Enhancing brain metastasis prediction in non-small cell lung cancer: a deep learning-based segmentation and CT radiomics-based ensemble learning model

Table 2 Comparisons of the performance of different classifiers by using radiomics features

Classifier	Dataset	ACC (%)	SEN (%)	SPE (%)	PPV (%)	NPV (%)	OR	F1 Score	F1_Weighted Score	MCC
XGBoost	TC	80.59	81.73	79.17	82.93	77.78	17	0.82	0.81	0.61
	VC1	79.5	76.83	82.28	81.82	77.38	15.39	0.79	0.79	0.59
	VC2	76.92	84.21	73.91	57.14	91.89	15.11	0.68	0.78	0.53
SVM	TC	76.60	74.52	79.17	81.58	71.51	11.11	0.78	0.77	0.53
	VC1	77.02	76.83	77.22	77.78	76.25	11.24	0.77	0.77	0.54
	VC2	70.77	68.42	71.74	50.00	84.62	5.50	0.58	0.72	0.37
MLP	TC	74.20	73.08	75.60	78.76	69.40	8.41	0.76	0.74	0.48
	VC1	75.78	76.83	74.68	75.90	75.64	9.78	0.76	0.76	0.52
	VC2	67.69	68.42	67.39	46.43	83.78	4.48	0.55	0.69	0.33
Decision Tree	TC	69.95	73.56	65.48	72.51	66.67	5.28	0.73	0.70	0.39
	VC1	72.05	75.61	68.35	71.26	72.97	6.70	0.73	0.72	0.44
	VC2	64.62	42.11	73.91	40.00	75.56	2.06	0.41	0.65	0.16

ISSN: 1470-7330