From: Machine learning determination of applied behavioral analysis treatment plan type
Performance metrics | ML prediction model | Random forest model | Standard of care comparator |
---|---|---|---|
AUROC (95% CI) | 0.895 (0.808–0.959) | 0.826 (0.678–0.951) | 0.767 (0.629–0.891) |
Sensitivity (95% CI) | 0.789 (0.673–0.906) | 0.750 (0.615–0.885) | 0.789 (0.700–0.878) |
Specificity (95% CI) | 0.808 (0.740–0.876) | 0.824 (0.753–0.894) | 0.635 (0.571–0.698) |
PPV (95% CI) | 0.600 (0.478–0.722) | 0.600 (0.464–0.736) | 0.441 (0.360–0.522) |
NPV (95% CI) | 0.913 (0.861–0.965) | 0.903 (0.846–0.960) | 0.892 (0.843–0.940) |