UK: The use of artificial intelligence (AI) can help in the automated analysis of stress echocardiograms, a recent study has suggested. The provision of automated classifications to clinicians while reading stress echocardiography (SE) could improve the inter-reader agreement, accuracy, and reader confidence. The study was published in the journal JACC: Cardiovascular Imaging on December 15, 2021.
Coronary artery disease (CAD) is the leading cause of mortality and morbidity worldwide. This can be effectively managed by cardiac imaging that helps in risk stratification on those who may require further treatment. one of the most widely used modalities for the noninvasive assessment of CAD is stress echocardiography. This is because of its high patient tolerability, absence of ionizing radiation, and low cost.
Against the above background, Ross Upton, University of Oxford, Oxford, United Kingdom, and colleagues aimed to establish whether an AI system can be developed to automate stress echocardiography analysis and support clinician interpretation.
For this purpose, the researchers developed an automated image processing pipeline to extract novel geometric and kinematic features from stress echocardiograms. This was collected as part of a large, United Kingdom-based prospective, multicenter, multivendor study. In order to identify patients with severe CAD on invasive coronary angiography, an ensemble machine learning classifier was trained, using the extracted features.
In an independent U.S. study, the model was tested. How the availability of an AI classification might impact the clinical interpretation of SEs was evaluated in a randomized crossover reader study.
Key findings include:
Acceptable classification accuracy for identification of patients with severe coronary artery disease in the training data set 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 data set.
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 area under the receiver-operating characteristic curve of 0.93.
"Automated analysis of stress echocardiograms is possible using AI and provision of automated classifications to clinicians when reading stress echocardiograms could improve the inter-reader agreement, accuracy, and reader confidence," wrote the authors.
Reference:
The study titled, "Automated Echocardiographic Detection of Severe Coronary Artery Disease Using Artificial Intelligence," was published in the journal JACC: Cardiovascular Imaging.
DOI: 10.1016/j.jcmg.2021.10.013