Table 3 Cross-validated evaluation results of prediction with 13 variables.
From: FASDetect as a machine learning-based screening app for FASD in youth with ADHD
Model (13 variables) | AUC | Accuracy | Precision | Recall | Brier |
|---|---|---|---|---|---|
Logistic Regression | 0.91 [0.83, 0.99] | 0.84 | 0.89 | 0.84 | 0.12 |
Support Vector Machine | 0.90 [0.80 0.99] | 0.85 | 0.85 | 0.92 | 0.12 |
Random Forest | 0.92 [0.84, 0.99] | 0.85 | 0.86 | 0.91 | 0.11 |
Gradient Boosting Decision Tree | 0.91 [0.82, 0.99] | 0.85 | 0.86 | 0.91 | 0.12 |
kNN Classifier | 0.90 [0.81, 0.99] | 0.84 | 0.87 | 0.88 | 0.12 |
Gaussian Process Classifier | 0.90 [0.81, 0.99] | 0.84 | 0.86 | 0.89 | 0.12 |
