cs.AI提交于 2026-10-31已译

以技能为中心的智能体推进临床基因组分析

Advancing Clinical Genomic Analysis with a Skill-Centred Agent

Qiaoyu Zheng · Weike Zhao · Yanjie Fan · Ye Cao · Mengqi Jiang · Xiao Zhou · et al.

中文摘要

临床基因组分析需要专家整合不断演变的指南、数据库和计算证据。随着测序日益普及，这一复杂且劳动密集的过程已成为基因组信息及时用于临床决策的主要瓶颈。为填补这一空白，开发了 ClinGeX，一个大型语言模型智能体，通过任务特定检索和依赖感知编排组合 105 个精选的可执行技能。在 223 个时间上留出的基准案例上，ClinGeX 与专家参考分类达到 71.7% 的宏平均任务级一致性，而最强对比方法为 45.7%。在一项三条件、平衡设计的人机协作研究中，45 名临床基因组专业人员评估了 135 个临床来源案例，条件为常规（无 AI 辅助）、DeepSeek 辅助和 ClinGeX 辅助。ClinGeX 辅助提高了标准级变异分析、罕见病基因组解读和分子肿瘤决策的原始案例级一致性（分别为 51.1%、57.8%、64.4%，对比条件为 15.6%、31.1%、20.0%），并在所有场景中减少了报告的解读时间。在一项探索性一个月真实世界非干预评估中，11 名经验丰富的专业人员对 96 个自选分析片段提交反馈，报告了频繁采纳结论和节省时间。这些发现支持可执行领域技能作为增强专家基因组解读的有前景方法。

关键要点

01临床基因组分析因指南、数据库和计算证据整合复杂而成为瓶颈
02ClinGeX 通过检索和依赖感知编排组合 105 个可执行技能
03在 223 个基准案例上任务级一致性达 71.7%，对比方法为 45.7%
04人机协作研究中 ClinGeX 辅助将案例级一致性提升至 51.1%-64.4% 并减少解读时间
05真实世界探索性评估中 11 名专业人员报告频繁采纳结论和节省时间

解读

尚无解读。

原始英文摘要

arXiv:2610.40556v1 Announce Type: new Abstract: Clinical genomic analysis requires experts to integrate evolving guidelines, databases, and computational evidence. As sequencing has become increasingly accessible, this complex and labor-intensive process has become a major bottleneck to the timely use of genomic information in clinical decision-making. To fill this gap, we developed ClinGeX, a large-language-model agent that composes 105 curated executable skills through task-specific retrieval and dependency-aware orchestration. On 223 temporally held-out benchmark cases, ClinGeX achieved 71.7\% macro-averaged task-level concordance with expert reference classifications, compared with 45.7\% for the strongest comparator. In a three-condition, counterbalanced human-AI collaboration study, 45 clinical genomic professionals assessed 135 clinically derived cases under routine (no AI assistance), DeepSeek-assisted and ClinGeX-assisted conditions. ClinGeX assistance increased raw case-level concordance across criterion-level variant analysis, genomic interpretation in rare disease and molecular oncology decision-making (51.1\%, 57.8\%, 64.4\% versus 15.6\%, 31.1\%, 20.0\% in comparator conditions) and reduced reported interpretation time in all scenarios. During an exploratory one-month real-world non-interventional assessment, 11 experienced professionals submitted feedback on 96 self-selected analysis episodes and reported frequent conclusion adoption and time savings. These findings support executable domain skills as a promising approach to augment specialist genomic interpretation.