Background/Objectives: Invasive coronary angiography (ICA) is the gold standard for the diagnosis of coronary artery disease (CAD), with various non-invasive imaging modalities also available. Machine learning (ML) methods are increasingly applied to overcome the limitations of diagnostic imaging by improving accuracy and observer
[...] Read more.
Background/Objectives: Invasive coronary angiography (ICA) is the gold standard for the diagnosis of coronary artery disease (CAD), with various non-invasive imaging modalities also available. Machine learning (ML) methods are increasingly applied to overcome the limitations of diagnostic imaging by improving accuracy and observer independent performance.
Methods: This meta-analysis (PRISMA method) summarizes the evidence for ML-based analyses of coronary imaging data from ICA, coronary computed tomography angiography (CT), and nuclear stress perfusion imaging (SPECT) to predict clinical outcomes and performance for precise diagnosis. We searched for studies from Jan 2012–March 2023. Study-reported c index values and 95% confidence intervals were used. Subgroup analyses separated models by outcome. Combined effect sizes using a random-effects model, test for heterogeneity, and Egger’s test to assess publication bias were considered.
Results: In total, 46 studies were included (total subjects = 192,561; events = 31,353), of which 27 had sufficient data. Imaging modalities used were CT (
n = 34), ICA (
n = 7) and SPECT (
n = 5). The most frequent study outcome was detection of stenosis (
n = 11). Classic deep neural networks (
n = 12) and convolutional neural networks (
n = 7) were the most used ML models. Studies aiming to diagnose CAD performed best (0.85; 95% CI: 82, 89); models aiming to predict clinical outcomes performed slightly lower (0.81; 95% CI: 78, 84). The combined c-index was 0.84 (95% CI: 0.81–0.86). Test of heterogeneity showed a high variation among studies (
I2 = 97.2%). Egger’s test did not indicate publication bias (
p = 0.485).
Conclusions: The application of ML methods to diagnose CAD and predict clinical outcomes appears promising, although there is lack of standardization across studies.
Full article