Interpreting Wide-Complex Tachycardia With the Use of Artificial Intelligence.
Benjamin J W Chow, Najmeh Fayyazifar, Saad Balamane, Nishita Saha, Manzar Farooqui, Bara'ah A Hasan, Owen Clarkin, Martin Green, Andrew Maiorana, Mehrdad Golian, Girish Dwivedi
Author Information
Benjamin J W Chow: Department of Medicine (Cardiology), University of Ottawa Heart Institute, Ottawa, Ottawa, Ontario, Canada; Department of Radiology, University of Ottawa, Ottawa, Ontario, Canada. Electronic address: bchow@ottawaheart.ca.
Najmeh Fayyazifar: Harry Perkins Institute of Medical Research, University of Western Australia, Murdoch, Western Australia, Australia; Department of Cardiology, Fiona Stanley Hospital, Murdoch, Western Australia, Australia.
Saad Balamane: Department of Medicine (Cardiology), University of Ottawa Heart Institute, Ottawa, Ottawa, Ontario, Canada.
Nishita Saha: Department of Medicine (Cardiology), University of Ottawa Heart Institute, Ottawa, Ottawa, Ontario, Canada.
Manzar Farooqui: Department of Medicine (Cardiology), University of Ottawa Heart Institute, Ottawa, Ottawa, Ontario, Canada.
Bara'ah A Hasan: Department of Medicine (Cardiology), University of Ottawa Heart Institute, Ottawa, Ottawa, Ontario, Canada.
Owen Clarkin: Department of Medicine (Cardiology), University of Ottawa Heart Institute, Ottawa, Ottawa, Ontario, Canada.
Martin Green: Department of Medicine (Cardiology), University of Ottawa Heart Institute, Ottawa, Ottawa, Ontario, Canada.
Andrew Maiorana: Fiona Stanley Hospital, Murdoch, Western Australia, Australia; School of Allied Health, Faculty of Health Sciences, Curtin University, Bentley, Perth, Western Australia.
Mehrdad Golian: Department of Medicine (Cardiology), University of Ottawa Heart Institute, Ottawa, Ottawa, Ontario, Canada.
Girish Dwivedi: Harry Perkins Institute of Medical Research, University of Western Australia, Murdoch, Western Australia, Australia; Department of Cardiology, Fiona Stanley Hospital, Murdoch, Western Australia, Australia.
BACKGROUND: Adopting artificial intelligence (AI) in medicine may improve speed and accuracy in patient diagnosis. We sought to develop an AI algorithm to interpret wide-complex tachycardia (WCT) electrocardiograms (ECGs) and compare its diagnostic accuracy with that of cardiologists. METHODS: Using 3330 WCT ECGs (2906 supraventricular tachycardia [SVT] and 424 ventricular tachycardia [VT]), we created a training/validation (3131) and a test set (199 ECGs). A convolutional neural network structure using a modification of differentiable architecture search was developed to differentiate between SVT and VT. RESULTS: The mean accuracy of electrophysiology (EP) cardiologists was 92.5% with sensitivity 91.7%, specificity 93.4%, positive predictive value 93.7%, and negative predictive value 91.7%. Non-EP cardiologists had an accuracy of 73.2 ± 14.4% with sensitivity, specificity, and positive and negative predictive values of 59.8 ± 18.2%, 93.8 ± 3.7%, 93.6 ± 2.3%, and 73.2 ± 14.4%, respectively. AI had superior sensitivity and accuracy (91.9% and 93.0%, respectively) than non-EP cardiologists and similar performance compared with EP cardiologists. Mean time to interpret each ECG varied from 10.1 to 13.8 seconds for EP cardiologists and from 3.1 to 16.6 seconds for non-EP cardiologists. AI required a mean of 0.0092 ± 0.0035 seconds for each ECG interpretation. CONCLUSIONS: AI appears to diagnose WCT with accuracy superior to non-EP cardiologists and similar to EP cardiologists. Using AI to assist with ECG interpretations may improve patient care.
