arXiv：cs.AI· Zhaoyu Fan, Bowen Han, Jincheng Ou, Yanwei Ren, Zehua He, Kaiyu Huang, Pengcheng He, Shanshan Ni, Chengchen Gong, Shuai Xue, Qingjiang Shi·· 5 小时前
ProCARE：以数据画像为基础的证据契约实现真实世界研究自动化
ProCARE: Real-World Study Automation via Profile-Grounded Evidence Contracts
AI 导读
ProCARE 是一个面向真实世界研究（RWS）自动化的框架，将异构数据画像转化为 Evidence Contracts，并把研究目标编译为强类型中间表示 RWS-IR，再通过确定性验证与局部修复检查生成的工作流。
正文
Authors:Zhaoyu Fan, Bowen Han, Jincheng Ou, Yanwei Ren, Zehua He, Kaiyu Huang, Pengcheng He, Shanshan Ni, Chengchen Gong, Shuai Xue, Qingjiang Shi
Abstract:Real-world studies (RWS) analyze routinely collected healthcare data, such as electronic health records and insurance claims, to estimate treatment effects, monitor safety, and identify risk factors outside randomized trials. Automating RWS with large language model agents is appealing but brittle: valid analyses depend on dataset-specific clinical semantics, including index dates, follow-up windows, patient/event-level units, and outcome boundaries that are often implicit in observational data. This leads to schema mismatches, temporal errors, inconsistent analytical granularity, and unsupported clinical claims. We present ProCARE, a profile-grounded framework that reformulates RWS automation as constrained compilation. ProCARE converts heterogeneous data profiles into Evidence Contracts specifying available variables, temporal attributes, distributions, and evidentiary limits, and compiles study objectives into RWS-IR, a strongly typed intermediate representation for variables, time relations, analysis units, and statistical tasks. Deterministic validation and localized repair then check and revise generated workflows across schema mapping, cohort construction, variable derivation, analysis, and interpretation. On 36 EHR-based benchmark tasks, ProCARE outperforms strong LLM-agent baselines in code executability, semantic consistency, and conclusion traceability, with automated violation diagnoses showing moderate-to-substantial agreement with blinded expert review.
| Comments: | 42 pages, 5 figures, including appendix. Accepted by NeurIPS'26. Code and benchmark: this https URL |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.16175 [cs.AI] |
| (or arXiv:2610.16175v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.16175 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zhaoyu Fan [view email]
[v1]
Mon, 12 Oct 2026 04:50:24 UTC (2,646 KB)
来源：arXiv：cs.AI · arxiv.org