Table 2 Literature using ensemble techniques in health risk prediction
From: Early prediction of chronic kidney disease based on ensemble of deep learning models and optimizers
Paper | Dataset | Algorithm | Highest accuracy |
|---|---|---|---|
Raza-2019 [23] | Heart disease dataset–statlog | MVE | 88.88% |
Atallah-2019 [24] | Heart disease dataset [25] | MVE | 90% |
Yadav-2019 [26] | Breast cancer Wisconsin (Original) | AE-MVE-WAE | (AE) 0.9998AUC |
Breast cancer Wisconsin (Diagnostic) | (AE) and (RAE) 100% AUC | ||
Haberman’s Survival Dataset | (AE) 0.636 | ||
Heart disease Dataset (Hungarian) | (AE) 0.8994 | ||
Indian liver Patient Database | (AE) 0.7892 | ||
Mammographic Mass Dataset | (AE) 0.8708 | ||
single-proton Emission Computed Tomography (SPECT) | (WAE) 0.8166 | ||
SPECTF heart-imaging Dataset | (RAE) 0.8166 | ||
Statlog (heart) Dataset | (RAE) 0.9272 | ||
Vertebral column Dataset | (AE) and (RAE) 0.9504 | ||
Tao Zhou-2021 [27] | The data are available from the author upon request | MVE | 99.05% |
Chandra-2021 [28] | COVID‐chest X-ray [29] | MVE | 98.062% Phase-I 91.329% Phase-II |
Brain tumor | MV | 100% training 93% testing | |
Hireš-2022 [32] | Parkinson’s disease | MV | 99% |