,使

Hyun-Lim Yang1, Leo Anthony Celi2, Hyeonhoon Lee3

  • 1Office of Hospital Information, Seoul National University Hospital, Seoul, Republic of Korea; Innovative Medical Technology Research Institute, Seoul National University Hospital, Seoul, Republic of Korea; Department of Medicine, Seoul National University College of Medicine, Seoul, Republic of Korea.

概括

数据集中的选择偏差显著影响低血压预测模型的性能. 深度学习模型在不偏见的数据上显示出更差的结果,突出了需要仔细验证的需要.