Assessing performance of the Hepatitis C Emergency Department (HepC-EnD) screening tool: implementation protocol

Hepatitis C virus (HCV) infection affects more than 2.4 million people in the United States, with approximately one-third of individuals unaware of their infection. Despite availability of highly curative direct-acting antiviral therapies, low screening and treatment uptake remain barriers to HCV elimination, leading the US Centers for Disease Control and Prevention to expand HCV screening recommendations in 2020 to include universal HCV testing for all adults. Emergency departments (EDs) represent an opportunity for HCV screening because they frequently serve populations at increased HCV risk. However, existing nontargeted ED screening programs are resource-intensive and may lack long-term sustainability. This study aims to develop, implement, and evaluate Hepatitis C Emergency Department (HepC-EnD), a machine learning (ML)-based clinical decision support (CDS) tool designed to enable targeted and sustainable HCV screening within ED workflows. The HepC-EnD screening tool will be assessed in a pre-post implementation study guided by the Exploration, Preparation, Implementation, Sustainment framework and CDS Five Rights. In Aim 1, ML based HCV risk prediction algorithms are developed and validated using electronic health record (EHR) data from OneFL+, incorporating sociodemographic, clinical, and social determinants of health predictors. In Aim 2, HepC-EnD is developed as an EHR-integrated CDS tool alerting ED health care professionals when predicted HCV risk scores exceed a prespecified threshold. Stakeholder meetings and semi-structured interviews with ED clinicians will guide iterative refinement to optimize usability and workflow integration. In Aim 3, a quasi-experimental pre-post study across two EDs compares targeted HepC-EnD screening against nontargeted HCV screening for 24 months. This type 2 hybrid implementation-effectiveness study will assess HepC-EnD usability, acceptability, feasibility, and adoption. The primary outcome is new HCV or HIV diagnosis. Secondary outcomes include alert rates, HCV and HIV testing rates, linkage to care rates, and cost-effectiveness. HepC-EnD addresses limitations of existing HCV screening approaches by integrating ML-driven risk stratification into routine clinical workflows. This targeted approach has the potential to improve screening efficiency and diagnostic yield while reducing the resource burden associated with nontargeted screening. If successful, HepC-EnD may provide a scalable and sustainable framework for integrating ML-based targeted screening into clinical practice. ClinicalTrial.gov (identifier NCT07406490, Date 1/27/2026).