Table 2 Performance of the three ML algorithms using the 16-variable dataset against the predicted 10-year CVD risk through the HellenicSCORE
From: Machine learning methodologies versus cardiovascular risk scores, in predicting disease risk
Algorithm | Accuracy | Specificity | Sensitivity | PPV | NPV |
|---|---|---|---|---|---|
k-NN | 0.96 | 0.37 | 0.98 | 0.97 | 0.50 |
RF | 0.99 | 0.79 | 1.00 | 0.99 | 0.98 |
DT | 0.99 | 0.87 | 0.99 | 0.99 | 0.89 |