Development and validation of a machine learning model for evidence of prior or current HCV infection: a demographic...

Hepatitis C virus (HCV) remains underdiagnosed in the United States despite recommendations for universal screening. A simple approach based on readily available demographic information may help target screening in settings where screening implementation continues to be incomplete.

We analyzed 10 NHANES cycles (1999-2014 and 2017-2023) and defined HCV exposure as a positive HCV antibody or RNA result. Using sex, birth year, race/ethnicity, birthplace, and income-to-poverty ratio, we trained and compared logistic regression (LR) and machine learning models in training and cycle-based internal validation cohorts (48,434 and 20,762 participants, respectively). Model performance was evaluated based on sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and the area under the receiver operating characteristic curve (AUROC). A web-based calculator was developed to estimate HCV-marker positivity risk and support prioritization of confirmatory HCV testing.

69,196 participants were included, with 967 showing evidence of HCV exposure. Weighted HCV prevalence remained relatively stable across cycles, ranging from 1.22% to 1.93%. The prevalence did not change significantly after the pandemic. Earlier birth year, male sex, non-Hispanic Black race, US-born status, and lower income-to-poverty ratio were independently associated with HCV exposure. XGBoost performed better than LR in the validation cohort (AUROC 0.859 vs. 0.762, p < 0.001), but PPV remained low (5.1%). In the RNA-positive sensitivity analysis, XGBoost again showed the best validation performance (AUROC 0.867). Predicted risk showed clear risk stratification: observed HCV prevalence increased from 0.05% in the lowest-risk decile to 7.80% in the highest, with the top decile containing 57.2% of participants with HCV exposure and the top three deciles containing 86.2%.

Five demographic variables were sufficient to build a supportive HCV-exposure risk stratification model in a nationally representative US sample. Most HCV-exposed individuals were concentrated in the highest predicted-risk groups, suggesting that this approach could help prioritize outreach and confirmatory testing where universal screening uptake remains incomplete. Because no laboratory data are required, it may also be practical in data-limited settings.