Implementation of a national AI technology program on cardiovascular outcomes and the health system

• DOI: 10.1038/s41591-025-03620-y
• Publication Date: 2025-04-05T05:22:22Z
• Authors: Timothy A. Fairbairn; Liam Mullen; Edward Nicol; Gregory Y. H. Lip; Matthias Schmitt; Matthew Shaw; Laurence Tidbury; Ian Kemp; Jennifer Crooks; Girvan Burnside; Sumeet Sharma; Anoop Chauhan; Chee Liew; Sawan Waidyanatha; Sri Iyenger; Andrew Beale; Imran Sunderji; John P. Greenwood; Manish Motwani; Anna Reid; Anna Beattie; Justin Carter; Peter Haworth; Nicholas Bellenger; Benjamin Hudson; Jonathan Rodrigues; Oliver Watson; Vinod Venugopal; Russell Bull; Peter O’Kane; Aparna Deshpande; Gerald P. McCann; Simon Duckett; Hatef Mansoubi; Victoria Parish; Joban Sehmi; Campbell Rogers; Sarah Mullen; Jonathan Weir-McCalL
• Keywords: Fractional Flow Reserve

Abstract Coronary artery disease (CAD) is a major cause of ill health and death worldwide. computed tomographic angiography (CCTA) the first-line investigation to detect CAD in symptomatic patients. This diagnostic approach risks greater second-line heart tests treatments at cost patient system. The National Health Service funded use an artificial intelligence (AI) tool, tomography (CT)-derived fractional flow reserve (FFR-CT), patients with chest pain improve physician decision-making reduce downstream tests. observational cohort study assessed impact FFR-CT on cardiovascular outcomes by including all investigated CCTA during national AI implementation program 27 hospitals (CCTA n = 90,553 7,863). was safe, no difference all-cause ( 1,134 (3.2%) versus 1,612 (2.9%), adjusted-hazard ratio (aHR) 1.00 (0.93–1.08), P 0.97) or mortality 465 (1.3%) 617 (1.1%), aHR 0.96 (0.85–1.08), 0.48), while reducing invasive coronary angiograms 5,720 (16%) 8,183 (14.9%), 0.93 (0.90–0.97), < 0.001) noninvasive cardiac (189/1,000 167/1,000), 0.001). Implementation AI-diagnostic tool as part intervention safe beneficial pathway system fewer 2 years.