TABLE 3.

Four-class classification on test set.

Performance	1CTR (RF)	2PETR (RF)	3CPR (SMO)
Accuracy (%)	62.9	79.1	91.2
True rate for:
Adc	0.73	0.89	0.89
Sqc	0.46	0.62	0.85
Mts	0.75	0.81	1.00
4Oth	0.57	0.71	0.93
Precision for:
Adc	0.57	0.79	0.90
Sqc	0.50	0.67	0.94
Mts	0.73	0.79	1.00
Oth	0.76	0.91	0.94
Kappa	0.50	0.71	0.89

¹CT-based radiomics (with Random Forest classification). ²PET-based radiomics (with Random Forest classification). ³The combination of CT- and PET-based radiomics (with Sequential minimal optimization classification). ⁴Other primary lung cancer types. The best performance metrics for each classification are highlighted in bold.