ArrhythmiaVision：面向ECG心律失常分类的具有视觉解释的资源节约型深度学习模型
ArrhythmiaVision: Resource-Conscious Deep Learning Models with Visual Explanations for ECG Arrhythmia Classification
AI总结：
本文提出两种轻量级一维卷积神经网络ArrhythmiNet V1和V2，以极小内存占用在MIT-BIH数据集上实现高精度五类心律失常分类，并结合SHAP与Grad-CAM提供可解释性，验证了在边缘设备上兼顾准确率、效率与临床透明性的可行性。
摘要：
心律失常是危及生命的心脏事件的主要原因，凸显了对准确、及时检测的迫切需求。心电图（ECG）仍然是心律失常诊断的临床金标准；然而，人工判读耗时、依赖临床专业知识且容易出现人为错误。尽管深度学习推动了自动化ECG分析的发展，但许多现有模型抽象掉了信号固有的时间与形态特征，缺乏可解释性，并且计算密集，阻碍了它们在资源受限平台上的部署。在本工作中，我们提出了两种新颖的轻量级一维卷积神经网络——ArrhythmiNet V1和V2，它们针对边缘设备上高效、实时的ECG心律失常分类进行了优化。受MobileNet深度可分离卷积设计的启发，这些模型的内存占用分别仅为302.18 KB和157.76 KB，同时在MIT-BIH心律失常数据集上对五类——正常窦性心律、左束支传导阻滞、右束支传导阻滞、房性早搏和室性早搏——分别取得了0.99（V1）和0.98（V2）的分类准确率。为确保临床透明度和相关性，我们集成了Shapley加性解释和梯度加权类激活映射，从而同时支持局部和全局可解释性。这些技术突出显示了具有生理意义的模式，例如对模型预测有贡献的QRS波群和T波。我们还讨论了性能与效率之间的权衡，并解决了当前在数据集多样性和泛化能力方面的局限性。总体而言，我们的研究结果证明了在实际可穿戴和嵌入式ECG监测系统中结合可解释性、预测准确性和计算效率的可行性。
英文摘要：
Cardiac arrhythmias are a leading cause of life-threatening cardiac events, highlighting the urgent need for accurate and timely detection. Electrocardiography (ECG) remains the clinical gold standard for arrhythmia diagnosis; however, manual interpretation is time-consuming, dependent on clinical expertise, and prone to human error. Although deep learning has advanced automated ECG analysis, many existing models abstract away the signal's intrinsic temporal and morphological features, lack interpretability, and are computationally intensive-hindering their deployment on resource-constrained platforms. In this work, we propose two novel lightweight 1D convolutional neural networks, ArrhythmiNet V1 and V2, optimized for efficient, real-time arrhythmia classification on edge devices. Inspired by MobileNet's depthwise separable convolutional design, these models maintain memory footprints of just 302.18 KB and 157.76 KB, respectively, while achieving classification accuracies of 0.99 (V1) and 0.98 (V2) on the MIT-BIH Arrhythmia Dataset across five classes: Normal Sinus Rhythm, Left Bundle Branch Block, Right Bundle Branch Block, Atrial Premature Contraction, and Premature Ventricular Contraction. In order to ensure clinical transparency and relevance, we integrate Shapley Additive Explanations and Gradient-weighted Class Activation Mapping, enabling both local and global interpretability. These techniques highlight physiologically meaningful patterns such as the QRS complex and T-wave that contribute to the model's predictions. We also discuss performance-efficiency trade-offs and address current limitations related to dataset diversity and generalizability. Overall, our findings demonstrate the feasibility of combining interpretability, predictive accuracy, and computational efficiency in practical, wearable, and embedded ECG monitoring systems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
