计算机科学

计算机科学 ›› 2026, Vol. 53 ›› Issue (7): 262-271.doi: 10.11896/jsjkx.250400022

• 数据库 & 大数据 & 数据科学 • 上一篇    下一篇

基于新型多层次心冲击图信号特征集的高血压识别与血压预测

张宇辰1, 叶涵宇2, 姚语涵3, 姜锐1, 杨刚4, 张先超5   

  1. 1 浙江工业大学计算机科学与技术学院 杭州 310023
    2 浙江工业大学机械工程学院 杭州 310023
    3 浙江工业大学信息工程学院 杭州 310023
    4 西安电子科技大学超高速电路设计与电磁兼容教育部重点实验室 西安 710071
    5 嘉兴大学生命健康智能感知浙江省工程研究中心 浙江 嘉兴 314001
  • 收稿日期:2025-04-07 修回日期:2025-07-26 出版日期:2026-07-15 发布日期:2026-07-10
  • 通讯作者: 张先超(zhangxianchao@zjxu.edu.cn)
  • 作者简介:(yuczhang9@zjut.edu.cn)
  • 基金资助:
    国家自然科学基金面上项目(62472386);浙江省自然科学基金重大项目(LD24F020009)

Hypertension Recognition and Blood Pressure Prediction Based on Novel Hierarchical Ballistocar-diogram Signal Feature Set

ZHANG Yuchen1, YE Hanyu2, YAO Yuhan3, JIANG Rui1, YANG Gang4, ZHANG Xianchao5   

  1. 1 College of Computer Science and Technology,Zhejiang University of Technology,Hangzhou 310023,China
    2 College of Mechanical Engineering,Zhejiang University of Technology,Hangzhou 310023,China
    3 College of Information Engineering,Zhejiang University of Technology,Hangzhou 310023,China
    4 Key Laboratory of High Speed Circuit Design and EMC Ministry of Education,Xidian University,Xi'an 710071,China
    5 Engineering Research Center of Intelligent Human Health Situation Awareness of Zhejiang Province,Jiaxing University,Jiaxing,Zhejiang 314001,China
  • Received:2025-04-07 Revised:2025-07-26 Published:2026-07-15 Online:2026-07-10
  • About author:ZHANG Yuchen,born in 1989,Ph.D,lecturer,is a member of CCF(No.K8064M).His main research interests include biomedical informatics,biomedi-cal signal processing,and artificial in-telligence theory and applications.
    ZHANG Xianchao,born in 1984,Ph.D,professor,Ph.D supervisor.His main research interests include digital health,integrated information networks,and intelligent perception and control.
  • Supported by:
    General Projects of the National Natural Science Foundation of China(62472386) and Key Program of the Natural Science Foundation of Zhejiang Province,China(LD24F020009).

PDF (PC)

10

摘要： 高血压的早期精准识别对于防止病情进一步恶化至关重要。心冲击图(Ballistocardiogram,BCG)信号是心脏质心随血流动态变化在正常呼吸和心脏周期中运动的综合反映,可以较精确地反映血压的变化。然而,现有基于BCG信号的高血压识别方法通常仅使用时频域或非线性域等传统手段提取有限特征,难以全面刻画与血压相关的信号模式,且多数仅能判断是否患病,无法预测具体血压值。为此,提出通过提取BCG信号时频域特征、非线性域特征、波动特征,特别是波形特征,构建新型多层次BCG信号特征集。采用多种经典的机器学习,如随机森林(Random Forest,RF),以及主流深度学习模型,如卷积神经网络(Convolutional Neural Network,CNN)、深度神经网络(Deep Neural Network,DNN)进行对比分析。结果表明,使用所提出的新型多层次BCG信号特征集进行高血压识别时,RF模型的准确率达到82.26%,CNN模型则达到83.57%。与Liu等的特征集在相同模型的识别结果(准确率分别为77.92%和78.2%)相比,有显著提升。血压值预测结果显示,DNN回归模型对舒张压的均方根误差(Root Mean Square Error,RMSE)为6.59,对收缩压的RMSE为3.99,均优于使用Liu等的特征集的结果。另外,还进行了BCG信号段长度对血压分析性能影响的验证。这些结果表明,所提出的特征工程方法可以更精准地捕捉与血压分析相关的BCG信号模式,具备从计算层面赋能更方便准确地无创无袖带血压监测的潜力。

关键词: 心冲击信号, 特征工程, 高血压识别, 血压预测, 机器学习

Abstract: Accurate early identification of hypertension is crucial for preventing further progression of the disease.Ballistocardiogram(BCG) signals,which reflect the dynamic movement of the heart's center of mass due to blood flow during normal respiration and cardiac cycles,can precisely capture blood pressure(BP) variations.However,most existing BCG-based hypertension identification methods primarily rely on traditional analyses(e.g.,time-frequency or nonlinear domain techniques) to extract limi-ted features,which fail to comprehensively characterize BP-related signal patterns.In addition,most BCG-based studies focus on diagnosing hypertension rather than predicting precise BP values.To address these limitations,this paper proposes a novel multi-level BCG feature set incorporating time-frequency domain features,nonlinear domain features,fluctuation characteristics,and waveform features.Comparative analyses are conducted using classical machine learning models,such as random forest(RF),and mainstream deep learning architectures such as convolutional neural network(CNN) and deep neural network(DNN).The results demonstrate that the proposed feature set significantly improves hypertension identification:the RF model achieves an accuracy of 82.26%,and the CNN model reaches 83.57%,outperforming Liu et al.'s feature set(accuracy of 77.92% and 78.2%,respectively).For BP prediction,the DNN regression model achieves a root mean square error(RMSE) of 6.59 mmHg for diastolic blood pressure(DBP) and 3.99 mmHg for systolic blood pressure(SBP),both superior to results using Liu et al.'s feature set.Additionally,this study validates the impact of the BCG signal's segment length on the performance of BP analysis.These fin-dings highlight that the proposed feature engineering approach effectively captures BCG signal patterns critical for BP analysis,demonstrating the potential to computationally enable more convenient and accurate non-invasive,cuffless BP monitoring.

Key words: Ballistocardiogram signal, Feature engineering, Hypertension identification, Blood pressure prediction, Machine lear-ning

中图分类号: 

  • TP18
[1]JAIN P,GAJBHIYE P,TRIPATHY R K,et al.A two-stagedeep CNN architecture for the classification of low-risk and high-risk hypertension classes using multi-lead ECG signals [J].Informatics in Medicine Unlocked,2020,21:100479.
[2]RAJPUT J S,SHARMA M,ACHARYA U R.Hypertension Diagnosis Index for Discrimination of High-Risk Hypertension ECG Signals Using Optimal Orthogonal Wavelet Filter Bank [J].International Journal of Environmental Research and Public Health,2019,16(21):4068.
[3]RAJPUT J S,SHARMA M,TAN R S,et al.Automated detection of severity of hypertension ECG signals using an optimal bi-orthogonal wavelet filter bank [J].Computers in Biology and Medicine,2020,123:103924.
[4]SHARMA M,RAJPUT J S,TAN R S,et al.Automated Detection of Hypertension Using Physiological Signals:A Review [J].International Journal of Environmental Research and Public Health,2021,18(11):5838.
[5]SOH D C K,NG E Y K,JAHMUNAH V,et al.Automateddiagnostic tool for hypertension using convolutional neural network [J].Computers in Biology and Medicine,2020,126:103999.
[6]SHARMA M,DARJI J,THAKRAR M,et al.Automated identification of sleep disorders using wavelet-based features extracted from electrooculogram and electromyogram signals [J].Computers in Biology and Medicine,2022,143:105224.
[7]World Health Organization.Global report on hypertension:therace against a silent killer[M].Geneva:World Health Organization,2023.
[8]SUN L,DING G,QIU Y,et al.TransFusionOdom:Interpretable Transformer-based LiDAR-Inertial Fusion Odometry Estimation [J].arXiv:2304.07728,2023.
[9]ANDREOZZI E,GARGIULO G D,ESPOSITO D,et al.A Novel Broadband Forcecardiography Sensor for Simultaneous Monitoring of Respiration,Infrasonic Cardiac Vibrations and Heart Sounds [J].Frontiers in Physiology,2021,12:725716.
[10]DEHKORDI P,TAVAKOLIAN K,TADI M J,et al.Investigating the estimation of cardiac time intervals using gyrocardiography [J].Physiological Measurement,2020,41(5):055004.
[11]SIECINSKI S,KOSTKA P S,TKACZ E J.Gyrocardiography:A Review of the Definition,History,Waveform Description,and Applications [J].Sensors,2020,20(22):6675.
[12]RAJPUT J S,SHARMA M,KUMBHANI D,et al.Automated detection of hypertension using wavelet transform and nonlinear techniques with ballistocardiogram signals [J].Informatics in Medicine Unlocked,2021,26:100736.
[13]CUI Z Q,XING X M.The research and progress of ballistocardiogram-based blood pressure monitoring technology[J].Yixue Xinzhi Zazhi,2021,31(2):145-154.
[14]LIU F,ZHOU X,WANG Z,et al.Unobtrusive Mattress-Based Identification of Hypertension by Integrating Classification and Association Rule Mining [J].Sensors,2019,19(7):1489.
[15]SADEK I,BISWAS J,ABDULRAZAK B.Ballistocardiogramsignal processing:a review [J].Health Information Science and Systems,2019,7(1):10.
[16]JIANG W J,CAO X S.Current state of ballistocardiogram development and its application prospects in aerospace medicine[J].Chinese Heart Journal,2025,37(1):68-72.
[17]KIM C S,CAREK A M,INAN O T,et al.Ballistocardiogram-Based Approach to Cuffless Blood Pressure Monitoring:Proof of Concept and Potential Challenge [J].IEEE Transactions on Biomedical Engineering,2018,65(11):2384-2391.
[18]NI H,CHO S,MANKOFF J,et al.Automated recognition ofhypertension through overnight continuous HRV monitoring [J].Journal of Ambient Intelligence and Humanized Computing,2018,9(6):2011-2023.
[19]CARLSON C,TURPIN V,SULIMAN A,et al.Bed-Based Ballistocardiography:Dataset and Ability to Track Cardiovascular Parameters [J].Sensors,2021,21(1):156.
[20]LIU F,ZHOU X,WANG Z,et al.OSA-weigher:an automated computational framework for identifying obstructive sleep apnea based on event phase segmentation [J].Journal of Ambient Intelligence and Humanized Computing,2019,10(5):1937-1954.
[21]TERATHONGKUM S,PICKLER R H.Relationships amongheart rate variability,hypertension,and relaxation techniques [J].Journal of Vascular Nursing,2004,22(3):78-82.
[22]LIU F,ZHOU X,WANG Z,et al.Identifying Obstructive Sleep Apnea by Exploiting Fine-grained BCG Features Based on Event Phase Segmentation [C]//Proceedings of the 2016 IEEE 16th International Conference on Bioinformatics and Bioengineering(BIBE).2016:293-300.
[23]SHAFFER F,GINSBERG J P.An overview of heart rate variability metrics and norms [J].Front Public Health,2017,5:258.
[24]ZHANG X D,ZHANG Y H.Frequency-domain characteristics response to passive exercise in patients with coronary artery disease [J].Frontiers in Cardiovascular Medicine,2021,8:760320.
[25]ZILLNER L,ANDREAS M,MACH M J M.Wearable heartrate variability and atrial fibrillation monitoring to improve cli-nically relevant endpoints in cardiac surgery－a systematic review [J].mHealth,2023,10:8.
[26]NI H,CHO S,MANKOFF J,et al.Automated recognition of hypertension through overnight continuous HRV monitoring [J].Journal of Ambient Intelligence and Humanized Computing,2018,9:2011-2023.
[27]LIU F,ZHOU X,WANG Z,et al.Identifying obstructive sleep apnea by exploiting fine-grained BCG features based on event phase segmentation[C]//Proceedings of the 2016 IEEE 16th International Conference on Bioinformatics and Bioengineering(BIBE).2016:293-300.
[28]TEJERA E,AREIAS M J,RODRIGUES A I,et al.Blood pressure and heart rate variability complexity analysis in pregnant women with hypertension [J].Hypertens Pregnancy,2012,31(1):91-106.
[29]HO Y L,LIN C,LIN Y H,et al.The prognostic value of non-linear analysis of heart rate variability in patients with congestive heart failure－a pilot study of multiscale entropy [J].PLoS One,2011,6(4):e18699.
[30]SHI P,YU H L.Heart rate variability in essential hypertension patients with different stages by nonlinear analysis:A preliminary study [J].Advances in Biomedical Engineering Research,2013,1:33-39.
[31]SONG Y,NI H,ZHOU X,et al.Extracting features for cardiovascular disease classification based on ballistocardiography[C]//Proceedings of the 2015 IEEE 12th International Confe-rence on Ubiquitous Intelligence and Computing(UIC-ATC-ScalCom).IEEE,2015:1-6.
[32]LAKE D E,RICHMAN J S,GRIFFIN M P,et al.Sample entropy analysis of neonatal heart rate variability [J].American Journal of Physiology:Regulatory Integrative and Comparative Physiology,2002,283(3):R789-R797.
[33]PENZEL T,KANTELHARDT J W,GROTE L,et al.Comparison of detrended fluctuation analysis and spectral analysis for heart rate variability in sleep and sleep apnea [J].IEEE Transactions on Biomedical Engineering,2003,50(10):1143-1151.
[34]SU B Y,ENAYATI M,HO K,et al.Monitoring the relative blood pressure using a hydraulic bed sensor system [J].IEEE Transactions on Biomedical Engineering,2018,66(3):740-748.
[35]RAJPUT J S,SHARMA M,KUMAR T S,et al.Automated de-tection of hypertension using continuous wavelet transform and a deep neural network with Ballistocardiography signals [J].International Journal of Environmental Research and Public Health,2022,19(7):4014.
[36]KURYLYAK Y,LAMONACA F,GRIMALDI D.A NeuralNetwork-based method for continuous blood pressure estimation from a PPG signal[C]//2013 IEEE International Instrumentation and Measurement Technology Conference(I2MTC).IEEE,2013:280-283.
[37]INAN O T,MIGEOTTE P F,PARK K S,et al.Ballistocardiography and seismocardiography:A review of recent advances [J].IEEE Journal of Biomedical and Health Informatics,2014,19(4):1414-1427.
[38]YOUSEFIAN P,SHIN S,MOUSAVI A,et al.The Potential of Wearable Limb Ballistocardiogram in Blood Pressure Monitoring via Pulse Transit Time [J].Scientific Reports,2019,9(1):10666.
[39]KIM C S,CAREK A M,INAN O T,et al.Ballistocardiogram-Based Approach to Cuffless Blood Pressure Monitoring:Proof of Concept and Potential Challenge [J].IEEE Transactions on Biomedical Engineering,2018,65(11):2384-2391.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市两江新区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发