# ChatHealthAI: Aligning Electronic Health Record Representations with Large Language Models for Grounded Clinical Reasoning

Source: [ChatHealthAI: Aligning Electronic Health Record Representations with Large Language Models for Grounded Clinical Reasoning](<https://www.sota2.com/research/paper/6a21067ec10484bac23f0036>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-10T05:00:46.690Z

Authors: Bo-Hong Wang, Baicheng Peng, Ruilin Wang, Jun Bai, Ziyang Song, Yue Li

Published: 2026-06-01T19:21:18.000Z

## Abstract

Large language models (LLMs) exhibit strong natural-language reasoning abilities for clinical decision support, but struggle to effectively model structured longitudinal electronic health records (EHRs). In contrast, EHR foundation models can learn predictive patient representations, yet lack interpretable language-based reasoning. To bridge this gap, we propose ChatHealthAI, a multimodal reasoning framework that aligns structured EHR representations from a pretrained EHR foundation model with the semantic space of a frozen LLM through a task-aware resampler. By integrating longitudinal patient representations with refined clinical event descriptions, ChatHealthAI enables clinically grounded natural-language reasoning while maintaining accurate patient prediction. We evaluated ChatHealthAI on three clinical predictive tasks from the EHRSHOT benchmark. Results show that ChatHealthAI improves reasoning quality and interpretability while preserving competitive predictive performance. These findings highlight the potential of integrating EHR foundation models with pretrained LLMs for interpretable clinical prediction.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [ICU Admission on EHRSHOT (test)](<https://www.sota2.com/research/sota/icu-admission-on-ehrshot-test.md>): ICU Admission; EHRSHOT (test); Precision: 38.5.

- [Length of Stay (LOS) on EHRSHOT (test)](<https://www.sota2.com/research/sota/length-of-stay-los-on-ehrshot-test.md>): Length of Stay (LOS); EHRSHOT (test); Precision: 44.2.

- [Readmission on EHRSHOT (test)](<https://www.sota2.com/research/sota/readmission-on-ehrshot-test.md>): Readmission; EHRSHOT (test); Precision: 20.8.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2606.02802>)

[PDF](<https://arxiv.org/pdf/2606.02802.pdf>)