Early and accurate diagnosis is essential for effective and timely treatment, which contributes to improved patient outcomes. Non-invasive imaging modalities, such as computed tomography (CT), coronary computed tomography angiography, and cardiac magnetic resonance, are being used increasingly for the diagnosis of coronary heart disease. AI applications have demonstrated great promise in enhancing cardiovascular imaging, for example by automating coronary artery segmentation and scoring [Wolterink 2016, Zeleznik 2021], coronary stenosis evaluation [Liang 2017], coronary plaque segmentation [Lin 2022b], functional assessment of coronary stenosis [Itu 2016], and by analyzing CMR images to derive clinically relevant measures [Bai 2018]. AI has also been shown to be a useful tool for prognostic assessment, providing better risk assessment [Nakanishi 2021] and stratification [Bar 2024]. Systematic searches were conducted of five main databases from January 2018 to September 2023 for articles that used AI-based non-invasive CAD imaging modalities. A meta-analysis was conducted on studies assessing the diagnostic performance of AI for detecting ≥50% stenosis using patient- and vessel-level data.