Accurate diagnosis of Mendelian diseases is crucial for precision therapy and assistance in preimplantation genetic diagnosis. However, existing methods often fall short of clinical standards or depend on extensive datasets to build pretrained machine learning models. To address this, we introduce an innovative LLM-Driven multi-agent debate system (MD2GPS) with natural language explanations of the diagnostic results. It utilizes a language model to transform results from data-driven and knowledge-driven agents into natural language, then fostering a debate between these two specialized agents. This system has been tested on 1,185 samples across four independent datasets, enhancing the TOP1 accuracy from 42.9% to 66% on average. Additionally, in a challenging cohort of 72 cases, MD2GPS identified potential pathogenic genes in 12 patients, reducing the diagnostic time by 90%. The methods within each module of this multi-agent debate system are also replaceable, facilitating its adaptation for diagnosing and researching other complex diseases.
@article{arxiv.2504.07881,
title = {An LLM-Driven Multi-Agent Debate System for Mendelian Diseases},
author = {Xinyang Zhou and Yongyong Ren and Qianqian Zhao and Daoyi Huang and Xinbo Wang and Tingting Zhao and Zhixing Zhu and Wenyuan He and Shuyuan Li and Yan Xu and Yu Sun and Yongguo Yu and Shengnan Wu and Jian Wang and Guangjun Yu and Dake He and Bo Ban and Hui Lu},
journal= {arXiv preprint arXiv:2504.07881},
year = {2025}
}