Table 5. Diagnostic efficacy of each independent predictor and predictive model using the training set for BI-RADS category 4A positive lesions.

Factor	SEN (95% CI)	SPE (95% CI)	PPV (95% CI)	NPV (95% CI)	AUC (95% CI)	Z value	P value
Age	0.75 (0.64–0.84)	0.47 (0.41–0.54)	0.32 (0.28–0.36)	0.85 (0.79–0.90)	0.61 (0.54–0.68)	6.10	<0.001
Nipple discharge	0.34 (0.24–0.45)	0.93 (0.89–0.96)	0.6 (0.47–0.72)	0.81 (0.78–0.83)	0.63 (0.58–0.69)	7.56	<0.001
Ultrasound BI-RADS assessment	0.75 (0.64–0.84)	0.61 (0.54–0.67)	0.39 (0.34–0.43)	0.88 (0.83–0.92)	0.68 (0.62–0.74)	6.10	<0.001
Deep learning system classification results	0.80 (0.70–0.88)	0.56 (0.49–0.62)	0.37 (0.33–0.42)	0.90 (0.84–0.93)	0.68 (0.63–0.73)	6.30	<0.001
Predictive model	0.79 (0.68–0.87)	0.78 (0.72–0.83)	0.53 (0.47–0.60)	0.92 (0.88–0.95)	0.85 (0.80–0.90)

BI-RADS, Breast Imaging Reporting and Data System; SEN, sensitivity; CI, confidence interval; SPE, specificity; PPV, positive predictive value; NPV, negative predictive value; AUC, area under the curve.