Suppr超能文献

BP-diff:一种基于 U-Net 的无袖带连续血压波形估计条件扩散模型。

BP-diff: a conditional diffusion model for cuffless continuous BP waveform estimation using U-Net.

机构信息

Department of School of Electronic Engineering, Beijing University of Posts and Telecommunication, Beijing 100876, People's Republic of China.

School of Physics and Electronic Information, Anhui Normal University, Wuhu 241003, People's Republic of China.

出版信息

Physiol Meas. 2024 Oct 14;45(10). doi: 10.1088/1361-6579/ad7fcc.

Abstract

Continuous monitoring of blood pressure (BP) is crucial for daily healthcare. Although invasive methods provide accurate continuous BP measurements, they are not suitable for routine use. Photoplethysmography (PPG), a non-invasive technique that detects changes in blood volume within the microcirculation using light, shows promise for BP measurement. The primary goal of this study is to develop a novel cuffless method based on PPG for accurately estimating continuous BP.We introduce BP-Diff, an end-to-end method for cuffless continuous BP waveform estimation utilizing a conditional diffusion probability model combined with a U-Net architecture. This approach takes advantage of the stochastic properties of diffusion models and the strong feature representation capabilities of U-Net. It integrates the continuous BP waveform as the initial status and uses the PPG signal and its derivatives as conditions to guide the training and sampling process.BP-Diff was evaluated using both uncalibrated and calibrated schemes. The results indicate that, when uncalibrated, BP-Diff can accurately track BP dynamics, including peak and valley positions, as well as timing. After calibration, BP-Diff achieved highly accurate BP estimations. The mean absolute error of the estimated BP waveforms, along with the systolic BP, diastolic BP, and mean arterial pressure from the calibrated BP-Diff model, were 2.99 mmHg, 2.6 mmHg, 1.4 mmHg, and 1.44 mmHg, respectively. Consistency tests, including Bland-Altman analysis and Pearson correlation, confirmed its high reliability compared to reference BP. BP-Diff meets the American Association for Medical Instrumentation standards and has achieved a Grade A from the British Hypertension Society.This study utilizes PPG signals to develop a novel cuffless continuous BP measurement method, demonstrating superiority over existing approaches. The method is suitable for integration into wearable devices, providing a practical solution for continuous BP monitoring in everyday healthcare.

摘要

连续监测血压(BP)对于日常保健至关重要。尽管有创方法可以提供准确的连续 BP 测量,但它们不适合常规使用。光电容积脉搏波描记法(PPG)是一种非侵入性技术,它使用光检测微循环内的血液体积变化,有望用于 BP 测量。本研究的主要目标是开发一种基于 PPG 的新无袖带方法,用于准确估计连续 BP。

我们引入了 BP-Diff,这是一种基于条件扩散概率模型结合 U-Net 架构的无袖带连续 BP 波估计的端到端方法。该方法利用扩散模型的随机特性和 U-Net 的强大特征表示能力。它将连续 BP 波形作为初始状态,并使用 PPG 信号及其导数作为条件来指导训练和采样过程。

BP-Diff 使用未校准和校准方案进行了评估。结果表明,在未校准的情况下,BP-Diff 可以准确跟踪 BP 动态,包括峰值和谷值位置以及时间。校准后,BP-Diff 实现了高度准确的 BP 估计。从校准的 BP-Diff 模型中,估计的 BP 波形的平均绝对误差以及收缩压、舒张压和平均动脉压分别为 2.99mmHg、2.6mmHg、1.4mmHg 和 1.44mmHg。一致性测试,包括 Bland-Altman 分析和 Pearson 相关,证实与参考 BP 相比,其具有高度可靠性。BP-Diff 符合美国医疗器械协会标准,并获得英国高血压学会的 A 级评定。

本研究利用 PPG 信号开发了一种新的无袖带连续 BP 测量方法,与现有方法相比具有优势。该方法适合集成到可穿戴设备中,为日常保健中的连续 BP 监测提供了实用的解决方案。

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验