Health economic simulation modeling of an AI-enabled clinical decision support system for coronary revascularization

Coronary revascularization decision-making can be challenging. While artificial intelligence (AI) models have been developed to support this decision-making, health economic evaluation of such models has been rare. To evaluate the economic value of an AI-enabled coronary revascularization decision support system in terms of cost savings and gains in quality adjusted life years (QALY). Retrospective health economic simulation modeling study using real-world patient data and AI-generated patient outcome predictions. 26,605 adult patients with obstructive coronary artery disease who underwent diagnostic coronary angiography between 2009 and 2019 in Alberta, Canada. Clinicians deciding among medical therapy only, percutaneous coronary intervention, and coronary artery bypass grafting were simulated to be provided with AI-generated decision support information in the form of 3- and 5-year major adverse cardiovascular event and all-cause mortality predictions. Average cost savings and gains in QALY, represented as a willingness-to-pay, per patient resulting from treatment decisions altered by the AI-generated decision support. Most actual coronary revascularization decisions could have been improved by AI decision support from a health economic perspective. At a willingness-to-pay of $50,000 per QALY, as many as 51% of all actual treatment decisions shifted to another treatment, resulting in an average cost saving of $31,204 and a QALY gain equivalent to up to $2,406 per patient. Even in a conservative scenario where clinicians’ AI adoption was limited by ignoring AI recommendations unless the gain in QALY was substantial, 22.4% of the actual decisions shifted, resulting in an average gain of 0.327 QALY, equivalent to up to $16,371, per patient. AI can help clinicians to optimize coronary revascularization decisions. The health system level economic value of optimized treatment decisions can be substantial in the form of reduced costs stemming from fewer future complications and improved patient outcomes. How much cost saving and gain in quality adjusted life years (QALY) can be expected from using an AI-enabled clinical decision support system for coronary revascularization decision-making? AI was able to improve the cost-effectiveness of 51% percent of actual treatment decisions. Pursuing AI-based optimal treatments would have resulted in an average cost saving of $31,204 and a QALY gain equivalent to $2,406 per patient. AI can help optimize coronary revascularization decisions, leading to substantial economic value in the form of cost savings and improved patient outcomes.