Automatic multilabel electrocardiogram diagnosis of heart rhythm or conduction abnormalities with deep learning: a cohort study

Abstract

Background Market-applicable concurrent electrocardiogram (ECG) diagnosis for multiple heart abnormalities that covers a wide range of arrhythmias, with better-than-human accuracy, has not yet been developed. We therefore aimed to engineer a deep learning approach for the automated multilabel diagnosis of heart rhythm or conduction abnormalities by real-time ECG analysis. MethodsWe used a dataset of ECGs (standard 10 s, 12-channel format) from adult patients (aged ≥18 years), with 21 distinct rhythm classes, including most types of heart rhythm or conduction abnormalities, for the diagnosis of arrhythmias at multilabel level. The ECGs were collected from three campuses of Tongji Hospital (Huazhong University of Science and Technology, Wuhan, China) and annotated by cardiologists. We used these datasets to develop a convolutional neural network approach to generate diagnoses of arrythmias. We collected a test dataset of ECGs from a new group of patients not included in the training dataset. The test dataset was annotated by consensus of a committee of board-certified, actively practicing cardiologists. To evaluate the performance of the model we assessed the F1 score and the area under the curve (AUC) of the receiver operating characteristic (ROC) curve, as well as quantifying sensitivity and specificity. To validate our results, findings for the test dataset were compared with diagnoses made by 53 ECG physicians working in cardiology departments who had a wide range of experience in ECG interpretation (range 0 to >12 years). An external public validation dataset of 962 ECGs from other hospitals was used to study generalisability of the diagnostic model.

Artificial intelligence-enhanced electrocardiography in cardiovascular disease management

“…In an evaluation published in 2020, a CNN was developed for the multilabel diagnosis of 21 distinct heart rhythms based on the 12-lead ECG using a training and validation dataset of >80,000 ECGs from >70,000 patients 11 . The reference standard consisted of consensus labels by a committee of cardiologists.…”

Interpretable deep learning for automatic diagnosis of 12-lead electrocardiogram

“…Recently, deep learning models have been applied to ECG data for various tasks including disease detection, annotation or localization, sleep staging, biometric human identification, denoising, and so on ( Hong et al., 2020 ). Deep neural networks have shown initial success in cardiac diagnosis from single-lead or multi-lead ECGs ( Chen et al, 2020 , Datta et al, 2017 , Hannun et al., 2019 , He et al., 2019 , Strodthoff et al., 2020 , Zhu et al., 2020 ). A deep learning model trained on a large single-lead ECG dataset with 91,232 ECG recordings shows superior performance than cardiologists for diagnosing 12 rhythm classes ( Hannun et al., 2019 ).…”

Automatic Detection for Multi-Labeled Cardiac Arrhythmia Based on Frame Blocking Preprocessing and Residual Networks

“…As for algorithms for multi-label classification (36), they can fall into problem transformation and algorithm adaption. With the development of neural networks, more studies (12,31,35,37) designed an adaptive algorithm for multi-label classification. However, algorithm adaption has a high demand for sufficient training data and effective parameter adjustment to reduce misdiagnosis for multi-labeled ECG.…”

“…However, the algorithms discussed earlier are mainly focused on processing single-lead ECG rather than the 12-lead ECG, which is commonly used in the clinical setting for providing more diagnostic information than a single-lead ECG on cardiac excitations (11). Also, it is still a challenge to auto-detect multitypes of cardiac diseases based on 12-lead ECG due to (i) similar morphological features of ECG among different types of diseases, such as between atrial fibrillation (AF) and premature atrial contraction (12); (ii) imbalanced ECG data for various heart diseases in some training datasets, which may result in excessive bias or over-fitting of the neural network for diagnosis; (iii) unequal recording length of clinical ECG recordings, which may result in loss of some essential signals in the process of preprocessing for training the neural network.…”