Skip to main content

Table 3 The performance of support vector machine models for the Classification I and Classification II

From: Application of support vector machine modeling for prediction of common diseases: the case of diabetes and pre-diabetes

Model Data set Sensitivity Specificity PPV NPV AUC
Classification Scheme I* Test 0.7715 0.7503 0.4926 0.9127 0.8347
  Training 0.7938 0.7169 0.4550 0.9211 0.8383
  10-fold cross- validation 0.7765 0.7027 0.4388 0.9130 0.8242
Classification Scheme II* Test 0.7359 0.6254 0.5061 0.8195 0.7318
  Training 0.7092 0.6590 0.6729 0.8087 0.7393
  10-fold cross- validation 0.7059 0.6589 0.5293 0.8054 0.7357
  1. PPV, positive predictive value; NPV, negative predictive value; AUC, area under the curve.
  2. *See Table 1 for the definitions of Classification Schemes I and II.