In recent years, there has been an increasing need to reduce healthcare costs
in remote monitoring of cardiovascular health. Detecting and classifying
cardiac arrhythmia is critical to diagnosing patients with cardiac
abnormalities. This paper shows that complex systems such as electrocardiograms
(ECG) can be applicable for at-home monitoring. This paper proposes a novel
application for arrhythmia detection using the state-of-the-art
You-Only-Look-Once (YOLO)v8 algorithm to classify single-lead ECG signals. A
custom YOLOv8 model was fine-tuned on the MIT-BIH dataset to detect arrhythmia
in real-time to allow continuous monitoring. Results show that our model can
detect heartbeats with a mAP@50 of 0.961 with a detection time of 0.002s on an
NVIDIA Tesla V100. Our study demonstrated the potential of real-time arrhythmia
detection, where the model output can be visually interpreted for at-home
users. Furthermore, this study could be extended into a real-time XAI model,
deployed in the healthcare industry, and significantly advancing healthcare
needs.

本论文提出一种基于 YOLOv8 算法的心律失常检测应用，通过在 MIT-BIH 数据集上的 fine-tuning，实现对单导联 ECG 信号的实时检测，可持续监测，检测时间为 0.002 秒，mAP@50 达到 0.961，能够为家庭用户提供直观的模型输出，实现了实时心律失常检测，具有推广至医疗行业的潜力。

使用 YOLOv8 进行实时心律失常检测的新应用

A novel application for real-time arrhythmia detection using YOLOv8

The performance of cardiac arrhythmia detection with electrocardiograms(ECGs)
has been considerably improved since the introduction of deep learning models.
In practice, the high performance alone is not sufficient and a proper
explanation is also required. Recently, researchers have started adopting
feature attribution methods to address this requirement, but it has been
unclear which of the methods are appropriate for ECG. In this work, we identify
and customize three evaluation metrics for feature attribution methods based on
the characteristics of ECG: localization score, pointing game, and degradation
score. Using the three evaluation metrics, we evaluate and analyze eleven
widely-used feature attribution methods. We find that some of the feature
attribution methods are much more adequate for explaining ECG, where Grad-CAM
outperforms the second-best method by a large margin.

通过评估 11 种特征归因方法的三个评估指标，即定位分数、指向游戏和退化得分，我们发现 Grad-CAM 这种方法非常适用于解释心电图 (ECG) 检测，并且比第二优秀的方法表现更加卓越。