Table 11.
An overview of recent studies for CVD risk prediction.
| Reference | Dataset | Proposed Model | Performance |
|---|---|---|---|
| [40] | [81] | Logistic Regression |
AUC 78.4% Accuracy 72.1% |
| [73] | Long Beach VA heart disease database |
Logistic Regression |
Accuracy 86.5% |
| [74] | [81] | SVM | AUC 78.84% |
| [75] | [81] | Hybrid Random Forest with a linear model (HRFLM) |
Accuracy 88.7% |
| [76] | [81] | SVM (linear kernel) | Accuracy 86.8% |
| [77] | UK Biobank | AutoPrognosis model | AUC 77.4% |
| [78] | [81] | Gradient Boosting algorithm | AUC 84% Accuracy 89.7% |
| [79] | Not Publicy Available | Neuro-Fuzzy model | Accuracy 91% |