Human-LLM Dialogue Improves Diagnostic Accuracy in Emergency Care

Burcu Sayin, Ngoc Vo Hong, Ipek Baris Schlicht, Jacopo Staiano, Pasquale Minervini +6 more
5/8/2026
cs.AI

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

Clinical decision-making in emergency medicine demands rapid, accurate diagnoses under uncertainty. Despite benchmark progress, evidence for LLMs as interactive aids in live physician workflows remains sparse. MedSyn lets physicians iteratively query an LLM provided with the full clinical record while initially viewing only the chief complaint. Seven physicians (three seniors, four residents) completed baseline and AI-assisted sessions across 52 MIMIC-IV cases stratified by difficulty. Blinded evaluation showed residents' Hard-case correctness rose from 0.589 to 0.734; difficulty-standardised completely-correct rates confirmed a medium effect (Δ = 0.092; p = 0.071; d = 0.47). Automated metrics corroborated these gains: standardised any-match accuracy improved by 0.156 (p < 0.0001), and residents showed the largest F1 gain (Δ = 0.138; p < 0.0001). Dialogue analysis revealed expertise-dependent strategies (seniors asked targeted, hypothesis-driven questions; residents relied on broader queries) and cross-expertise concordance increased (Δ = 0.145; p < 0.0001). Interactive LLM support meaningfully enhances diagnostic reasoning.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Towards Accurate Differential Diagnosis with Large Language Models

85% match2023

Language Models And A Second Opinion Use Case: The Pocket Professional

85% match2024

ClinEnv: An Interactive Multi-Stage Long Horizon EHR Environment for Agents

83% match2026

Are LLMs Ready to Assist Physicians? PhysAssistBench for Interactive Doctor-Patient-EHR Assistance

83% match2026

CLExEval: A Human-in-the-Loop Framework for Qualitative Evaluation of LLM Clinical Reasoning

83% match2026

Advancing Medical Artificial Intelligence Using a Century of Cases

82% match2025

Cite this paper

@article{sayin2026humanllm,
  title  = {Human-LLM Dialogue Improves Diagnostic Accuracy in Emergency Care},
  author = {Burcu Sayin and Ngoc Vo Hong and Ipek Baris Schlicht and Jacopo Staiano and Pasquale Minervini and Sara Allievi and Nicola Susca and Nicola Osti and Alberto Maino and Vito Racanelli and Andrea Passerini},
  year   = {2026},
  eprint = {2605.08533},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2605.08533v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2605.08533.svg)](https://codeofpaper.com/paper/2605.08533)

Discussion