Diagnosing cardiac arrhythmia through interpreting electrocardiogram (ECG) recordings is a challenging and time-consuming task, frequently resulting in inconsistent outcomes and misdiagnosis due to signal noise, interference, and comorbidities. To overcome these challenges, machine learning algorithms have been explored as potential solutions, with promising initial results. However, their lack of generalizability and explainability has hindered their widespread use in clinical settings. This study focuses on evaluating and reproducing a popular Deep Neuron Network (DNN) model proposed by Ribeiro et al. The performance of the model in classifying ECG recordings was found to be influenced by the characteristics of the training dataset, which was composed of different ECG recordings. Although the model exhibited strong generalizability with an F1 score of 0.87 when tested on the CPSC dataset, its performance was inconsistent when applied to the Shaoxing and Ningbo Hospital ECG dataset. To enhance the model's interpretability and performance, an attention layer was incorporated into the network, which improved its focus and resulted in an F1 score of 0.87 from 0.83 trained on the same dataset.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.