Cost-utility analysis of single nucleotide polymorphism panel-based machine learning algorithm to predict risk of opioid use disorder.

Aim: To conduct a cost-utility analysis of a novel genetic diagnostic test (OUDTEST) for risk of developing opioid use disorder for elective orthopedic surgery patients. Materials & Methods: A simulation model assessed cost-effectiveness and quality-adjusted life-years (QALYs) for OUDTEST from private insurer and self-insured employer perspectives over a 5-year time horizon for a hypothetical patient population. Results: OUDTEST was found to cost less and increase QALYs, over a 5-year period for private insurance (savings US$2510; QALYs 0.02) and self-insured employers (-US$2682; QALYs 0.02). OUDTEST was a dominant strategy in 71.1% (private insurance) and 72.7% (self-insured employer) of model iterations. Sensitivity analyses revealed robust results except for physician compliance. Conclusion: OUDTEST was expected to be a cost-effective solution for personalizing postsurgical pain management in orthopedic patients.