• Designing Clinically Useful AI: A Blueprint for Impact

     Shyon Parsa, M.D., Timothy Keyes, Ph.D., Dev Dash, M.D., M.P.H., Danton Char, M.D., Michelle M. Mello, J.D., Ph.D., Alison Callahan, Ph.D., Margaret Ann Smith, M.B.A., Sinjin Lee, M.D., Thomas Wang, Ph.D., Heidi Salisbury, C.N.S., Shinichi Goto, M.D., Ph.D., Vicki Parikh, M.D., Kenneth W. Mahaffey, M.D., Michael Salerno, M.D., Ph.D., Euan A. Ashley, D.Phil., Nigam H. Shah, Ph.D., and Sneha S. Jain, M.D., M.B.A. 

    Abstract

    Most artificial intelligence (AI) tools in health care are evaluated on statistical performance for diagnostic accuracy alone, which often fails to account for the realities of the clinical systems into which they may be deployed. This disconnect has contributed to a proliferation of AI tools that perform well in development but fail to gain traction or generate meaningful impact in clinical use. We propose the use of health AI target product profiles, which specify the performance thresholds an AI tool must meet to produce benefit within a specific care setting, accounting for workflow, capacity, and utility trade-offs. Using hypertrophic cardiomyopathy (HCM) detection as an example, we simulate the performance of an AI-augmented clinical program across a range of AI tool characteristics and health care resource constraints to identify the conditions under which clinical value could be realized. Health AI target product profiles can guide AI tool development, inform AI tool selection if multiple AI tools have already been developed, guide implementation strategies for AI-augmented programs, and prevent investment in AI tools that are unlikely to create value. Ultimately, this approach offers a proactive and context-driven pathway for designing clinically useful AI that can empower health systems, patients, and providers as active members of the AI design process. (Funded by the American Heart Association.)