Employing Bayesian survival and cost-effectiveness modelling for more informed healthcare decision-making: Practical overview and current perspectives

Bayesian statistics offers a rigorous approach to integrate historical study or real-world data into survival, cost effectiveness, and related models that are commonly used in health technology assessments. In this article, we motivate the adoption of Bayesian methods to perform these analyses and explain how Bayesian methods can empower evidence generation for challenging datasets. Then, we discuss current factors hindering more widespread application of Bayesian methods to clinical study data and outline opportunities to employ Bayesian approaches and thereby overcome issues with conventional methods that frequently arise in regulatory and reimbursement submissions.

Key takeaways

• Bayesian models can improve the accuracy, precision, and transparency of treatment efficacy estimates in challenging decision-making scenarios, such as at initial reimbursement when data are immature and in rare diseases or subgroup analyses where sample size is limited.
• The use of Bayesian methods in health technology assessments is likely to continue to increase in the future as payers place further emphasis on early access agreements and precision medicine.
   

Download whitepaper

Return to Insights Center