Table 2. Comparison of Model Results.

A comparison of all model performance statistics across the different models. Youden’s J-Index, Precision, Recall, and F1-Score were calculated only for the positive class, i.e. for rapid progressors only. Sensitivity, Specificity, and Youden’s were calculated at the optimal point for an equally weighted sensitivity and specificity using Youden’s J-Index. Precision and Recall were calculated for maximum F1-Score.

	Model V	Model VC	Model VO	Model VOC	Model V2	Model V2OC	Model V3	Model V3OC
AUC (95% CI)	0.74 (0.62, 0.86)	0.75 (0.63, 0.87)	0.76 (0.64, 0.88)	0.77 (0.65, 0.88)	0.81 (0.70, 0.92)	0.81 (0.70, 0.92)	0.84 (0.74, 0.95)	0.87 (0.77, 0.97)
Sensitivity (95% CI)	0.73 (0.68, 0.77)	0.82 (0.78, 0.85)	0.77 (0.73, 0.81)	0.68 (0.64, 0.72)	0.73 (0.68, 0.77)	0.73 (0.68, 0.77)	0.82 (0.78, 0.85)	0.95 (0.93, 0.97)
Specificity (95% CI)	0.73 (0.68, 0.77)	0.66 (0.61, 0.70)	0.67 (0.63, 0.72)	0.80 (0.76, 0.84)	0.78 (0.74, 0.82)	0.79 (0.75, 0.83)	0.82 (0.78, 0.85)	0.74 (0.70, 0.78)
Youden’s J-Index	0.45	0.47	0.44	0.49	0.51	0.52	0.64	0.69
Precision	0.20	0.21	0.18	0.16	0.33	0.26	0.32	0.39
Recall	0.41	0.45	0.45	0.55	0.45	0.45	0.41	0.41
F1-Score	0.27	0.29	0.25	0.25	0.38	0.33	0.36	0.40