Annu Int Conf IEEE Eng Med Biol Soc. 2021 Nov;2021:5674-5677. doi: 10.1109/EMBC46164.2021.9630554.
Arterial blood pressure (ABP) waveform is a common physiological signal that contains a wealth of cardiovascular information. According to the cardiac cycle, the ABP waveform is divided into rapid ejection, systolic and diastolic phases. Therefore, the characteristic points of the arterial blood pressure waveform, i.e. their onsets, systolic peaks, represent the timing of the minimum and maximum pressures. It is important to detect these characteristic points accurately. Recently, many researchers have introduced some feature points detection methods, but the accuracy is not particularly high. In this paper, a deep learning method is proposed to achieve periodic segmentation and feature points detection of ABP signals using a one-dimensional U-Net network. The network can split the ABP signal into two parts and accurately detect the feature points. The method is validated on an ABP dataset of 126 people, 500 people each. Performances are good at different tolerance thresholds, with an average time difference of less than 1.5 ms. Finally, the method performs with 99.79% and 99.79% sensitivity, 99.99% and 99.94% positive predictivity, and 0.23% and 0.27% error rates for both onsets and systolic peaks at a tolerance threshold of 30 ms. To our knowledge, this is the first paper to use deep learning methods for the onsets and systolic peaks detections of ABP signals.
动脉血压（ABP）波形是一种常见的生理信号，包含丰富的心血管信息。根据心动周期，ABP 波形分为快速射血、收缩和舒张期。因此，动脉血压波形的特征点，即它们的起点、收缩峰，代表着最小和最大压力的时间。准确检测这些特征点非常重要。最近，许多研究人员引入了一些特征点检测方法，但准确性不是特别高。在本文中，提出了一种深度学习方法，使用一维 U-Net 网络对 ABP 信号进行周期性分段和特征点检测。该网络可以将 ABP 信号分为两部分，并准确地检测特征点。该方法在 126 人的 ABP 数据集和 500 人的 ABP 数据集上进行了验证。在不同的容限阈值下表现良好，平均时间差小于 1.5ms。最后，在容限阈值为 30ms 时，该方法对起点和收缩峰的灵敏度分别为 99.79%和 99.99%，阳性预测值分别为 99.79%和 99.94%，误报率分别为 0.23%和 0.27%。据我们所知，这是第一篇使用深度学习方法检测 ABP 信号起点和收缩峰的论文。
