TY - GEN
T1 - Deep Neural Network Trained on Surface ECG Improves Diagnostic Accuracy of Prior Myocardial Infarction over Q Wave Analysis
AU - Yildirim, Ozal
AU - Baloglu, Ulas B.
AU - Talo, Muhammed
AU - Ganesan, Prasanth
AU - Tung, Jagteshwar S.
AU - Kang, Guson
AU - Tooley, James
AU - Alhusseini, Mahmood I.
AU - Baykaner, Tina
AU - Wang, Paul J.
AU - Perez, Marco V.
AU - Tereshchenko, Larisa
AU - Narayan, Sanjiv M.
AU - Rogers, Albert J.
N1 - Publisher Copyright:
© 2021 Creative Commons.
PY - 2021
Y1 - 2021
N2 - Clinical screening of myocardial infarction is important for preventative treatment and risk stratification in cardiology practice, however current detection by electrocardiogram Q-wave analysis provides only modest accuracy for assessing prior cardiac events. We set out to evaluate the ability of a deep neural network trained on the electrocardiogram to identify patients with clinical history of myocardial infarction. We assessed 608 patients at two academic centers with adjudicated history of myocardial infarction. Surface electrocardiograms were used to train a neural network-based model that classifies patients with and without a history of infarction. Endpoints were assessed by clinical record review and accuracy of the model was compared against the manual assessment of pathologic Q waves. The neural network outperformed the accuracy of pathologic Q waves (62%). In training, the model accuracy converged to >98%. Validation was performed by cross-validation (k=5) with validation accuracy 71 ± 5%. Receiver-operator characteristics analysis resulted in a c-statistic of 0.730. Deep learning of a 12-lead ECG can identify features of prior myocardial injury more accurately than clinical Q-wave analysis and may serve as a valuable clinical screening tool.
AB - Clinical screening of myocardial infarction is important for preventative treatment and risk stratification in cardiology practice, however current detection by electrocardiogram Q-wave analysis provides only modest accuracy for assessing prior cardiac events. We set out to evaluate the ability of a deep neural network trained on the electrocardiogram to identify patients with clinical history of myocardial infarction. We assessed 608 patients at two academic centers with adjudicated history of myocardial infarction. Surface electrocardiograms were used to train a neural network-based model that classifies patients with and without a history of infarction. Endpoints were assessed by clinical record review and accuracy of the model was compared against the manual assessment of pathologic Q waves. The neural network outperformed the accuracy of pathologic Q waves (62%). In training, the model accuracy converged to >98%. Validation was performed by cross-validation (k=5) with validation accuracy 71 ± 5%. Receiver-operator characteristics analysis resulted in a c-statistic of 0.730. Deep learning of a 12-lead ECG can identify features of prior myocardial injury more accurately than clinical Q-wave analysis and may serve as a valuable clinical screening tool.
UR - http://www.scopus.com/inward/record.url?scp=85124744647&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85124744647&partnerID=8YFLogxK
U2 - 10.23919/CinC53138.2021.9662825
DO - 10.23919/CinC53138.2021.9662825
M3 - Conference contribution
AN - SCOPUS:85124744647
T3 - Computing in Cardiology
BT - 2021 Computing in Cardiology, CinC 2021
PB - IEEE Computer Society
T2 - 2021 Computing in Cardiology, CinC 2021
Y2 - 13 September 2021 through 15 September 2021
ER -