Skip to main content

Table 3 Test data and training data for each fivefold cross-validation, and training data after data expansion

From: Creation of an artificial intelligence model for intubation difficulty classification by deep learning (convolutional neural network) using face images: an observational study

  1. The number of facial images of patients classified into the easy and difficult groups by fivefold cross-validation is shown. The number of facial images of patients in the easy group and the difficult group in the training dataset increased by 3 and 9 times, respectively
Back to article page

Journal of Intensive Care

ISSN: 2052-0492