Selected article for: "external test cohort and internal validation"

Author: Cheng Jin; Weixiang Chen; Yukun Cao; Zhanwei Xu; Xin Zhang; Lei Deng; Chuansheng Zheng; Jie Zhou; Heshui Shi; Jianjiang Feng
Title: Development and Evaluation of an AI System for COVID-19
  • Document date: 2020_3_23
  • ID: k1lg8c7q_62
    Snippet: To measure the performance of classification model, AUC and some other metrics are computed on both internal validation and external test cohort. The metrics of internal validation cohort is computed on slice-level because the training is on slice-level and turning of super-parameters will be easier if validation is also done on slice-level. While metrics for external test cohort and reader study cohort are on case level, consistent with clinical.....
    Document: To measure the performance of classification model, AUC and some other metrics are computed on both internal validation and external test cohort. The metrics of internal validation cohort is computed on slice-level because the training is on slice-level and turning of super-parameters will be easier if validation is also done on slice-level. While metrics for external test cohort and reader study cohort are on case level, consistent with clinical application.

    Search related documents:
    Co phrase search for related documents