Practice Pattern Changes After Adoption Of Diagnostic AI Tool Used In Conjunction With Cardiac Imaging.
Authors
Affiliations (3)
Affiliations (3)
- Anna Zink ([email protected]), Tufts University, Medford, Massachusetts.
- Michael E. Chernew, Harvard University, Boston, Massachusetts.
- Hannah T. Neprash, University of Minnesota, Minneapolis, Minnesota.
Abstract
In 2018, Medicare established coverage and reimbursement for its first service using artificial intelligence (AI): computed tomography (CT) fractional flow reserve (FFR<sub>CT</sub>). FFR<sub>CT</sub> is used in conjunction with cardiac imaging to diagnose coronary artery disease. Medicare reimbursement provides the opportunity to observe clinicians' adoption of FFR<sub>CT</sub> and examine changes in utilization, spending, clinician productivity, and patient outcomes associated with its use. In this study, we exploited variation in the timing of FFR<sub>CT</sub> adoption by clinicians, quantifying changes in practice patterns before and after adoption compared with nonadopters. We found that use of the underlying coronary artery disease test required for FFR<sub>CT</sub> increased after the adoption of FFR<sub>CT</sub>, whereas invasive test use declined. On net, per patient diagnostic spending for coronary artery disease increased. We found no evidence that adopting FFR<sub>CT</sub> facilitated earlier diagnosis of coronary artery disease, although clinicians saw a larger share of patients with coronary artery disease after adoption, and clinician productivity (that is, total visit count) increased. After clinicians adopted FFR<sub>CT</sub>, we observed a decrease in rates of cardiac-related adverse events among their patients.