医学人工智能产品测试数据集通用化描述方法研究  

Generalized method for describing test datasets of medical artificial intelligence products

作　　者：车贺宾 薛万国[1] 徐洪丽 董敬 汪安安 刘广东[2] CHE He-bin;XUE Wan-guo;XU Hong-li;DONG Jing;WANG An-an;LIU Guang-dong(Medical Big Data Research Center,Chinese PLA General Hospital,Beijing 100853,China;Health Service Department,the Sixth Medical Center of Chinese PLA General Hospital,Beijing 100037,China)

机构地区：[1]解放军总医院医学大数据研究中心,北京100853 [2]解放军总医院第六医学中心卫勤部,北京100037

出　　处：《医疗卫生装备》2023年第7期74-78,共5页Chinese Medical Equipment Journal

基　　金：国家重点研发计划项目(2019Y FB1404801);中国人民解放军总医院医学工程实验室自主科研课题(2022SYSZZK Y28)。

摘　　要：介绍了目前医学人工智能产品测试数据集的构建情况及存在的问题,提出了设计底层通用医学数据模块并通过模块灵活组配所需测试数据集的构建模式,制订了具有一定灵活性的测试数据集通用化描述方法,为有效检测医学人工智能产品的准确性、实用性等性能提供了数据支撑。The construction and problems of the medical artificial intelligence product test datasets were introduced.A new mode for establishing medical artificial intelligence product test datasets was put forward involving in development of a general medical data modules and requirement-based arrangement of test datasets.A generalized test dataset description method with a certain degree of flexibility was formulated to provide data support for measuring the accuracy and practicality of medical artificial intelligence products.

关 键 词：医学人工智能产品 测试数据集 医学数据模块 通用化描述 

分 类 号：R318[医药卫生—生物医学工程] R197.39[医药卫生—基础医学]