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

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.