AUD-DSS: a decision support system for early detection of patients with alcohol use disorder

BMC Bioinformatics

Table 6 Average performance of the developed models based on test set

Model	Precision (positive predictive value)	Recall (sensitivity)	F1-score	Accuracy	AUROC	AUPRC
Baseline
Stacking ensemble (AUDPM)	0.91	0.78	0.83	0.92	0.95	0.70
Random forest	0.94	0.70	0.75	0.90	0.95	0.56
Decision tree	0.74	0.72	0.73	0.85	0.76	0.54
K-nearest neighbour	0.78	0.76	0.77	0.88	0.84	0.61
Support vector machine	0.90	0.62	0.66	0.87	0.86	0.38
XGBoost	0.87	0.73	0.77	0.90	0.73	0.56
Proposed pipeline
Stacking ensemble (AUDPM)	0.97	0.96	0.97	0.98	0.99	0.90
Random forest	0.97	0.89	0.93	0.96	0.99	0.87
Decision tree	0.87	0.80	0.83	0.91	0.91	0.70
K-nearest neighbour	0.79	0.74	0.76	0.88	0.86	0.59
Support vector Machine	0.96	0.81	0.86	0.93	0.95	0.75
XGBoost	0.90	0.73	0.78	0.90	0.73	0.62

ISSN: 1471-2105