Skip to main content

Table 4 AI model accuracy of fivefold cross-validation in supine-side-closed mouth-base position

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

  1. Datasets 1–5 in the supine-side-closed mouth-base position were used and divided into training data and test data
  2. The AUC was calculated for each dataset, and the 95% confidence interval, sensitivity, specificity, and precision were shown
Back to article page

Journal of Intensive Care

ISSN: 2052-0492