Cuffless Blood Pressure Estimation Based on Both Artificial and Data-Driven Features from Plethysmography  

作　　者：Huan Li Yue Wang Yunpeng Guo 

机构地区：[1]College of Software Engineering,Sichuan University,Chengdu 610065,China

出　　处：《国际计算机前沿大会会议论文集》2022年第2期159-171,共13页International Conference of Pioneering Computer Scientists, Engineers and Educators（ICPCSEE）

摘　　要：Blood pressure(BP)is an important indicator of individuals’health conditions for the prevention or treatment of cardiovascular disease.However,conventional measurements require inconvenient cuffbased instruments and are not able to detect continuous blood pressure.Advanced methods utilize machine learning to estimate BP by constructing artificial features in plethysmography(PPG)or using an end-to-end deep learning framework to estimate BP directly.Empirical features are limited by current research on cardiovascular disease and are not sufficient to express BP variability,while data-driven approaches neglect expert knowledge and lack interpretability.To address this issue,in this paper we propose a method for continuous BP estimation that extracts both artificial and data-driven features from PPG to take advantage of expert knowledge and deep learning at the same time.Then a deep residual neural network is designed to reduce information redundancy in the gathered features and refine high-level features for BP estimation.The results show that our proposed methods outperforms the compared methods in three commonly used metrics.

关 键 词：Blood pressure estimation PLETHYSMOGRAPHY Artificial features Data-driven features 

分 类 号：TP1[自动化与计算机技术—控制理论与控制工程]