Skip to main content

Table 3 Comparison of performance indices of the artificial neural network (ANN), MLR, and Cox regression models for predicting 5-year postoperative mortality of breast cancer patients

From: Predictive model for 5-year mortality after breast cancer surgery in Taiwan residents

Dataset Sensitivity (%) Specificity (%) PPV (%) NPV (%) Accuracy (%) AUC (%)
Training dataset (n = 2543)
 ANN model 86.88 89.09 65.24 87.91 87.43 72.86
 MLR model 83.72 87.73 64.80 83.57 86.55 52.42
 Cox model 86.37 88.06 60.24 85.48 84.53 65.13
Testing dataset (n = 726)
 ANN model 88.00 89.04 77.52 87.64 88.50 71.67
 MLR model 83.00 84.36 73.35 87.02 86.09 51.93
 Cox model 86.43 87.57 74.99 87.10 86.45 65.87
Validation dataset (n = 363)
 ANN model 85.66 88.71 53.42 86.89 88.82 70.76
 MLR model 83.77 87.35 50.96 86.01 85.40 52.44
 Cox model 84.61 85.43 52.02 86.60 86.91 64.79
  1. PPV positive predictive value, NPV negative predictive value, AUC area under receiver operating characteristic curve