Chronic hepatitis B affects more than a million people in the U.S. and causes 4,000 deaths each year, yet the costs and benefits of treatment have not been fully evaluated. Using a model that simulates disease progression, we compare treatment programs for hepatitis B that start at an early versus late stage of disease. Early care is shown to improve health, reduce premature deaths, and prevent expensive complications, making it highly cost-effective. Our results demonstrate the importance of linking hepatitis B screening to treatment, and illustrate how predictive models can be used to evaluate strategies for improving access to care.