Then the PCLR model containing s PCs (PCLR(s)) is obtained by getting rid of the r last PCs in the last equation, so the dependent variables can be obtained as follows:
In the new model, the parameters of the PCLR model just contain the first s PCs as covariates.
In other words, PCLR employs the first s PCs except for the original predictor variables to explain the binary dependent variable.
The ANN and PCLR models were performed with the probability of MetS.
Model (28) is considered as the desired PCLR model.
The ROC and discrimination result of the PCLR model are shown in Figure 2.
The ROC of the two methods is shown in the Figure 2; from the figure, the AUROC of the BPANN is larger than PCLR. Thus, the BPANN has abetter predictive ability than PCLR.
From Table 5, BPANN has a higher predictive accuracy than PCLR, with a larger sensitivity value (0.884297521) for BPANN than for PCLR (0.52892562).
In the current study, the results of the predictive performance showed that the ANN model had a higher predictive rate for identifying true positive or negative patients from undiagnosed MetS patients because it had sufficient sensitivity (88.42%) and specificity (83.66%) compared to the PCLR model (52.89% and 92.2%).
AUC values (AUC = 0.9043) obtained by the ANN model for identifying MetS were superior to values obtained by the PCLR model (AUC = 0.8873), which means that the ANN model had a higher predictive accuracy compared to the PCLR model.