Table 5.
The table shows the prediction of Parkinson’s by using AI.
| SN | Citations | IC | DS | GT | FE | TOC | ML vs. DL | ACC % | AUC |
|---|---|---|---|---|---|---|---|---|---|
| 1 | Bikias et al. [199] (2021) | LBBM (FoG) | 18 | PD vs. Non PD | SVM | CNN | DL | 90.00 | NR |
| 2 | Pramanik et al. [200] (2021) | LBBM (Voice) | 252 | PD vs. Non PD | NB | RF | ML | 95.00 | NR |
| 3 | Borzì et al. [201] (2021) | OBBM, LBBM (FoG) | 11 | PD vs. Non PD | RF | NB | ML | 84.10 | NR |
| 4 | Aich et al. [202] (2020) |
OBBM, LBBM (FoG) |
20 | PD vs. Non PD | RF | SVM, RF, KNN | ML | 97.35 | 0.74 |
| 5 | Pramanik et al. [203] (2021) | LBBM (Voice) | 169 | PD vs. Non PD | NB | SVM, RF | ML | 78.97 | 0.78 |
| 6 | Zahid et al. [204] (2020) |
LBBM (Voice) | 50 | PD vs. Non PD | SVM | RF | HDL | 99.1 | NR |
| 7 | Nissar et al. [205] (2019) |
LBBM (Voice) | 188 | PD vs. Non PD | NB | XGBoost | ML | 92.76 | NR |
SN: serial number, IC: input covariates, DS: data size, GT: ground truth, OBBM: office-based biomarker, LBBM: laboratory based biomarkers, FE: feature extraction, TOC: type of classifier, ACC: percentage accuracy, AUC: Area Under Curve, FoG: freezing of gait, NR: not reported.