Physics-informed neural networks for modeling physiological time series for cuffless blood pressure estimation.

Physics-informed neural networks for modeling physiological time series for cuffless blood pressure estimation.
复制标题

DOI:
10.1038/s41746-023-00853-4
复制
发表时间:
2023-06-09
影响因子:
15.2
通讯作者:
--
中科院分区:
医学1区
文献类型:
--
作者:

文献摘要

参考文献

相似文献

通过十年前开始的现成可穿戴设备的激增,人工智能驱动的普遍生理监测的大胆愿景为精确医疗提取可操作信息创造了巨大的机会。这些人工智能算法对系统的输入输出关系进行建模,在许多情况下,这些系统表现出复杂的性质和个性化要求。一个特别的例子是使用可穿戴生物阻抗进行无袖带血压估计。然而,这些算法需要在大量的真实数据上进行训练。在生物医学应用的背景下,收集地面真实数据,特别是在个性化层面上,是具有挑战性的,繁重的,在某些情况下是不可行的。我们的目标是建立生理时间序列数据的物理信息神经网络(PINN)模型,该模型将使用最小的基础真值信息来提取复杂的心血管信息。我们通过建立泰勒近似来逐渐改变输入和输出之间已知的心血管关系(例如,传感器测量血压),并将此近似纳入我们提出的神经网络训练中,从而实现这一目标。通过一个基于时间序列生物阻抗数据的连续无截断BP估计实例,验证了该框架的有效性。我们表明,通过在相同数据集上测试的最先进的时间序列模型上使用pinn,我们保持了高相关性(收缩压:0.90,舒张压:0.89)和低误差(收缩压:1.3±7.6 mmHg,舒张压:0.6±6.4 mmHg),同时平均减少了15倍的真实训练数据量。这可能有助于开发未来的人工智能算法,以帮助使用最少的训练数据来解释普遍的生理数据。
The bold vision of AI-driven pervasive physiological monitoring, through the proliferation of off-the-shelf wearables that began a decade ago, has created immense opportunities to extract actionable information for precision medicine. These AI algorithms model input-output relationships of a system that, in many cases, exhibits complex nature and personalization requirements. A particular example is cuffless blood pressure estimation using wearable bioimpedance. However, these algorithms need training over significant amount of ground truth data. In the context of biomedical applications, collecting ground truth data, particularly at the personalized level is challenging, burdensome, and in some cases infeasible. Our objective is to establish physics-informed neural network (PINN) models for physiological time series data that would use minimal ground truth information to extract complex cardiovascular information. We achieve this by building Taylor’s approximation for gradually changing known cardiovascular relationships between input and output (e.g., sensor measurements to blood pressure) and incorporating this approximation into our proposed neural network training. The effectiveness of the framework is demonstrated through a case study: continuous cuffless BP estimation from time series bioimpedance data. We show that by using PINNs over the state-of-the-art time series models tested on the same datasets, we retain high correlations (systolic: 0.90, diastolic: 0.89) and low error (systolic: 1.3 ± 7.6 mmHg, diastolic: 0.6 ± 6.4 mmHg) while reducing the amount of ground truth training data on average by a factor of 15. This could be helpful in developing future AI algorithms to help interpret pervasive physiologic data using minimal amount of training data.
DOI: 10.1038/s41597-023-02020-6
发表时间: 2023-03-21
期刊: SCIENTIFIC DATA
影响因子: 9.8
作者:
Gonzalez, Sergio;Hsieh, Wan-Ting;Chen, Trista Pei-Chun
通讯作者: Chen, Trista Pei-Chun
DOI: 10.1097/cce.0000000000000624
发表时间: 2022-03
影响因子: --
作者:
Dvir A;Goldstein N;Rapoport A;Balmor RG;Nachman D;Merin R;Fons M;Ben Ishay A;Eisenkraft A
通讯作者: Eisenkraft A
DOI: 10.1093/brain/awab439
发表时间: 2022-04-18
期刊: Brain : a journal of neurology
影响因子: --
作者:
通讯作者: --
DOI: 10.1109/tbme.2013.2291385
发表时间: 2014-03
期刊: IEEE transactions on bio-medical engineering
影响因子: --
作者:
Mingwu Gao;Guanqun Zhang;Olivier NB;Mukkamala R
通讯作者: Mukkamala R
DOI: 10.1007/s10618-020-00701-z
发表时间: 2020-07-13
影响因子: 4.8
作者:
Dempster, Angus;Petitjean, Francois;Webb, Geoffrey, I
通讯作者: Webb, Geoffrey, I