Artificial Intelligence and Digital Health Innovations in Hepatitis Care: Transforming Screening, Diagnosis, and Elimination Efforts

Abstract

Viral hepatitis remains one of the leading causes of preventable death worldwide, with the World Health Organization
estimating that 287 million people were living with chronic hepatitis B or C infection in 2024 and roughly 3,500
people dying each day from hepatitis-related complications, placing global elimination targets for 2030 off track.
Artificial intelligence (AI) and digital health technologies are increasingly positioned as tools capable of narrowing
the diagnosis-and-treatment gap that underlies this burden. This review synthesizes current literature on the application
of AI and digital health innovations across the hepatitis care continuum, including machine learning-based screening
and risk prediction, deep learning approaches for non-invasive liver fibrosis staging and hepatocellular carcinoma
(HCC) detection on imaging, telemedicine and facilitated-telehealth models for linkage to care, mobile health
applications for patient self-management, large language model (LLM)-based chatbots for patient education and
clinical decision support, and AI-assisted drug discovery for antiviral and functional-cure strategies. Evidence
indicates that AI models can match or exceed conventional diagnostic accuracy in several domains, that telemedicine
markedly improves treatment access among underserved and rural populations, and that digital tools show promise in
HCC risk stratification and drug repurposing. However, persistent challenges include algorithmic bias, data privacy
concerns, the digital divide affecting marginalized populations, limited external validation of AI models, and an
evolving regulatory landscape. This review concludes that AI and digital health tools, when implemented equitably
and validated rigorously, offer a meaningful pathway toward accelerating global hepatitis elimination goals.