Table 1. Performance metrics of the combined prediction model for a timeframe of 26 and 104 weeks.

Results using a threshold selected for high sensitivity (>80%), a threshold for high specificity (>90%), and one for a balanced case are presented.

Metric	26 weeks			104 weeks
Threshold	Balanced	High sensitivity	High specificity	Balanced	High sensitivity	High specificity
False Negative Rate	0.26 (0.17, 0.35)	0.14 (0.07, 0.24)	0.43 (0.32, 0.54)	0.29 (0.25, 0.35)	0.14 (0.1, 0.19)	0.46 (0.39, 0.54)
False Positive Rate	0.18 (0.15, 0.22)	0.35 (0.28, 0.44)	0.08 (0.06, 0.1)	0.23 (0.2, 0.25)	0.44 (0.35, 0.52)	0.01 (0.09, 0.10)
Negative Predictive Value	0.95 (0.93, 0.96)	0.97 (0.94, 0.98)	0.93 (0.91, 0.94)	0.95 (0.94, 0.96)	0.97 (0.96, 0.98)	0.94 (0.93, 0.95)
Positive Predictive Value	0.40 (0.33, 0.48)	0.29 (0.23, 0.36)	0.55 (0.46, 0.65)	0.29 (0.25, 0.33)	0.20 (0.17, 0.25)	0.43 (0.36, 0.47)
Sensitivity	0.74 (0.65, 0.83)	0.86 (0.76, 0.93)	0.57 (0.46, 0.68)	0.71 (0.65, 0.76)	0.86 (0.81, 0.90)	0.55 (0.46, 0.61)
Specificity	0.82 (0.78, 0.85)	0.65 (0.56, 0.72)	0.92 (0.9, 0.94)	0.77 (0.75, 0.80)	0.56 (0.48, 0.66)	0.91 (0.90, 0.92)