Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yang, Tao, Huang, Dandan, Lin, Yunting, Wu, Pengfei, Wu, Zhikun, Ma, Gangyuan, Lu, Yulan, Dong, Xinran, Li, Dingpeng, Ge, Junshuang, Zhang, Zhiyan, Huang, Xuanzhao, Nong, Wenyan, Zhou, Yao, Tang, Hui, Yang, Hongxi, Zhang, Shijie, Li, Juan, Cao, Xiaojun, Yang, Lin, Gao, Xia, Xu, Kaishou, Gu, Xiaoqiong, Zhang, Wen, Xia, Huimin, Liu, Li, Zhou, Wenhao, Li, Mulin Jun
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2511.14638
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915625821011968
author Yang, Tao
Huang, Dandan
Lin, Yunting
Wu, Pengfei
Wu, Zhikun
Ma, Gangyuan
Lu, Yulan
Dong, Xinran
Li, Dingpeng
Ge, Junshuang
Zhang, Zhiyan
Huang, Xuanzhao
Nong, Wenyan
Zhou, Yao
Tang, Hui
Yang, Hongxi
Zhang, Shijie
Li, Juan
Cao, Xiaojun
Yang, Lin
Gao, Xia
Xu, Kaishou
Gu, Xiaoqiong
Zhang, Wen
Xia, Huimin
Liu, Li
Zhou, Wenhao
Li, Mulin Jun
author_facet Yang, Tao
Huang, Dandan
Lin, Yunting
Wu, Pengfei
Wu, Zhikun
Ma, Gangyuan
Lu, Yulan
Dong, Xinran
Li, Dingpeng
Ge, Junshuang
Zhang, Zhiyan
Huang, Xuanzhao
Nong, Wenyan
Zhou, Yao
Tang, Hui
Yang, Hongxi
Zhang, Shijie
Li, Juan
Cao, Xiaojun
Yang, Lin
Gao, Xia
Xu, Kaishou
Gu, Xiaoqiong
Zhang, Wen
Xia, Huimin
Liu, Li
Zhou, Wenhao
Li, Mulin Jun
contents Rare diseases affect hundreds of millions worldwide, yet diagnosis often spans years. Convectional pipelines decouple noisy evidence extraction from downstream inferential diagnosis, and general/medical large language models (LLMs) face scarce real world electronic health records (EHRs), stale domain knowledge, and hallucinations. We assemble a large, domain specialized clinical corpus and a clinician validated reasoning set, and develop RareSeek R1 via staged instruction tuning, chain of thought learning, and graph grounded retrieval. Across multicenter EHR narratives and public benchmarks, RareSeek R1 attains state of the art accuracy, robust generalization, and stability under noisy or overlapping phenotypes. Augmented retrieval yields the largest gains when narratives pair with prioritized variants by resolving ambiguity and aligning candidates to mechanisms. Human studies show performance on par with experienced physicians and consistent gains in assistive use. Notably, transparent reasoning highlights decisive non phenotypic evidence (median 23.1%, such as imaging, interventions, functional tests) underpinning many correct diagnoses. This work advances a narrative first, knowledge integrated reasoning paradigm that shortens the diagnostic odyssey and enables auditable, clinically translatable decision support.
format Preprint
id arxiv_https___arxiv_org_abs_2511_14638
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Specialized Large Language Model for Clinical Reasoning and Diagnosis in Rare Diseases
Yang, Tao
Huang, Dandan
Lin, Yunting
Wu, Pengfei
Wu, Zhikun
Ma, Gangyuan
Lu, Yulan
Dong, Xinran
Li, Dingpeng
Ge, Junshuang
Zhang, Zhiyan
Huang, Xuanzhao
Nong, Wenyan
Zhou, Yao
Tang, Hui
Yang, Hongxi
Zhang, Shijie
Li, Juan
Cao, Xiaojun
Yang, Lin
Gao, Xia
Xu, Kaishou
Gu, Xiaoqiong
Zhang, Wen
Xia, Huimin
Liu, Li
Zhou, Wenhao
Li, Mulin Jun
Computation and Language
Rare diseases affect hundreds of millions worldwide, yet diagnosis often spans years. Convectional pipelines decouple noisy evidence extraction from downstream inferential diagnosis, and general/medical large language models (LLMs) face scarce real world electronic health records (EHRs), stale domain knowledge, and hallucinations. We assemble a large, domain specialized clinical corpus and a clinician validated reasoning set, and develop RareSeek R1 via staged instruction tuning, chain of thought learning, and graph grounded retrieval. Across multicenter EHR narratives and public benchmarks, RareSeek R1 attains state of the art accuracy, robust generalization, and stability under noisy or overlapping phenotypes. Augmented retrieval yields the largest gains when narratives pair with prioritized variants by resolving ambiguity and aligning candidates to mechanisms. Human studies show performance on par with experienced physicians and consistent gains in assistive use. Notably, transparent reasoning highlights decisive non phenotypic evidence (median 23.1%, such as imaging, interventions, functional tests) underpinning many correct diagnoses. This work advances a narrative first, knowledge integrated reasoning paradigm that shortens the diagnostic odyssey and enables auditable, clinically translatable decision support.
title A Specialized Large Language Model for Clinical Reasoning and Diagnosis in Rare Diseases
topic Computation and Language
url https://arxiv.org/abs/2511.14638