, treatments, and the information available at each decision. Electronic health records (EHRs) contain these histories, but differences...

Xin-Ye Yang, Yu-Li Wang, Cheng-Ting Lin et al. · 0 citations
Sep 2026

A Living Benchmark for Information Retrieval from Electronic Health Records

A scalable framework that automatically generates question--answer pairs from longitudinal EHR notes that supports evaluations that static benchmarks cannot, including the generation of multiple answers that reflect variation in clinician reasoning for robust performance assessment and continuously refreshing benchmark...

J. Cahoon, C. Stanwyck, Sulaiman Somani et al. · 1 citation
#artificial intelligence Review Oct 2026

ProCARE: Real-World Study Automation via Profile-Grounded Evidence Contracts

Real-world studies (RWS) analyze routinely collected healthcare data, such as electronic health records and insurance claims, to estimate treatment effects, monitor safety, and identify risk factors outside randomized trials. Automating RWS with large language model agents is appealing but brittle: valid analyses depen...

Zhao-Yu Fan, Bo-Wen Han, Jin-Cheng Ou et al. · 1 citation
Review Open access Sep 2026

From electronic health records to real-world evidence: Savana Next-Generation Registry digital solution

SNGR demonstrates how unstructured EHR data can be transformed into analysis-ready datasets for RWE generation, and provides a scalable and methodologically robust infrastructure for next-generation registries, particularly suited for oncology and other data-rich clinical domains.

J. Marin-Corral, N. Iglesias, S. Menke et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.