An ensemble machine learning classifier was trained, using the extracted features, to identify patients with severe coronary artery disease on invasive coronary angiography. The model was tested in an independent US study.
How availability of an AI classification might impact clinical interpretation of stress echocardiograms was evaluated in a randomised cross-over reader study.
Acceptable classification accuracy for identification of patients with severe coronary artery disease in the training dataset was achieved on cross fold validation based on 31 unique geometric and kinematic features, with a specificity of 92.7% and a sensitivity of 84.4%.
This accuracy was maintained in the independent validation dataset. The use of the AI classification tool by clinicians increased inter-reader agreement and confidence as well as sensitivity for detection of disease by 10% to achieve an AUROC of 0.93.
Figure 1. Novel Artificial Intelligence–Derived Features Improve Coronary Disease Classification Novel quantitative features of regional wall motion can be implemented into machine learning classifiers to assist and enhance clinician performance during interpretation of stress echocardiography in the investigation of coronary artery disease. AI = artificial intelligence; AUROC = area under the receiver-operating characteristic curve; CAD = coronary artery disease; SE = stress echocardiography.
Automated analysis of stress echocardiograms is possible using artificial intelligence, and provision of automated classifications to clinicians when reading stress echocardiograms using EchoGo Pro could improve accuracy, inter-reader agreement and reader confidence.