Table 1 Performance of the top-performing ML models on held-out test data
From: Quantifying device type and handedness biases in a remote Parkinson’s disease AI-powered assessment
Accuracy | F1-score | AUROC | Sensitivity | Specificity | |
|---|---|---|---|---|---|
Random forest | 92% | 84% | 94% | 86% | 92% |
LightGBM | 86% | 78% | 91% | 78% | 90% |
XGBoost | 86% | 77% | 93% | 81% | 88% |
