Motivated by the desire to facilitate clinically relevant applications of AI, we propose to systematically review biomedical AI efforts in the published literature and ongoing within the CTSA program from the perspective of translational science and clinical applications.
At least two communities are involved in biomedical AI. The first group is comprised of “methodologists” including statisticians, computer and “data” scientists who understand mathematics, statistics and computing. The second, too often separate, community is comprised of “domain experts” including biomedical scientists, clinicians and health-care administrators who understand the problems and the data.These communities have very different perspectives including largely separate literatures, conferences, promotion criteria and cultures. Since 2006, the CTSA program has included efforts to bring these two groups together in service of translational science and clinical application.
The proposed Synergy paper brings together computer scientists, informaticians, translational scientists and clinicians to match AI applications to the NCATS vision of translational science (https://ncats.nih.gov/translation/spectrum) to identify challenges and opportunities for AI across the translational science spectrum.