Table 3.

Predictive model results with hyperparameter calibration.

LR	MD	MF	A	E	S	F1-score	AUC
0.1	2	sqrt	0.94	0.94	0.94	0.94	0.94
0.1	2	log2	0.94	0.94	0.94	0.94	0.94
0.1	3	sqrt	0.94	0.92	0.96	0.94	0.94
0.1	3	log2	0.95	0.94	0.96	0.95	0.95
0.1	4	sqrt	0.96	0.96	0.96	0.96	0.96
0.1	4	log2	0.95	0.94	0.96	0.95	0.95
0.1	5	sqrt	0.96	0.96	0.96	0.96	0.96
0.1	5	log2	0.96	0.96	0.96	0.96	0.96
0.3	2	sqrt	0.95	0.94	0.96	0.95	0.95
0.3	2	log2	0.95	0.92	0.98	0.95	0.95
0.3	3	sqrt	0.98	0.98	0.98	0.98	0.98
0.3	3	log2	0.97	0.96	0.98	0.97	0.97
0.3	4	sqrt	0.96	0.94	0.98	0.96	0.96
0.3	4	log2	0.98	0.98	0.98	0.98	0.98
0.3	5	sqrt	0.97	0.98	0.96	0.97	0.97
0.3	5	log2	0.98	0.98	0.98	0.98	0.98
0.5	2	sqrt	0.95	0.96	0.94	0.95	0.95
0.5	2	log2	0.97	0.96	0.98	0.97	0.97
0.5	3	sqrt	0.96	0.96	0.96	0.96	0.96
0.5	3	log2	0.98	0.98	0.98	0.98	0.98
0.5	4	sqrt	0.97	0.98	0.96	0.97	0.97
0.5	4	log2	0.98	0.98	0.98	0.98	0.98
0.5	5	sqrt	0.98	0.98	0.98	0.98	0.98
0.5	5	log2	0.98	0.98	0.98	0.98	0.98
0.7	2	sqrt	0.96	0.96	0.96	0.96	0.96
0.7	2	log2	0.95	0.92	0.98	0.95	0.95
0.7	3	sqrt	0.98	0.98	0.98	0.98	0.98
0.7	3	log2	0.98	0.98	0.98	0.98	0.98
0.7	4	sqrt	0.97	0.96	0.98	0.97	0.97
0.7	4	log2	0.98	0.98	0.98	0.98	0.98
0.7	5	sqrt	0.96	0.96	0.96	0.96	0.96
0.7	5	log2	0.97	0.96	0.98	0.97	0.97

LR: learning rate, MD: maximum depth, MF: maximum number of regressors, A: accuracy, E: specificity, S: sensitivity, AUC: area under the curve.

Source: elaborated by the authors based on the data of the study