布里斯托大学提出医疗AI可靠性测试框架，借鉴药物审批模式
原标题：Bristol researchers say medicine already knows how to handle black boxes and AI could learn from it
AI 摘要
布里斯托大学研究人员提出名为“Learning Ensemble”的框架，借鉴药物上市审批方式，系统评估医疗AI的可靠性。该框架要求开发者记录并检查三方面：系统运行限制与训练数据、跨患者群体的可靠性、以及系统是否真正适合预期临床用途。研究引用2021年案例说明，AI可能依赖无关图像特征或对弱势群体漏诊，导致部署后失效。作者认为该框架只是起点，旨在为开发者提供共同语言以更早发现问题。
正文节选
Bristol researchers say medicine already knows how to handle black boxes and AI could learn from it Key Points - Researchers at the University of Bristol propose testing medical AI systems for reliability systematically, modeled on how drugs get vetted. - Their approach, called "Learning Ensemble," checks three areas: the system's operating limits and training data, its reliability across all patient groups, and its actual fit for daily clinical use. - The process is meant to keep systems from f