Table 7.

Performance of the prediction of depression screening status in contrasted subsamples.

Contrasted subsample and model (feature set)			No information rate		Accuracy		Sensitivity		Specificity		PPVa		NPVb		κ		AUCc
PHQ-9d score of ≥10 at assessment 1 or 2 (n=78)
	Ae	0.51		0.80		0.82		0.78		0.78		0.82		0.59		0.75
	Bf	0.51		0.77		0.79		0.75		0.75		0.79		0.54		0.74
	Cg	0.51		0.71		0.74		0.68		0.68		0.73		0.41		0.70
PHQ-9 score of ≥8 at assessment 1 or 2 (n=44)
	A	0.50		0.71		0.73		0.68		0.70		0.71		0.41		0.71
	B	0.50		0.71		0.77		0.64		0.68		0.74		0.41		0.68
	C	0.50		0.71		0.73		0.68		0.70		0.71		0.41		0.64
PHQ-9 average score of ≥8 (n=84)
	A	0.50		0.77		0.79		0.76		0.77		0.78		0.55		0.76
	B	0.50		0.71		0.71		0.71		0.71		0.71		0.43		0.71
	C	0.50		0.61		0.64		0.57		0.60		0.62		0.21		0.57
Top 20% and bottom 20% by average PHQ-9 score (n=96)
	A	0.50		0.77		0.77		0.77		0.77		0.77		0.54		0.80
	B	0.50		0.74		0.73		0.75		0.75		0.74		0.48		0.76
	C	0.50		0.65		0.63		0.67		0.65		0.64		0.29		0.62

^aPPV: positive predictive value.

^bNPV: negative predictive value.

^cAUC: area under the curve.

^dPHQ-9: 9-item Patient Health Questionnaire.

^eModel A includes digital biomarkers selected at a significance level of <.01.

^fModel B includes digital biomarkers selected at a significance level of <.05.

^gModel C includes digital biomarkers selected at a significance level of <.05 and ≥.01.