临床 AI 部署前必须回答的两个问题：当临床判断成为预测捷径时
When Clinical Judgment Becomes a Predictive Shortcut: Two Questions Clinical AI Must Answer Before Deployment
AI 导读
一篇 arXiv 论文提出，临床 AI 可利用已有临床判断产生的信息预测结局，但仅凭预测性能不足以证明其实用性。作者提出与预期用途和信息条件相匹配的证据要求，并加入状态参照与代理相对时机检验。现有评估实践中的泄漏检查、整体预测性能和外部验证均无法回答这些问题，该框架可帮助医院评估关键条件是否在最需要时仍然成立。
正文 · 原文
Abstract:Clinical AI can predict outcomes using information generated by existing clinical judgment. Such performance alone cannot establish usefulness before recognition or across care processes. We propose evidence requirements matched to intended use and information conditions, with additional state-reference and proxy-relative timing tests for stronger recognition claims. This framework helps hospitals assess whether the conditions supporting performance hold when assistance is most needed. These questions remain outside current evaluation practice leakage checks, overall predictive performance, and external validation do not address them; the framework makes them explicit and specifies the direct evidence required to answer them.
| Comments: | 27 pages, 1 figure, 3 tables, 1 box; includes Multimedia Appendix 1 |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2609.25852 [cs.AI] |
| (or arXiv:2609.25852v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2609.25852 arXiv-issued DOI via DataCite |
Submission history
From: Jing Yang [view email]
[v1]
Tue, 22 Sep 2026 08:16:44 UTC (1,636 KB)
[v2]
Fri, 23 Oct 2026 17:33:10 UTC (1,522 KB)
来源：arXiv cs.AI · arxiv.org