Table 3

Comparison of performance with and without fall injuries

Model	AUC (95% CI)	Sensitivity (95% CI)	Specificity (95% CI)	Gap*	PPV (95% CI)	NPV (95% CI)	MCC (95% CI)
Child models
With falls	0.86 (0.85 to 0.87)	0.78 (0.77 to 0.79)	0.78 (0.77 to 0.79)	0.44	0.09 (0.08 to 0.10)	0.992 (0.990 to 0.994)	0.626 (0.613 to 0.639)
No falls	0.85 (0.84 to 0.86)	0.71 (0.70 to 0.72)	0.81 (0.80 to 0.82)	0.48	0.12 (0.11 to 0.13)	0.987 (0.983 to 0.991)	0.569 (0.553 to 0.585)
Adult models
With falls	0.85 (0.85 to 0.85)	0.76 (0.76 to 0.76)	0.80 (0.80 to 0.80)	0.44	0.11 (0.11 to 0.11)	0.990 (0.989 to 0.991)	0.619 (0.614 to 0.624)
No falls	0.87 (0.87 to 0.87)	0.77 (0.76 to 0.78)	0.84 (0.83 to 0.85)	0.39	0.16 (0.15 to 0.17)	0.989 (0.988 to 0.990)	0.659 (0.652 to 0.666)
All ages models
With falls	0.85 (0.85 to 0.85)	0.74 (0.74 to 0.74)	0.81 (0.81 to 0.81)	0.45	0.12 (0.12 to 0.12)	0.989 (0.988 to 0.990)	0.602 (0.597 to 0.607)
No falls	0.86 (0.86 to 0.86)	0.77 (0.76 to 0.78)	0.79 (0.78 to 0.80)	0.44	0.13 (0.13 to 0.13)	0.988 (0.987 to 0.989)	0.623 (0.617 to 0.629)

*The gap between sensitivity and specificity. Calculated as follows: Gap = (1−Sensitivity) + (1−Specificity).
AUC, area under curve; MCC, Matthews correlation coefficient; NPV, negative predictive value; PPV, positive predictive value.