arXiv cs.CY· Jiayu Feng·· 4 天前AI 评分39
多模态 AI 的临床价值主张超出证据支持
Clinical value claims in multimodal AI outpace supporting evidence
AI 导读
一项审计发现，多模态 AI 模型的临床价值主张普遍超出证据支持。研究审计了 177 项比较多模态与单模态模型的研究，当每个数据源单独建模时 AUROC 增益更小（调整后差异 -0.030）；完整基准测试比例从综述研究的 69.1% 降至近期研究的约 46.0%。仅约 22% 评估决策效用，无一开展前瞻性评估，但 84.0% 和约 87.7% 仍声称具有潜在临床价值或改善护理。
正文
Abstract:Multimodal prediction models add a data source, such as imaging or an assay, to clinical information, and health systems must decide whether that added test is worth acquiring. We audited 177 studies comparing multimodal with unimodal models: 81 from a systematic review and 96 from a probability sample of 2025-2026 PubMed records. Gains in the area under the receiver operating characteristic curve (AUROC) were smaller when a study fitted a separate model for every data source (adjusted difference, -0.030; 95% CI, -0.056 to -0.005). Within 78 such studies, leaving out the strongest source's model would have raised the average gain from 0.046 to 0.108. This complete benchmarking fell from 69.1% of review studies to an estimated 46.0% of recent ones. An estimated 22% assessed decision utility and none evaluated a model prospectively, yet most claimed potential clinical usefulness or improved care (84.0% and an estimated 87.7%).
| Subjects: | Machine Learning (cs.LG); Computers and Society (cs.CY) |
| Cite as: | arXiv:2610.14395 [cs.LG] |
| (or arXiv:2610.14395v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.14395 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jiayu Feng [view email]
[v1]
Fri, 9 Oct 2026 23:39:12 UTC (3,322 KB)
来源：arXiv cs.CY · arxiv.org