Table 6.
Benchmarking table for the multiclass, multi-label, and ensemble studies in CVD/non-CVD field.
| C1 | C2 | C3 | C4 | C5 | C6 | C7 | C8 | C9 | C10 | C11 | C12 | C13 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| SN | Author | Yr | JOU | DS | CVD | Domain | ML | CT | CVP | MC | MLB | Ensbl | Summary |
| R1 | Boernama et al. [211] | ’21 | IEEE | 30 | 🗶 | EEG | 🗸 | SVM, NN, LDA, OVO | 🗶 | 🗸 | 🗶 | 🗶 | EEG Classification |
| R2 | Collins et al. [212] | ’16 | BMJ | 122 | 🗸 | BP | 🗶 | 🗶 | 🗶 | 🗶 | 🗶 | 🗶 | CVD Meta-analysis |
| R3 | Dissanayake et al. [213] | ’21 | Hindawi | CHDD | 🗸 | 🗶 | 🗸 | RF, SVM, DT, KNN, LR, GNB | K5 | 🗸 | 🗶 | 🗶 | CVD risk |
| R4 | Galar et al. [214] | ’12 | IEEE Tran. | Imb D | 🗶 | 🗶 | 🗸 | SMOTE | K5 | 🗶 | 🗶 | 🗸 | Ensemble Classification |
| R5 | Stewart et al. [215] | ’17 | JRSMCD | 🗶 | 🗸 | 🗶 | 🗶 | 🗶 | 🗶 | 🗶 | 🗶 | 🗶 | CVD risk |
| R6 | Mathew et al. [216] | ’21 | IEEE | 6 | 🗶 | Edu | 🗸 | Adaboost, KNN, BPSO | K7 | 🗸 | 🗶 | 🗸 | Teaching Quality |
| R7 | Uike et al. [217] | ’21 | IEEE | 8 | 🗶 | SC | 🗸 | XG-Boost | Open | 🗸 | 🗶 | 🗶 | SC Classification |
| R8 | Wang et al. [218] | ’14 | Plos One | 736 | 🗶 | CF | 🗸 | RF, NBC, KNN | K10 | 🗶 | 🗸 | 🗶 | CF Classification |
| R9 | Wiharto et al. [219] | ’16 | HIR | 303 | 🗸 | 🗶 | 🗸 | K-Star | K* | 🗸 | 🗶 | 🗶 | CHD Classification |
| R10 | Boi et al. [220] | ’18 | CAR | 126 | 🗸 | 🗶 | 🗸 | SVM, RF, CNN | 🗶 | 🗶 | 🗶 | 🗸 | OCT-based risk stratification |
| R11 | Jamthikar et al. [35] | ’20 | CBM | 208 | 🗸 | 🗶 | 🗸 | KNN, RF, DT | K10 | 🗸 | 🗶 | 🗶 | CVD risk |
| R12 | Bianchini et al. [221] | ’08 | IEEE | 10 | 🗸 | 🗶 | 🗸 | 🗶 | 🗶 | 🗸 | 🗶 | 🗶 | Cardiovascular Risk Markers |
| R13 | Liu et al. [222] | ’12 | IEEE | 15 | 🗶 | Statistics | 🗸 | LDA | 🗶 | 🗶 | 🗸 | 🗶 | Statistical Classification |
| R14 | Charte et al. [223] | ’20 | IEEE | 🗶 | 🗶 | Software | 🗸 | MULAN | 🗶 | 🗶 | 🗸 | 🗶 | Comparison |
| R15 | Siblini et al. [224] | ’15 | IEEE | 156 | 🗶 | DM | 🗸 | LDA, MDDM | 🗶 | 🗶 | 🗸 | 🗶 | DM Reduction |
| R16 | Indhumathi et al. [225] | ’21 | IEEE | 30 | 🗸 | 🗶 | 🗸 | Probabilistic | 🗶 | 🗶 | 🗶 | 🗶 | CVD Management |
| R17 | Kolli et al. [226] | ’19 | IEEE | 86,155 | 🗸 | 🗶 | 🗸 | LogitBoost | K5 | 🗸 | 🗶 | 🗸 | Coronary Artery Calcification |
| R18 | Proposed Study | ’22 | 🗶 | 265 | 🗸 | 🗶 | 🗸 | 🗶 | 🗶 | 🗸 | 🗸 | 🗸 | CVD risk |
DS: Data size; ML: Machine learning; CVP: Cross-validation protocol; MC: Multiclass; MLB: Multi-label; GNB: Gaussian I Bayes; HD: Heart disease; CHDD: Cleveland heart disease datasets; Ensbl: Ensemble; IEEE Tran: IEEE Transaction; JRSMCD: Journal of the Royal Society of Medicine Cardiovascular disease; CT: Classifier type; ImbD: Imbalance data; JOU: Journal; SC: Sickle cells; CF: Chronic fatigue.