An explainable, bias-audited machine learning model to detect hidden hepatitis C from region-wide real-world health records
- 1BarcelonaBeta Brain Research Center
Abstract
Background: Although direct-acting antivirals have transformed hepatitis C virus (HCV) treatment, 25-30% of active infections in Spain remain undiagnosed. We aimed to develop and validate an interpretable machine-learning model to identify undiagnosed HCV infection using only data already recorded within the health system. Materials and Methods: We conducted a retrospective, population-based cohort study using the Andalusian Population Health Database (BPS). Individuals diagnosed with HCV between 2017 and 2024 (n=25,028) were matched, up to 10:1, to controls by birth year, sex, and health district. An Explainable Boosting Machine was trained on 2017-2022 data, with a threshold set in a 2023 validation set to guarantee [≥]60% sensitivity, then evaluated unmodified in an independent, non-matched, population-representative 2024 sample approximating real-world screening. Predictors comprised chronic-disease diagnoses and laboratory summary statistics recorded [≥]30 days before the index date; age and sex were excluded as matching variables. Predictors reflecting socioeconomic proxies or matching artefacts (pharmaceutical co-payment category, a zone-level deprivation index) were removed after explainability review. Results: In the independent test set, the model achieved an AUC of 0.837 (0.826 in validation), sensitivity 63.5%, specificity 91.8%, positive predictive value 7.0%, and negative predictive value 99.6%. Leading predictors were minimum alanine aminotransferase, HIV infection, dependence on non-tobacco substances, and platelet-count statistics, forming a clinically coherent, laboratory- and comorbidity-driven profile. Conclusion: An explainable model built exclusively from routine electronic health record data can identify undiagnosed HCV infection with discrimination comparable to previously published tools, evaluated under conditions approximating true population prevalence. Bias-auditing was feasible without sacrificing interpretability, supporting a scalable, equity-conscious instrument for the final phase of HCV elimination.
Related
- Reliability-Audited Explainable AI for Multi-Class Skin-Lesion 2 Triage Under Cross-Device Domain Shift
- Scalable Causal-Interpretable Machine Learning for Cancer Prescreening Using Electronic Health Records
- A methodological exploration of monthly incidence rate of hepatitis B in China: a time series and machine learning analysis
- Explainable machine learning and deep learning models for predicting in-hospital mortality in burn patients
- An explainable machine-learning framework for seasonal early warning of West Nile virus using predictive climate data
BibTeX
@misc{estebanmedina2026explainable,
title = {{An explainable, bias-audited machine learning model to detect hidden hepatitis C from region-wide real-world health records}},
author = {A. Esteban-Medina and C. Loucera and J. Dopazo and M. Romero Gomez},
howpublished = {medRxiv},
year = {2026},
month = nov,
doi = {10.64898/2026.11.05.26367298},
url = {https://www.medrxiv.org/content/10.64898/2026.11.05.26367298v1},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - An explainable, bias-audited machine learning model to detect hidden hepatitis C from region-wide real-world health records
AU - A. Esteban-Medina
AU - C. Loucera
AU - J. Dopazo
AU - M. Romero Gomez
PY - 2026
DA - 2026/11/05
PB - medRxiv
DO - 10.64898/2026.11.05.26367298
UR - https://www.medrxiv.org/content/10.64898/2026.11.05.26367298v1
AB - Background: Although direct-acting antivirals have transformed hepatitis C virus (HCV) treatment, 25-30% of active infections in Spain remain undiagnosed. We aimed to develop and validate an interpretable machine-learning model to identify undiagnosed HCV infection using only data already recorded within the health system. Materials and Methods: We conducted a retrospective, population-based cohort study using the Andalusian Population Health Database (BPS). Individuals diagnosed with HCV between 2017 and 2024 (n=25,028) were matched, up to 10:1, to controls by birth year, sex, and health district. An Explainable Boosting Machine was trained on 2017-2022 data, with a threshold set in a 2023 validation set to guarantee [≥]60% sensitivity, then evaluated unmodified in an independent, non-matched, population-representative 2024 sample approximating real-world screening. Predictors comprised chronic-disease diagnoses and laboratory summary statistics recorded [≥]30 days before the index date; age and sex were excluded as matching variables. Predictors reflecting socioeconomic proxies or matching artefacts (pharmaceutical co-payment category, a zone-level deprivation index) were removed after explainability review. Results: In the independent test set, the model achieved an AUC of 0.837 (0.826 in validation), sensitivity 63.5%, specificity 91.8%, positive predictive value 7.0%, and negative predictive value 99.6%. Leading predictors were minimum alanine aminotransferase, HIV infection, dependence on non-tobacco substances, and platelet-count statistics, forming a clinically coherent, laboratory- and comorbidity-driven profile. Conclusion: An explainable model built exclusively from routine electronic health record data can identify undiagnosed HCV infection with discrimination comparable to previously published tools, evaluated under conditions approximating true population prevalence. Bias-auditing was feasible without sacrificing interpretability, supporting a scalable, equity-conscious instrument for the final phase of HCV elimination.
ER -