ClinLens: Towards Long-Horizon Coding Agents for Longitudinal Multimodal Clinical Data Science

AI 中文解读

核心亮点：这项研究首次给AI医生配备了从心电图、X光片到病历文本的"全套体检工具"，结果发现现有AI系统虽然能写出代码，却多半分析得不对。通俗解读：以前测试AI看病，只考单一科目，比如只看化验单或只读病历。这次研究人员设计了200道综合考题，让AI像真正的医生一样，同时翻阅五年内的住院记录、心电图、胸片和心脏超声，最后交出完整分析。结果令人意外：几乎所有AI都能"写完作业"，但只有少数能真正答对——好比学生交卷很积极，可多数答案逻辑错误或漏掉了关键时间信息。最强的AI组合也只拿到56.3%的正确率，而普通临床系统正确率还不到3%。实际影响：这项技术距离改变日常生活还有距离，但它给医疗AI圈划了条"及格线"。未来如果AI能真正理解连续多年的健康数据，医生就能把整理病历、追踪病情变化的繁琐工作交给它，自己专心做治疗决策。对普通人来说，这意味着更快的辅助诊断和更少的漏诊风险，但前提是AI得先跨过这道"会写不等于会想"的门槛。目前这项研究更像一面镜子，照出了AI在真实医疗场景中的短板，也指明了下一步攻关方向。

arXiv:2607.26155v1 Announce Type: new Abstract: Clinical data-science agents must transform heterogeneous longitudinal records into auditable analyses, yet existing benchmarks largely isolate medical question answering, structured-table reasoning, or generic scientific repositories. We introduce CLINLENS, a benchmark of 200 executable tasks over five linked MIMIC resources spanning structured electronic health records, notes, electrocardiograms, chest radiographs, and echocardiograms. A 4 x 5 taxonomy crosses four patient-time scopes with five analysis capabilities. Program-first reverse synthesis pairs each bounded semi-raw package with an evaluator-private reference workflow and checks required artifacts, cohort and temporal semantics, and the final answer. On a fixed 126-task suite, the strongest of 24 standardized model-scaffold configurations achieves 56.3% scope-macro STRICTPASS despite 100% EXECSUCCESS. For reference, a separately configured coding agent solves 83 of 126 tasks, while five biomedical systems adapted to GPT-4o-mini reach at most 2.9% scope-macro STRICTPASS. These results expose a substantial gap between runnable submissions and correct clinical analyses.