# Trustworthy Agents for Electronic Health Records through Confidence Estimation

Source: [Trustworthy Agents for Electronic Health Records through Confidence Estimation](<https://www.sota2.com/research/paper/68fa7adb1e209131cea8588f>)

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

Data updated: 2025-10-26T05:28:46.355Z

Authors: Yongwoo Song, Minbyul Jeong, Mujeen Sung

Published: 2025-08-26T14:59:04.000Z

## Abstract

Large language models (LLMs) show promise for extracting information from Electronic Health Records (EHR) and supporting clinical decisions. However, deployment in clinical settings faces challenges due to hallucination risks. We propose Hallucination Controlled Accuracy at k% (HCAcc@k%), a novel metric quantifying the accuracy-reliability trade-off at varying confidence thresholds. We introduce TrustEHRAgent, a confidence-aware agent incorporating stepwise confidence estimation for clinical question answering. Experiments on MIMIC-III and eICU datasets show TrustEHRAgent outperforms baselines under strict reliability constraints, achieving improvements of 44.23%p and 25.34%p at HCAcc@70% while baseline methods fail at these thresholds. These results highlight limitations of traditional accuracy metrics in evaluating healthcare AI agents. Our work contributes to developing trustworthy clinical agents that deliver accurate information or transparently express uncertainty when confidence is low.

## 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.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2508.19096>)

[PDF](<https://arxiv.org/pdf/2508.19096.pdf>)
