Background: Cost-effectiveness analysis of artificial intelligence (AI) in medicine demands consideration of clinical, technical, and economic aspects to generate impactful research of a novel and highly versatile technology.
Objective: We aimed to systematically scope existing literature on the cost-effectiveness of AI and to extract and summarize clinical, technical, and economic dimensions required for a comprehensive assessment.
Methods: A scoping literature review was conducted to map medical, technical, and economic aspects considered in studies on the cost-effectiveness of medical AI. Based on these, a framework for health policy analysis was developed.
Results: Among 4820 eligible studies, 13 met the inclusion criteria for our review. Internal medicine and emergency medicine were the clinical disciplines most frequently analyzed. Most of the studies included were from the United States (5/13, 39%), assessed solutions requiring market access (9/13, 69%), and proposed optimization of direct resources as the most frequent value proposition (7/13, 53%). On the other hand, technical aspects were not uniformly disclosed in the studies we analyzed. A minority of articles explicitly stated the payment mechanism assumed (5/13, 38%), while it remained unspecified in the majority (8/13, 62%) of studies.
Conclusions: Current studies on the cost-effectiveness of AI do not allow to determine if the investigated AI solutions are clinically, technically, and economically viable. Further research and improved reporting on these dimensions seem relevant to recommend and assess potential use cases for this technology.
