3 个月前

光电容积脉搏波描记图中的节拍检测:开源算法的基准测试

光电容积脉搏波描记图中的节拍检测:开源算法的基准测试

摘要

光电容积脉搏波(Photoplethysmogram, PPG)信号广泛应用于脉搏血氧仪和智能手表中。在分析PPG信号的过程中,心搏检测是一项基础性步骤。尽管已有多种PPG心搏检测算法被提出,但目前尚不清楚哪种算法表现最优。研究目的:本研究旨在实现以下三个目标:(i)构建一个用于设计与测试PPG心搏检测算法的框架;(ii)评估不同应用场景下PPG心搏检测算法的性能表现;(iii)探究患者人口统计学特征与生理状态对算法性能的影响。研究方法:基于来自八个数据集的PPG与心电图(ECG)同步数据,对15种心搏检测算法进行了评估。采用F1分数作为性能评价指标,该指标综合了敏感性(sensitivity)与阳性预测值(positive predictive value)。主要研究结果:在无运动干扰的情况下,有8种算法表现良好,在医院数据及静息状态下采集的可穿戴设备数据中,F1分数均达到≥90%。然而,在运动状态下,算法性能显著下降,F1分数范围为55%–91%;在新生儿中,算法表现劣于成人,F1分数为84%–96%(新生儿)对比98%–99%(成人);在心房颤动(atrial fibrillation, AF)患者中,F1分数为92%–97%,显著低于正常窦性心律下的99%–100%。研究意义:两种PPG心搏检测算法——“MSPTD”与“qppg”表现最佳,且二者在性能特征上具有互补性。本研究结果可为选择合适的PPG心搏检测算法提供实证依据。所有相关算法、数据集及评估框架均公开免费获取,便于后续研究与应用。

基准测试

基准方法指标
photoplethysmography-ppg-beat-detection-onWFD: Wavelet Foot Delineation
F1 score: 86.5
photoplethysmography-ppg-beat-detection-onATM: Adaptive Threshold Method
F1 score: 71.1
photoplethysmography-ppg-beat-detection-onMSPTD: MultiScale Peak & Trough Detection
F1 score: 97.5
photoplethysmography-ppg-beat-detection-onPulses
F1 score: 96.6
photoplethysmography-ppg-beat-detection-onqppg: Adapted Onset Detector
F1 score: 96.9
photoplethysmography-ppg-beat-detection-onAMPD: Automatic Multiscale Peak Detection
F1 score: 97.2
photoplethysmography-ppg-beat-detection-onPWD: Pulse Wave Delineator
F1 score: 92.9
photoplethysmography-ppg-beat-detection-onERMA: EventRelated Moving Averages
F1 score: 93.6
photoplethysmography-ppg-beat-detection-onIMS: Incremental Merge Segmentation
F1 score: 93.6
photoplethysmography-ppg-beat-detection-onPDA: Peak Detection Algorithm
F1 score: 92.2
photoplethysmography-ppg-beat-detection-onABD: Automatic Beat Detection
F1 score: 96.8
photoplethysmography-ppg-beat-detection-onHeartPy
F1 score: 95.6
photoplethysmography-ppg-beat-detection-onSPAR: Symmetric Projection Attractor Reconstruction
F1 score: 95.3
photoplethysmography-ppg-beat-detection-onSWT: Stationary Wavelet Transform
F1 score: 59.0
photoplethysmography-ppg-beat-detection-onCOppg: Percentile Peak Detector
F1 score: 92.4
photoplethysmography-ppg-heart-ratePWD: Pulse Wave Delineator
MAPE: 8.4
photoplethysmography-ppg-heart-rateSWT: Stationary Wavelet Transform
MAPE: 51.0
photoplethysmography-ppg-heart-rateABD: Automatic Beat Detection
MAPE: 3.3
photoplethysmography-ppg-heart-rateERMA: EventRelated Moving Averages
MAPE: 7.9
photoplethysmography-ppg-heart-rateIMS: Incremental Merge Segmentation
MAPE: 7.7
photoplethysmography-ppg-heart-rateHeartPy
MAPE: 4.9
photoplethysmography-ppg-heart-rateCOppg: Percentile Peak Detector
MAPE: 9.6
photoplethysmography-ppg-heart-ratePDA: Peak Detection Algorithm
MAPE: 7.8
photoplethysmography-ppg-heart-rateMSPTD: MultiScale Peak & Trough Detection
MAPE: 2.4
photoplethysmography-ppg-heart-ratePulses
MAPE: 3.3
photoplethysmography-ppg-heart-rateWFD: Wavelet Foot Delineation
MAPE: 17.5
photoplethysmography-ppg-heart-rateATM: Adaptive Threshold Method
MAPE: 38.5
photoplethysmography-ppg-heart-rateAMPD: Automatic Multiscale Peak Detection
MAPE: 2.9
photoplethysmography-ppg-heart-rateqppg: Adapted Onset Detector
MAPE: 3.5
photoplethysmography-ppg-heart-rateSPAR: Symmetric Projection Attractor Reconstruction
MAPE: 4.6

用 AI 构建 AI

从想法到上线——通过免费 AI 协同编程、开箱即用的环境和市场最优价格的 GPU 加速您的 AI 开发

AI 协同编程
即用型 GPU
最优价格
立即开始

Hyper Newsletters

订阅我们的最新资讯
我们会在北京时间 每周一的上午九点 向您的邮箱投递本周内的最新更新
邮件发送服务由 MailChimp 提供
光电容积脉搏波描记图中的节拍检测:开源算法的基准测试 | 论文 | HyperAI超神经