Table 6 Open in new tab The performance...

Techniques (Parameters)	Training dataset	Validation dataset
SVC (g = 0.001, c = 2)	90.36	87.53	88.95	0.78	0.96	90.72	87.11	88.92	0.78	0.95
RF (Ntree = 1000)	88.56	87.53	88.05	0.76	0.95	89.18	87.63	88.40	0.77	0.95
ETree (Ntree = 400)	90.75	88.82	89.78	0.80	0.96	90.72	90.21	90.46	0.81	0.96
MLP (activation = logistic)	87.79	85.22	86.50	0.73	0.93	86.08	88.66	87.37	0.75	0.94
KNN (neighbors = 9)	91.77	80.46	86.12	0.73	0.94	94.33	74.23	84.28	0.70	0.94
Ridge (alpha = 0)	84.19	84.96	84.58	0.69	0.90	85.05	83.51	84.28	0.69	0.91

Techniques (Parameters)	Training dataset	Validation dataset
SVC (g = 0.001, c = 2)	90.36	87.53	88.95	0.78	0.96	90.72	87.11	88.92	0.78	0.95
RF (Ntree = 1000)	88.56	87.53	88.05	0.76	0.95	89.18	87.63	88.40	0.77	0.95
ETree (Ntree = 400)	90.75	88.82	89.78	0.80	0.96	90.72	90.21	90.46	0.81	0.96
MLP (activation = logistic)	87.79	85.22	86.50	0.73	0.93	86.08	88.66	87.37	0.75	0.94
KNN (neighbors = 9)	91.77	80.46	86.12	0.73	0.94	94.33	74.23	84.28	0.70	0.94
Ridge (alpha = 0)	84.19	84.96	84.58	0.69	0.90	85.05	83.51	84.28	0.69	0.91

Table 6

The performance of DPC-based models developed using different machine learning techniques on alternate dataset

Techniques (Parameters)	Training dataset					Validation dataset
Techniques (Parameters)	Sen	Spc	Acc	MCC	AUROC	Sen	Spc	Acc	MCC	AUROC
SVC (g = 0.001, c = 2)	90.36	87.53	88.95	0.78	0.96	90.72	87.11	88.92	0.78	0.95
RF (Ntree = 1000)	88.56	87.53	88.05	0.76	0.95	89.18	87.63	88.40	0.77	0.95
ETree (Ntree = 400)	90.75	88.82	89.78	0.80	0.96	90.72	90.21	90.46	0.81	0.96
MLP (activation = logistic)	87.79	85.22	86.50	0.73	0.93	86.08	88.66	87.37	0.75	0.94
KNN (neighbors = 9)	91.77	80.46	86.12	0.73	0.94	94.33	74.23	84.28	0.70	0.94
Ridge (alpha = 0)	84.19	84.96	84.58	0.69	0.90	85.05	83.51	84.28	0.69	0.91

Techniques (Parameters)	Training dataset					Validation dataset
Techniques (Parameters)	Sen	Spc	Acc	MCC	AUROC	Sen	Spc	Acc	MCC	AUROC
SVC (g = 0.001, c = 2)	90.36	87.53	88.95	0.78	0.96	90.72	87.11	88.92	0.78	0.95
RF (Ntree = 1000)	88.56	87.53	88.05	0.76	0.95	89.18	87.63	88.40	0.77	0.95
ETree (Ntree = 400)	90.75	88.82	89.78	0.80	0.96	90.72	90.21	90.46	0.81	0.96
MLP (activation = logistic)	87.79	85.22	86.50	0.73	0.93	86.08	88.66	87.37	0.75	0.94
KNN (neighbors = 9)	91.77	80.46	86.12	0.73	0.94	94.33	74.23	84.28	0.70	0.94
Ridge (alpha = 0)	84.19	84.96	84.58	0.69	0.90	85.05	83.51	84.28	0.69	0.91

Sen: sensitivity, Spc: specificity, Acc: accuracy, MCC: Matthews correlation coefficient, AUROC: area under the receiver operating characteristic curve.

This Feature Is Available To Subscribers Only