Dias Felipe M, Cardenas Diego A C, Toledo Marcelo A F, Oliveira Filipe A C, Ribeiro Estela, Krieger Jose E, Gutierrez Marco A
Heart Institute (InCor), Clinics Hospital University of Sao Paulo Medical School, Brazil.
Polytechnique School (POLI-USP), University of Sao Paulo, Brazil.
Physiol Meas. 2025 Apr 22;46(4). doi: 10.1088/1361-6579/adcb86.
Hypertension, a leading contributor to cardiovascular morbidity, underscores the need for accurate and continuous blood pressure (BP) monitoring. Photoplethysmography (PPG) emerges as a promising approach for continuous BP monitoring. However, the precision of BP estimates derived from PPG signals has been the subject of ongoing debate, requiring a comprehensive evaluation of their efficacy. This paper aims to provide the potentials and limitations regarding BP estimation from single-site PPG signals.We developed a calibration-based Siamese ResNet model for BP estimation. We compared the use of normalized PPG (N-PPG) against the normalized invasive arterial BP (N-IABP) signals as input. N-IABP signals, while not directly presenting systolic (SBP) and diastolic (DBP) BP values, are expected to offer more precise estimations than PPG since it is a direct pressure sensor inside the body. Thus, if N-IABP poses challenges in BP estimation, predicting BP from PPG signals might be even more challenging.Our evaluation, conducted using the AAMI and BHS standards on the VitalDB dataset, revealed that inference using N-IABP signals meet with AAMI standards for both SBP and DBP, with errors of1.29±6.33mmHg for systolic pressure and1.17±5.78for diastolic pressure. In contrast, N-PPG based inference exhibited inferior performance than N-IABP, presenting1.49±11.82mmHg and0.89±7.27mmHg for systolic and diastolic pressure respectively in their best setup.Our findings establish a critical benchmark for PPG performance, providing realistic expectations for its BP estimation capabilities. We concluded that while PPG signals contain BP-correlated information, they may not suffice for accurate prediction.
高血压是心血管疾病发病的主要因素，这凸显了准确且持续监测血压（BP）的必要性。光电容积脉搏波描记法（PPG）成为持续血压监测的一种有前景的方法。然而，从PPG信号得出的血压估计精度一直是持续争论的主题，需要对其有效性进行全面评估。本文旨在提供关于从单部位PPG信号估计血压的潜力和局限性。我们开发了一种基于校准的连体残差网络模型用于血压估计。我们比较了将归一化PPG（N-PPG）与归一化有创动脉血压（N-IABP）信号作为输入的情况。N-IABP信号虽然不直接呈现收缩压（SBP）和舒张压（DBP）值，但由于它是体内的直接压力传感器，预计比PPG能提供更精确的估计。因此，如果N-IABP在血压估计中存在挑战，从PPG信号预测血压可能更具挑战性。我们使用AAMI和BHS标准在VitalDB数据集上进行的评估表明，使用N-IABP信号进行推理符合AAMI关于SBP和DBP的标准，收缩压误差为1.29±6.33mmHg，舒张压误差为1.17±5.78。相比之下，基于N-PPG的推理表现不如N-IABP，在其最佳设置下，收缩压和舒张压分别为1.49±11.82mmHg和0.89±7.27mmHg。我们的研究结果为PPG性能建立了一个关键基准，对其血压估计能力提供了现实的期望。我们得出结论，虽然PPG信号包含与血压相关的信息，但它们可能不足以进行准确预测。
