TABLE 2.

Comparison metrics for the final model in TMJOAI and TMJPI. Multi-class precision and recall for the TMJOAI models are shown as Precision1 and Recall1 for OA and Precision0 and Recall0 for control groups, respectively, and the final F1-score was calculated by taking the macro average of the two classes’ F-1 scores (38, 39).

TMJOAI Models	AUC	Accuracy	Precision1	Precision0	Recall1	Recall0	F1 Score
XGBoost	0.829	0.772	0.778	0.766	0.761	0.783	0.772
LightGBM	0.842	0.804	0.804	0.804	0.804	0.804	0.804
XGBoost + LightGBM	0.837	0.783	0.783	0.783	0.783	0.783	0.783
TMJPI Model	AUC	Accuracy	Precision	Sensitivity	Specificity	F1 score
KRVFL+	0.809	0.709	0.774	0.627	0.791	0.661