Enhancing Deep Learning-based 3-lead ECG Classification with Heartbeat Counting and Demographic Data Integration

Q: What is the clinical evidence from this study?

Study design: Other. Population: Cardiovascular diseases. Intervention: Deep learning system for 3-lead ECG classification with heartbeat counting and demographic data integration vs. Current state-of-the-art ECG classification methods (including 12-lead models). Primary outcome: Classification performance (F1 score).

Key Result

A novel deep learning system for 3-lead ECG classification integrating heartbeat counting and demographic data achieved F1 scores of 0.9796 and 0.8140 on the Chapman and CPSC2018 datasets.

Structured PICO

Does a deep learning system with heartbeat counting and demographic data integration improve 3-lead ECG classification performance compared to state-of-the-art methods?

Population

Two large-scale ECG datasets (Chapman and CPSC2018)

Intervention

Deep learning system for 3-lead ECG classification using multi-task learning (heartbeat counting regression) and demographic data integration

Comparator

Current state-of-the-art ECG classification methods, including models trained on standard 12-lead ECG

Outcome

Classification performance measured by F1 scoresurrogate

Integrating heartbeat counting and demographic data into a deep learning model for 3-lead ECGs achieves classification performance comparable to or better than standard 12-lead ECG models, potentially enhancing the utility of portable ECG devices.

Abstract

An increasing number of people are being diagnosed with cardiovascular diseases (CVDs), the leading cause of death globally. The gold standard for identifying these heart problems is via electrocardiogram (ECG). The standard 12-lead ECG is widely used in clinical practice and most of the current research. However, using fewer leads can make ECG more pervasive as it can be integrated with portable or wearable devices. This article introduces two novel techniques to improve the performance of the current deep learning system for 3-lead ECG classification, making it comparable with models that are trained using standard 12-lead ECG. Specifically, we propose a multi-task learning scheme in the form of the number of heartbeats regression and an effective mechanism to integrate patient demographic data into the system. With these two advancements, we got classification performance in terms of F1 scores of 0.9796 and 0.8140 on two large-scale ECG datasets, i.e., Chapman and CPSC2018, respectively, which surpassed current state-of-the-art ECG classification methods, even those trained on 12-lead data. Our source code is available at github.com/lhkhiem28/LightX3ECG.

Bookmark

Cite This Study

Le et al. (Wed,) conducted a other in Cardiovascular diseases. Deep learning system for 3-lead ECG classification with heartbeat counting and demographic data integration vs. Current state-of-the-art ECG classification methods (including 12-lead models) was evaluated on Classification performance (F1 score). A novel deep learning system for 3-lead ECG classification integrating heartbeat counting and demographic data achieved F1 scores of 0.9796 and 0.8140 on the Chapman and CPSC2018 datasets.

synapsesocial.com/papers/6a1fd9b2d07b6822bbba5357 https://doi.org/https://doi.org/10.1109/iecbes54088.2022.10079267

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: