Electrocardiogram-based prediction of conduction disturbances after transcatheter aortic valve replacement with convolutional neural network

Abstract

Background Permanent pacemaker implantation and left bundle branch block are common complications after transcatheter aortic valve replacement (TAVR) and are associated with impaired prognosis. Aims This study aimed to develop an artificial intelligence (AI) model for predicting conduction disturbances after TAVR using preprocedural 12-lead electrocardiogram (ECG) data. Methods We collected preprocedural 12-lead ECGs of patients who underwent TAVR at West China Hospital between March 2016 and March 2022. A hold-out testing set comprising 20% of the sample was randomly selected. We developed an AI model using a convolutional neural network, trained it using fivefold cross validation, and tested it on the hold-out testing cohort. We also developed and validated an enhanced model that included additional clinical features. Results After applying exclusion criteria, we included 1354 ECGs of 718 patients in the study. The AI model predicted conduction disturbances in the hold-out testing cohort with an AUC of 0.764, accuracy of 0.743, F1 score of 0.752, sensitivity of 0.876, and specificity of 0.624, based solely on pre-procedural ECG data. The performance was better than the Emory score (AUC = 0.704), as well as the Logistic (AUC = 0.574) and XGboost (AUC = 0.520) models built with previously identified high-risk ECG patterns. After adding clinical features, there was an increase in the overall performance with an AUC of 0.779, accuracy of 0.774, F1 score of 0.776, sensitivity of 0.794, and specificity of 0.752. Conclusions AI-enhanced ECGs may offer better predictive value than traditionally defined high-risk ECG patterns.

Artificial intelligence and transcatheter aortic valve implantation-induced conduction disturbances—adding insight beyond the human ‘I’

“…propose an interesting solution to do so based on the pre-operative ECG. 4 They developed an artificial intelligence (AI) model for ECG analysis to overcome the problem that human ECG interpretation is hampered by subjectiveness and level of expertise. This adds up to the ongoing discussion about the ECG criteria of LBBB and, hence, strikingly demonstrates the limitations of human ECG reading, interpretation, and classification of abnormalities.…”