Explanation and prediction of clinical data with imbalanced class distribution based on pattern discovery and disentanglement

Table 3 Comparison result from 20-time-10-fold cross-validation using different classification algorithm

Original Thoracic Data	LR	CART	NB	cPDD
F1-Score(T)	0.01 ± 0.00	0.19 ± 0.03	0.24 ± 0.01	0.33 ± 0.01
G-mean(T)	0.01 ± 0.01	0.20 ± 0.03	0.36 ± 0.01	0.38 ± 0.01
Avg. F1	0.01 ± 0.01	0.19 ± 0.03	0.24 ± 0.01	0.33 ± 0.01
Avg. Acc	0.84 ± 0.84	0.82 ± 0.01	0.15 ± 0.00	0.59 ± 0.01
Balanced Acc.	0.50 ± 0.00	0.54 ± 0.01	0.50 ± 0.00	0.62 ± 0.01
MCC	−0.01 ± 0.00	0.11 ± 0.03	0.01 ± 0.00	0.18 ± 0.01

F1-Score(T) Average F1-Score on Risk = T, G-means(T) Average G-mean on Risk = T, Avg. F1 Average F1-Score for both classes (Risk = T and Risk = F), Avg. Acc Average of prediction accuracy on the whole dataset

ISSN: 1472-6947