Unverified50% confidenceFactExact time
Traditional triage AI evaluation usually focuses on acuity accuracy, that is, whether the urgency level output by the model matches the gold standard.
1
Sources
50%
Confidence
Long-term
Relevance
11/18/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedEvaluating automation bias requires specifically incorporating observation of the clinical decision-making process, for example recording the proportion of doctors who modify AI recommendations, the response time to AI prompts, and the frequency with which erroneous AI outputs are intercepted or let through, rather than focusing only on final outcome metrics.74% similarUnverifiedIn medical statistics, diagnostic accuracy usually refers to the proportion of samples in which the model correctly determines the disease category out of the total sample.73% similarVerifiedExpected Calibration Error (ECE) is the most commonly used metric for measuring calibration quality, computed by binning predictions by confidence and calculating the weighted average of the difference between mean confidence and actual accuracy per bin.72% similarUnverified医学AI临床验证的性能基准须针对目标人群建立,不能直接沿用公开数据集的评测结果,需通过多中心前瞻性研究证明安全性和有效性72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1182502API
curl https://kongchang.com/api/v1/knowledge/claims/1182502MCP
get_claim(id=1182502)