Automated echocardiographic detection of severe coronary artery disease using artificial intelligence
Upton, R, Mumith, A, Beqiri, A, Parker, A, Hawkes, W, Gao, S, Porumb, M, Sarwar, R, Marques, P, Markham, D, Kenworthy, J, O'Driscoll, J., Hassanali, N, Groves, K, Dockerill, C, Woodward, W, Alshargi, M, McCourt, A, Wilkes, E.H, Heitner, S.B, Yadava, M, Stojanovski, D, Lamata, P, Woodward, G and Leeson, P Automated echocardiographic detection of severe coronary artery disease using artificial intelligence. JACC: Cardiovascular Imaging.
|Authors||Upton, R, Mumith, A, Beqiri, A, Parker, A, Hawkes, W, Gao, S, Porumb, M, Sarwar, R, Marques, P, Markham, D, Kenworthy, J, O'Driscoll, J., Hassanali, N, Groves, K, Dockerill, C, Woodward, W, Alshargi, M, McCourt, A, Wilkes, E.H, Heitner, S.B, Yadava, M, Stojanovski, D, Lamata, P, Woodward, G and Leeson, P|
Background: Coronary artery disease is the leading global cause of mortality and morbidity and stress echocardiography remains one of the most commonly used diagnostic imaging tests.
Objectives: To establish whether an artificially intelligent system can be developed to automate stress echocardiography analysis and support clinician interpretation.
Methods: An automated image processing pipeline was developed to extract novel geometric and kinematic features from stress echocardiograms collected as part of a large, UK-based prospective, multi-centre, multi-vendor study. 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.
Results: 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.
Conclusion: Automated analysis of stress echocardiograms is possible using artificial intelligence and provision of automated classifications to clinicians when reading stress echocardiograms could improve accuracy, inter-reader agreement and reader confidence.
|Keywords||Stress echocardiography; Artificial intelligence; Coronary artery disease|
|Journal||JACC: Cardiovascular Imaging|
|Publication process dates|
|Accepted||22 Oct 2021|
|Deposited||11 Nov 2021|
|Accepted author manuscript|
File Access Level
|Output status||In press|
2views this month
1downloads this month