Table 2.

Key performance metrics of the best three models based on J-statistic, all outcomes

	Hip replacement surgery						Knee replacement surgery
	VAS			Q score			VAS			Q score
Model	xgbTree	msaenet	neural net	xgbTree	msaenet	glm	xgbTree	msaenet	glm	xgbTree	msaenet	glm
Training
AUC	0.87	0.87	0.86	0.78	0.78	0.78	0.87	0.86	0.86	0.71	0.71	0.71
Best threshold	0.5	0.45	0.55	0.5	0.5	0.5	0.5	0.45	0.45	0.5	0.5	0.5
Sensitivity	0.81	0.79	0.81	0.78	0.76	0.76	0.82	0.79	0.79	0.70	0.69	0.69
Specificity	0.76	0.77	0.76	0.64	0.67	0.67	0.73	0.76	0.76	0.59	0.61	0.61
J-statistic	0.57	0.57	0.57	0.42	0.43	0.43	0.56	0.56	0.56	0.29	0.30	0.30
Testing
Sensitivity	0.82	0.72	0.84	0.79	0.78	0.77	0.83	0.70	0.71	0.70	0.70	0.70
Specificity	0.77	0.85	0.73	0.63	0.64	0.65	0.73	0.83	0.83	0.61	0.61	0.62
Pos Pred Value	0.75	0.79	0.72	0.96	0.96	0.96	0.62	0.69	0.68	0.91	0.91	0.91
Neg Pred Value	0.84	0.78	0.85	0.23	0.22	0.22	0.89	0.85	0.85	0.27	0.27	0.27
F1	0.78	0.75	0.78	0.86	0.86	0.85	0.71	0.69	0.69	0.79	0.79	0.79
Balanced Accuracy	0.79	0.78	0.79	0.71	0.71	0.71	0.78	0.77	0.77	0.66	0.66	0.66
J-statistic	0.59	0.56	0.58	0.42	0.42	0.42	0.57	0.54	0.54	0.31	0.31	0.31