AI 中文总结
本研究量化了不同PPG伪影对两种AF检测器（$\boldsymbol{\textit{D}}_{r}$、$\boldsymbol{\textit{D}}_{f}$）不确定性的影响，发现伪影类型和时长的影响具有检测器特异性，设备位移导致不确定性增加最大，共形预测可降低假阳性率。
AI 中文摘要
从光体积描记图（PPG）检测心房颤动（AF）对伪影高度敏感，但不同AF检测器受伪影影响的不确定性却鲜为人知。本研究旨在量化不同PPG伪影类型对AF检测器不确定性的影响。探索了两种AF检测的机器学习方法：一种以25秒PPG信号为输入（$\boldsymbol{\textit{D}}_{r}$），另一种以AF相关节律不规则特征为输入（$\boldsymbol{\textit{D}}_{f}$）。这些检测器在心脏康复期间采集的腕部PPG信号上进行训练，随后在包含受控伪影类型和时长的26万条PPG信号上进行系统评估。采用基于阈值的错误率、共形预测和蒙特卡洛失活（Monte Carlo dropout）对不确定性进行量化。在无伪影的PPG信号中，$\boldsymbol{\textit{D}}_{f}$的灵敏度/特异度为0.94/0.94，优于$\boldsymbol{\textit{D}}_{r}$的0.92/0.86。与无伪影性能相比，$\boldsymbol{\textit{D}}_{r}$在设备位移、前臂运动、手部运动和接触不良这四类12秒伪影下，灵敏度/特异度分别下降0.52/0.03、0.25/0.03、0.16/0.02、0.07/0.02；而$\boldsymbol{\textit{D}}_{f}$在相同伪影下，对应下降值为0.31/0.07、0.19/0.11、0.14/0.15、0.13/0.21。$\boldsymbol{\textit{D}}_{f}$对短伪影更具鲁棒性，但不确定性随伪影时长增加而上升；$\boldsymbol{\textit{D}}_{r}$在出现伪影时性能会突然下降，但对伪影时长的敏感性较低。采用90%覆盖率的共形预测后，$\boldsymbol{\textit{D}}_{r}$的假阳性率最多降低12%，$\boldsymbol{\textit{D}}_{f}$最多降低64%。伪影类型和时长对AF检测不确定性具有检测器特异性影响，其中设备位移导致的不确定性增加最大。
英文摘要
Detection of atrial fibrillation (AF) from photoplethysmogram (PPG) is highly sensitive to artifacts, yet their effect on uncertainty of different AF detectors remains poorly understood. This work aims to quantify how different PPG artifact types affect the uncertainty of AF detectors. Two machine learning approaches to AF detection were explored: one using 25-s PPG signals as input ($\mathit{D}_r$) and another using AF-related rhythm irregularity features ($\mathit{D}_f$). The detectors were trained on wrist PPG signals acquired during cardiac rehabilitation and then systematically evaluated on 260,000 PPG signals containing controlled artifact types and durations. Uncertainty was quantified using a threshold-based error rate, conformal prediction, and Monte Carlo dropout. Using artifact-free PPG signals, $\mathit{D}_f$ outperforms $\mathit{D}_r$ with sensitivity/specificity of 0.94/0.94 versus 0.92/0.86. Relative to artifact-free performance, sensitivity/specificity drops by 0.52/0.03, 0.25/0.03, 0.16/0.02, and 0.07/0.02 using $\mathit{D}_r$ for 12-s artifacts of device displacement, forearm motion, hand motion, and poor contact respectively. For $\mathit{D}_f$, the respective drops are 0.31/0.07, 0.19/0.11, 0.14/0.15, and 0.13/0.21 for the same artifacts. $\mathit{D}_f$ is more robust to short artifacts but exhibits increasing uncertainty with longer artifact durations, whereas $\mathit{D}_r$ shows an abrupt performance drop when artifacts occur but is less sensitive to artifact duration. Applying conformal prediction with 90$\%$ coverage reduces the false-positive rate by up to 12$\%$ for $\mathit{D}_r$ and up to 64$\%$ for $\mathit{D}_f$. Artifact type and duration have detector-specific effects on AF detection uncertainty. Device displacement causes the largest increase in uncertainty.
