ScholarPulse 日报 2026-10-31

2026-10-31 学术简报：2 篇。基于105个可执行技能构建的LLM智能体ClinGeX，能显著提升临床基因组分析的一致性并缩短专家解读耗时。

今日速览

序号	标题	来源	日期	主题	推荐等级
1	Advancing Clinical Genomic Analysis with a Skill-Centred Agent	arXiv	2026-10-29	RAG	高
2	Agentic LLM reasoning in pediatric diabetes outcome prediction from multimodal medical records	arXiv	2026-10-29	AI-Agent	高

重点论文与技术动态

1. Advancing Clinical Genomic Analysis with a Skill-Centred Agent

来源：arXiv
日期：2026-10-29
作者/机构：Qiaoyu Zheng, Weike Zhao, Yanjie Fan, Ye Cao, Mengqi Jiang, Xiao Zhou
主题标签：RAG, arXiv
推荐等级：高
分类：cs.AI, q-bio.GN

一句话结论

基于105个可执行技能构建的LLM智能体ClinGeX，能显著提升临床基因组分析的一致性并缩短专家解读耗时。

核心内容

基准表现优异：在223例时间留出病例评测中，ClinGeX任务级一致性达71.7%，显著优于最强对照的45.7%。
人机协同提效：45位专业人员测试表明，其在变异分析、罕见病及肿瘤决策中的一致性（51.1%、57.8%、64.4%）远超无AI与DeepSeek辅助对照（15.6%、31.1%、20.0%），且耗时均减少。
真实场景认可：在为期1个月的真实世界评估中，11名专家在96个分析事件中频繁采纳其结论并显著节省时间。

方法与数据

采用任务检索与依赖感知编排调度105个精选可执行技能；测试数据涵盖223例基准用例、135例临床衍生用例及96个真实分析事件（底层模型等细节摘要未明确）。

价值判断

值得关注：在罕见病和肿瘤精准治疗等复杂临床决策中，有效突破基因组分析的人力瓶颈。
可复用点：结合依赖感知编排的可执行领域技能Agent框架。
局限/待核查：真实世界评估规模较小（11人、96例）；技能的具体实现细节摘要未明确。

摘要

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.

2. Agentic LLM reasoning in pediatric diabetes outcome prediction from multimodal medical records

来源：arXiv
日期：2026-10-29
作者/机构：Daniel Palacios, Guantong Qi, Anna Kadi, Natali Borrego, Sukru Aras, Michael L. Ferm
主题标签：AI-Agent, arXiv
推荐等级：高
分类：q-bio.QM, cs.CL

一句话结论

LLM智能体CEDAR通过融合多模态病历预测儿科糖尿病结局，性能显著超越传统机器学习，且具备极高事实准确性与临床可信度。

核心内容

预测性能更优：在T2D与T1D队列中合并AUROC分别达0.815和0.756（传统机器学习仅0.603~0.700），稀疏筛查结局提升尤为显著。
证据极度精准：模型引用的70,246个临床数值中仅4个与病历不符，展现了可靠的防幻觉能力。
契合专家逻辑：两位专科医生仅依据CEDAR引用的证据与推理，约90%的病例与模型判断一致，专家间一致性达90.5%。

方法与数据

纳入2,489例T2D与4,018例T1D青少年的18个月多模态记录（含结构化数据、社会决定因素及CGM数据），构建具备证据引用和自我审计的CEDAR流水线，预测24个月时的结局。

价值判断

值得关注：在样本小、结局罕见的儿科复杂场景中，成功验证了LLM智能体优于传统机器学习的预测潜力。
可复用点：证据引用与自我审计（self-auditing）相结合的Agent推理工作流。
局限/待核查：所采用的具体LLM底座模型及外部泛化表现摘要未明确。

摘要

Large language model (LLM) agents are proposed for clinical prediction but are untested in pediatrics, where cohorts are small and outcomes are uncommon. Using records from 2,489 youth with type 2 diabetes (T2D) and 4,018 with type 1 diabetes (T1D), spanning structured data, note-derived social determinants and, in T1D, continuous glucose monitoring data, we predicted seven T2D outcomes, four also in T1D, at 24 months from 18 months of follow-up. CEDAR (Clinical Evidence-Driven Agent for Risk-prediction), an evidence-citing, self-auditing LLM pipeline, outperformed trained machine learning in both cohorts (pooled area under the receiver operating characteristic curve 0.815 versus 0.656 to 0.700 in T2D and 0.756 versus 0.603 to 0.631 in T1D), most on the sparsely screened outcomes. Only 4 of 70,246 values it cited did not match the chart. Reading only the evidence and reasoning cited by CEDAR, two pediatric endocrinologists reached the same prediction as CEDAR in about nine of ten cases, agreeing with each other on 90.5%.