Enhancing Deep Learning-based 3-lead ECG Classification with Heartbeat Counting and Demographic Data Integration
This work addresses the need for accurate and pervasive ECG monitoring using fewer leads for integration into portable or wearable devices, representing a strong specific gain in the domain of medical AI.
The paper tackles the problem of improving 3-lead ECG classification for cardiovascular disease detection by integrating heartbeat counting and demographic data, achieving F1 scores of 0.9796 and 0.8140 on two datasets, surpassing state-of-the-art methods even those using 12-lead data.
Nowadays, 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 the majority of current research. However, using a lower number of 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 CPSC-2018, respectively, which surpassed current state-of-the-art ECG classification methods, even those trained on 12-lead data. To encourage further development, our source code is publicly available at https://github.com/lhkhiem28/LightX3ECG.