A 12-Lead ECG database to identify origins of idiopathic ventricular arrhythmia containing 334 patients

Zheng, Jianmin; Fu, Guohua; Anderson, Kyle; Rakovski, Cyril

doi:10.1038/s41597-020-0440-8

Cited by 16 publications

(15 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hypertension was the most common underlying disease, followed by dyslipidemia and type 2 DM. More details of the other open-source data sets can be found in the report of J Zheng et al [ 17 ].…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

A High-Precision Deep Learning Algorithm to Localize Idiopathic Ventricular Arrhythmias

Chang

Chen

Liu

et al. 2022

JPM

View full text Add to dashboard Cite

Background: An accurate prediction of ventricular arrhythmia (VA) origins can optimize the strategy of ablation, and facilitate the procedure. Objective: This study aimed to develop a machine learning model from surface ECG to predict VA origins. Methods: We obtained 3628 waves of ventricular premature complex (VPC) from 731 patients. We chose to include all signal information from 12 ECG leads for model input. A model is composed of two groups of convolutional neural network (CNN) layers. We chose around 13% of all the data for model testing and 10% for validation. Results: In the first step, we trained a model for binary classification of VA source from the left or right side of the chamber with an area under the curve (AUC) of 0.963. With a threshold of 0.739, the sensitivity and specification are 90.7% and 92.3% for identifying left side VA. Then, we obtained the second model for predicting VA from the LV summit with AUC is 0.998. With a threshold of 0.739, the sensitivity and specificity are 100% and 98% for the LV summit. Conclusions: Our machine learning algorithm of surface ECG facilitates the localization of VPC, especially for the LV summit, which might optimize the ablation strategy.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Furthermore, to increase our training data size, we also included the online datasets presented in a previously published study [ 17 ]. This data set is composed of 334 patients which are gathered at Chapman University and Ningbo First Hospital of Zhejiang University, Ningbo, China.…”

Section: Methodsmentioning

confidence: 99%

A High-Precision Deep Learning Algorithm to Localize Idiopathic Ventricular Arrhythmias

Chang

Chen

Liu

et al. 2022

JPM

View full text Add to dashboard Cite

show abstract

“…We have collected a large expertly labeled database consisting of 18,612 ECG recordings recorded from 545 patients, we trained and validated a state-of-the-art machine learning algorithm to predict the exact 21 anatomical origins of IVA with an accuracy of 98.24%. Under the auspices of Chapman University and Ningbo First Hospital of Zhejiang University, we created and shared our proprietary 12-lead ECG database interpreted by experts with the scientific community ( 30 ).…”

Section: Discussionmentioning

confidence: 99%

A High Precision Machine Learning-Enabled System for Predicting Idiopathic Ventricular Arrhythmia Origins

Zheng

Struppa

et al. 2022

Front. Cardiovasc. Med.

Self Cite

View full text Add to dashboard Cite

BackgroundRadiofrequency catheter ablation (CA) is an efficient antiarrhythmic treatment with a class I indication for idiopathic ventricular arrhythmia (IVA), only when drugs are ineffective or have unacceptable side effects. The accurate prediction of the origins of IVA can significantly increase the operation success rate, reduce operation duration and decrease the risk of complications. The present work proposes an artificial intelligence-enabled ECG analysis algorithm to estimate possible origins of idiopathic ventricular arrhythmia at a clinical-grade level accuracy.MethodA total of 18,612 ECG recordings extracted from 545 patients who underwent successful CA to treat IVA were proportionally sampled into training, validation and testing cohorts. We designed four classification schemes responding to different hierarchical levels of the possible IVA origins. For every classification scheme, we compared 98 distinct machine learning models with optimized hyperparameter values obtained through extensive grid search and reported an optimal algorithm with the highest accuracy scores attained on the testing cohorts.ResultsFor classification scheme 4, our pioneering study designs and implements a machine learning-based ECG algorithm to predict 21 possible sites of IVA origin with an accuracy of 98.24% on a testing cohort. The accuracy and F1-score for the left three schemes surpassed 99%.ConclusionIn this work, we developed an algorithm that precisely predicts the correct origins of IVA (out of 21 possible sites) and outperforms the accuracy of all prior studies and human experts.

show abstract

“…Secondly, the trained model presented good generalization properties when predicting samples from the QT database (Table 1) as well as in the LU [23] and the Zhejiang [30] databases (Table 2). Specifically, the performance on the LU database surpasses all approaches in the literature and even displays F 1 -scores of 100% for the QRS and T waves, which hint to both the robustness of our model and at the relative simplicity of the represented rhythms in the database.…”

Section: Loss Functionmentioning

confidence: 99%

“…The QT [22], the LU [23] and the database from the Ningbo First Hospital of Zhejiang University [30] (hereinafter the "Zhejiang" database) were employed for model training and evaluation. Specifically: the QT database was used for synthetic data generation and model training; the LU database, for synthetic data generation and evaluation; and the Zhejiang database, for model testing.…”

Section: Databasesmentioning

confidence: 99%

Generalizing electrocardiogram delineation -- Training convolutional neural networks with synthetic data augmentation

Jiménez-Pérez¹,

Acosta²,

Alcaine³

et al. 2021

Preprint

View full text Add to dashboard Cite

Obtaining per-beat information is a key task in the analysis of cardiac electrocardiograms (ECG), as many downstream diagnosis tasks are dependent on ECG-based measurements. Those measurements, however, are costly to produce and time-consuming to process in bulk, especially in recordings that change throughout long periods of time. Currently, ECG delineation is performed either using digital signal processing (DSP), which are able to produce high-quality delineations but are difficult to generalize, and machine learning (ML), which commonly produces increased performance at the cost of needing large databases of annotated data. However, the existing annotated databases for ECG delineation are small, being insufficient in size and in the array of pathological conditions they represent. This article delves into the latter with two main contributions. First, a pseudo-synthetic data generation scheme was developed, based in probabilistically composing unseen ECG traces given "pools" of fundamental segments cropped from the original databases and a set of rules for their arrangement into coherent synthetic traces. The generation of conditions is controlled by imposing expert knowledge on the generated trace, which increases the input variability for training the model. Second, two novel segmentation-based loss functions have been developed, which attempt at enforcing the prediction of an exact number of independent structures and at producing closer segmentation boundaries by focusing on a reduced number of samples. The best performing model obtained an F 1 -score of 99.38% and a delineation error of 2.19 ± 17.73 ms and 4.45 ± 18.32 ms for all wave's fiducials (onsets and offsets, respectively), as averaged across the P, QRS and T waves for three distinct freely available databases. The excellent results were obtained despite the heterogeneous characteristics of the tested databases, in terms of lead configurations (Holter, 12-lead), sampling frequencies (250, 500 and 2, 000 Hz) and represented pathophysiologies (e.g., different types of arrhythmias, sinus rhythm with structural heart disease), hinting at its generalization capabilities, while outperforming current state-of-the-art delineation approaches.

show abstract

A 12-Lead ECG database to identify origins of idiopathic ventricular arrhythmia containing 334 patients

Cited by 16 publications

References 15 publications

A High-Precision Deep Learning Algorithm to Localize Idiopathic Ventricular Arrhythmias

A High-Precision Deep Learning Algorithm to Localize Idiopathic Ventricular Arrhythmias

A High Precision Machine Learning-Enabled System for Predicting Idiopathic Ventricular Arrhythmia Origins

Generalizing electrocardiogram delineation -- Training convolutional neural networks with synthetic data augmentation

Contact Info

Product

Resources

About