Skip to main content

Table 3 Sensitivity, specificity, positive predictive value, and negative predictive value of the training and validation group: comparing linear discriminant analysis and artificial neural network

From: Prediction of conversion of laparoscopic cholecystectomy to open surgery with artificial neural networks

Group Statistical accuracy Discriminant Analysis artificial neural network
Training Sensitivity 50.7 61.6
  specificity 84.3 99.4
  positive predictive value 24.7 91.8
  negative predictive value 94.4 96.2
validation Sensitivity 55.5 66.7
  specificity 82.2 98.9
  positive predictive value 23.8 85.7
  negative predictive value 94.2 96.8
  1. The prediction models were created based on the data of training group.