Key result
The loss-modified YOLOv8 model achieved an average accuracy of 99.5% and 0.992 mAP@50 for real-time arrhythmia detection, with a rapid detection time of 0.002 seconds.
Why the study?
Remote monitoring of cardiovascular health is increasingly needed to reduce healthcare expenses, requiring accurate real-time detection and classification of cardiac arrhythmias from home ECG measurements.
Does a loss-modified YOLOv8n model accurately detect and classify cardiac arrhythmias in real-time from single-lead ECG signals?
Does a loss-modified YOLOv8n model accurately detect and classify cardiac arrhythmias in real-time from single-lead ECG signals?
A novel loss-modified YOLOv8 model demonstrates high accuracy and rapid detection speeds for real-time ECG arrhythmia classification, showing potential for home-based monitoring.
Hypothesis-generating for home real-time arrhythmia detection; leaves open prospective clinical validation.
In a landscape characterized by heightened connectivity and mobility, coupled with a surge in cardiovascular ailments, the imperative to curtail healthcare expenses through remote monitoring of cardiovascular health has become more pronounced. The accurate detection and classification of cardiac arrhythmias are pivotal for diagnosing individuals with heart irregularities. This study underscores the feasibility of employing electrocardiograms (ECG) measurements in the home environment for real-time arrhythmia detection. Presenting a fresh application for arrhythmia detection, this paper leverages the cutting-edge You-Only-Look-Once (YOLO)v8 algorithm to categorize single-lead ECG signals. We introduce a novel loss-modified YOLOv8 model, fine-tuned on the MIT-BIH arrhythmia dataset, enabling real-time continuous monitoring. The obtained results substantiate the efficacy of our approach, with the model attaining an average accuracy of 99.5% and 0.992 mAP@50, and a rapid detection time of 0.002 seconds on an NVIDIA Tesla V100. Our investigation exemplifies the potential of real-time arrhythmia detection, enabling users to visually interpret the model output within the comfort of their homes. Furthermore, this study lays the groundwork for an extension into a real-time explainable AI (XAI) model capable of deployment in the healthcare sector, thereby significantly advancing the realm of healthcare solutions.
No takes yet. Share an insight, caveat, or question.
Guang Jun Nicholas Ang (2023) studied Cardiac arrhythmia. YOLOv8 algorithm with dynamic inverse-class frequency and Wise IoU vs. Standard YOLOv8n and other state-of-the-art models was evaluated on Mean average precision (mAP@50) and classification accuracy. The loss-modified YOLOv8 model achieved an average accuracy of 99.5% and 0.992 mAP@50 for real-time arrhythmia detection, with a rapid detection time of 0.002 seconds.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: