Logo image
Automated Clinical Problem Detection from SOAP Notes using a Collaborative Multi-Agent LLM Architecture
Abstract   Open access

Automated Clinical Problem Detection from SOAP Notes using a Collaborative Multi-Agent LLM Architecture

Yeawon Lee, Xiaoyang Wang and Christopher Yang
Proceedings of the 16th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, pp 1-1
12 Oct 2025
url
https://doi.org/10.1145/3765612.3767792View
Published, Version of Record (VoR) Open

Abstract

Applied computing -- Life and medical sciences -- Health informatics Computing methodologies -- Artificial intelligence -- Natural language processing -- Natural language generation
Interpreting clinical narratives is critical, yet single-agent LLMs are brittle and create a single point of failure. We present a collaborative MAS that models a clinical team to detect problems using only S+O—enforcing inference rather than A/P keyword lookup.

Metrics

11 Record Views

Details

UN Sustainable Development Goals (SDGs)

This publication has contributed to the advancement of the following goals:

#3 Good Health and Well-Being

InCites Highlights

Data related to this publication, from InCites Benchmarking & Analytics tool:

Web of Science research areas
Mathematical & Computational Biology
Medical Informatics
Logo image