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

Yuheng Jia; Yiming Li; Gaden Luosang; Jianyong Wang; Gang Peng; Xingzhou Pu; Weili Jiang; Wenjian Li; Zhengang Zhao; Yong Peng; Yuan Feng; Jiafu Wei; Yuanning Xu; Xingbin Liu; Zhang Yi; Mao Chen

doi:10.1093/ehjdh/ztae007

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

Eur Heart J Digit Health. 2024 Feb 8;5(3):219-228. doi: 10.1093/ehjdh/ztae007. eCollection 2024 May.

Authors

Yuheng Jia¹, Yiming Li¹, Gaden Luosang^{2

3}, Jianyong Wang², Gang Peng¹, Xingzhou Pu¹, Weili Jiang², Wenjian Li², Zhengang Zhao¹, Yong Peng¹, Yuan Feng¹, Jiafu Wei¹, Yuanning Xu¹, Xingbin Liu¹, Zhang Yi², Mao Chen¹

Affiliations

¹ Department of Cardiology, West China Hospital, Sichuan University, No.37 Guoxue Street, Chengdu 610041, P. R. China.
² Machine Intelligence Laboratory, College of Computer Science, Sichuan University, No.24 South Section 1, Yihuan Road, Chengdu 610065, P. R. China.
³ Department of Information Science and Technology, Tibet University, No.10 Zangda East Road, Lhasa 850000, Tibet, P. R. China.

Abstract

Aims: Permanent pacemaker implantation and left bundle branch block are common complications after transcatheter aortic valve replacement (TAVR) and are associated with impaired prognosis. This study aimed to develop an artificial intelligence (AI) model for predicting conduction disturbances after TAVR using pre-procedural 12-lead electrocardiogram (ECG) images.

Methods and results: We collected pre-procedural 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 five-fold cross-validation and tested it on the hold-out testing cohort. We also developed and validated an enhanced model that included additional clinical features. 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 area under the curve (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 images. 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.

Conclusion: Artificial intelligence-enhanced ECGs may offer better predictive value than traditionally defined high-risk ECG patterns.

Keywords: Artificial intelligence; Conduction disturbances; Convolutional neural network; Electrocardiogram; Transcatheter aortic valve replacement.