Artificial Intelligence Detection of Heart Failure on Coronary CT Angiography: External Validation in Patients with NSTE-ACS

Vollständiger Abstract

Worum geht es in dieser Arbeit?

Abstract Background Heart failure (HF) in non-ST-segment elevation acute coronary syndrome (NSTE-ACS) is associated with poor prognosis but often under-recognised. Coronary computed tomography angiography (CCTA), increasingly used in NSTE-ACS, contains cardiopulmonary features not routinely assessed for HF. We evaluated whether an artificial intelligence (AI) algorithm applied to CCTA could identify HF likelihood in NSTE-ACS. Methods In this retrospective external validation study, the AI algorithm was applied without retraining or recalibration to CCTA scans from 1009 patients with NSTE-ACS in the VERDICT-trial. Using a prespecified threshold, patients were classified as low or high AI-likelihood of HF. The primary outcome was HF during index hospitalisation. The secondary outcome was post-discharge HF hospitalisation among patients discharged alive without HF, with analyses adjusted for GRACE score>140 and severe coronary artery disease. Death was treated as a competing risk. Results Overall, 838 patients (83%) were classified as low AI-likelihood and 171 (17%) as high. During index hospitalisation, HF was diagnosed in 10 patients (1%) with low AI-likelihood and 12 (7%) with high. Sensitivity was 55%, specificity 84%, positive predictive value 7%, and negative predictive value 99%. High AI-likelihood was associated with increased risk of index HF (sHR, 5.39, 95%CI 2.32-12.50). After discharge, HF hospitalisation occurred in 25 patients (3%) with low AI-likelihood and 14 (8%) with high. High AI-likelihood remained associated with HF hospitalisation (sHR 2.56, 95%CI 1.34-4.90). Conclusions AI-based CCTA analysis identified a large low-risk subgroup and a smaller subgroup at increased HF risk, supporting further evaluation of opportunistic HF assessment from CCTA.