Table 4.

Table of performance metrics of different ML algorithms for NSCLC.

ML model	Class	NSCLC
		Accuracy	Precision	Recall	F1 score
Logistic regression	0	0.68	0.68	0.68	0.71
	1	0.68	0.68	0.68	0.81
	W. Avg	0.68	0.68	0.68	0.77
k-Nearest neighbours	0	0.7	0.84	0.76	0.76
	1	0.76	0.79	0.77	0.76
	W. Avg	0.73	0.82	0.77	0.76
Support vector machine	0	0.74	0.88	0.8	0.84
	1	0.87	0.71	0.78	0.86
	W. Avg	0.8	0.79	0.79	0.85
Random forest classifier	0	0.79	0.87	0.86	0.84
	1	0.88	0.79	0.82	0.89
	W. Avg	0.85	0.84	0.84	0.86
XgBoost algorithm	0	0.86	0.80	0.83	0.82
	1	0.79	0.85	0.82	0.79
	W. Avg	0.83	0.82	0.82	0.81
AdaBoost algorithm	0	0.80	0.84	0.83	0.80
	1	0.83	0.79	0.81	0.85
	W. Avg	0.81	0.81	0.81	0.83