Research Article
Human Tongue Thermography Could Be a Prognostic Tool for Prescreening the Type II Diabetes Mellitus
Table 5
Confusion matrices of all the classifiers.
| (a) Support vector machine (SVM) | Normal (predicted) | Diabetes mellitus (predicted) | Normal (actual) | 67 (TN) | 3 (FP) | Diabetes mellitus (actual) | 7 (FN) | 63 (TP) |
| (b) Naïve Bayes (NB) | Normal (predicted) | Diabetes mellitus (predicted) | Normal (actual) | 58 (TN) | 12 (FP) | Diabetes mellitus (actual) | 3 (FN) | 67 (TP) |
| (c) Convolutional Neural Network (CNN) | Normal (predicted) | Diabetes mellitus (predicted) | Normal (actual) | 67 (TN) | 3 (FP) | Diabetes mellitus (actual) | 5 (FN) | 65 (TP) |
|
|
TP: true positive, FP: false positive, TN: true negative, FN: false negative, PPV: positive predictive value, NPV: negative predictive value.
|