Most deep learning models of multiclass arrhythmia classification are tested on fingertip photoplethysmographic (PPG) data, which has higher signal-to-noise ratios compared to smartwatch-derived PPG, and the best reported sensitivity value for premature atrial/ventricular contraction (PAC/PVC) detection is only 75%. To improve upon PAC/PVC detection sensitivity while maintaining high AF detection, we use multi-modal data which incorporates 1D PPG, accelerometers, and heart rate data as the inputs to a computationally efficient 1D bi-directional Gated Recurrent Unit (1D-Bi-GRU) model to detect three arrhythmia classes. We used motion-artifact prone smartwatch PPG data from the NIH-funded Pulsewatch clinical trial. Our multimodal model tested on 72 subjects achieved an unprecedented 83% sensitivity for PAC/PVC detection while maintaining a high accuracy of 97.31% for AF detection. These results outperformed the best state-of-the-art model by 20.81% for PAC/PVC and 2.55% for AF detection even while our model was computationally more efficient (14 times lighter and 2.7 faster).

翻译：目前大多数多类心律失常分类的深度学习模型均在指尖光电容积脉搏波（PPG）数据上进行测试，此类数据相较于智能手表采集的PPG信号具有更高的信噪比，而现有文献报道的房性/室性早搏（PAC/PVC）检测最高灵敏度仅为75%。为在保持高心房颤动（AF）检测性能的同时提升PAC/PVC检测灵敏度，本研究采用融合一维PPG信号、加速度计数据与心率信息的多模态数据作为输入，构建计算高效的二维双向门控循环单元（1D-Bi-GRU）模型以实现三类心律失常的检测。实验数据来源于美国国立卫生研究院资助的Pulsewatch临床试验中易受运动伪影干扰的智能手表PPG数据集。基于72名受试者测试的多模态模型取得了突破性进展：PAC/PVC检测灵敏度达到83%，同时维持97.31%的AF检测准确率。该结果在计算效率显著提升（模型体积缩小14倍、推理速度加快2.7倍）的前提下，PAC/PVC与AF检测性能分别超越现有最优模型20.81%和2.55%。