Routine laboratory model for identifying significant fibrosis in chronic hepatitis B

Table 3 Discriminative performance of the machine-learning model across cohorts

Cohort1	AUC (95%CI)	Sensitivity (95%CI)	Specificity (95%CI)	PPV	NPV	F1 (95%CI)
Development	0.8528 (0.8301-0.8722)	0.8088 (0.7711-0.8449)	0.7077 (0.6735-0.7394)	0.6212	0.8619	0.7027 (0.6708-0.7337)
External (First Affiliated Hospital of Zhejiang University)	0.8379 (0.8000-0.8721)	0.7290 (0.6506-0.7949)	0.7361 (0.6966-0.7778)	0.4788	0.8909	0.5780 (0.5151-0.6383)
National Health and Nutrition Examination Survey (surrogate-labeled)	0.817 (0.800-0.833)

¹Area under the receiver operating characteristic curve with 95% confidence intervals is reported for the development cohort and the biopsy-confirmed external validation cohort (First Affiliated Hospital of Zhejiang University), together with sensitivity, specificity, positive predictive value, negative predictive value, and F1-score (with 95% confidence intervals where applicable) evaluated at the pre-specified operating point used in the main analysis. For the National Health and Nutrition Examination Survey exploratory cohort, fibrosis status was derived using an aspartate aminotransferase to platelet ratio index/fibrosis-4-based surrogate phenotyping algorithm rather than histology; therefore, only area under the curve (95% confidence interval) is presented as the primary measure of discrimination for this surrogate-labeled outcome, and threshold-dependent metrics are not reported.

PPV: Positive predictive value; NPV: Negative predictive value; AUC: Area under the curve; CI: Confidence interval.