Blood pressure estimation and classification using a reference signal-less photoplethysmography signal: a deep learning framework

被引:5
|
作者
Pankaj [1 ]
Kumar, Ashish [1 ,2 ]
Komaragiri, Rama [1 ]
Kumar, Manjeet [3 ]
机构
[1] Bennett Univ, Dept Elect & Commun Engn, Greater Noida, India
[2] Bennett Univ, Sch Comp Sci Engn & Technol, Greater Noida, India
[3] Delhi Technol Univ, Dept Elect & Commun Engn, Delhi, India
关键词
Blood pressure; Classification; Convolutional Neural Network; Deep Learning; Hypertension; Photoplethysmography; Regression; Wearable device; HEART-RATE; ELECTROCARDIOGRAM; TIME;
D O I
10.1007/s13246-023-01322-8
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
The markers that help to predict th function of a cardiovascular system are hemodynamic parameters like blood pressure (BP), stroke volume, heart rate, and cardiac output. Continuous analysis of hemodynamic parameters such as BP can detect abnormalities earlier, preventing cardiovascular diseases (CVDs). However, sometimes due to motion artifacts, it becomes difficult to monitor the BP accurately and classify it. This work presents an optimized deep learning model having the capability to estimate the systolic blood pressure (SBP) and diastolic blood pressure (DBP) and classify the BP stages simultaneously from the same network using only a single channel photoplethysmography (PPG) signal. The proposed model is designed by exploiting the deep learning framework of a convolutional neural network (CNN), exhibiting the inherent ability to extract features automatically. Moreover, the proposed framework utilizes the superlet transform method to transform a 1-D PPG signal into a 2-D super-resolution time-frequency (TF) spectrogram. A superlet transform separates the peaks related to true PPG signal components and motion artifacts components. Thus, the superlet provides a robust realtime approach to accurately estimating and classifying BP using a single PPG sensor signal and does not require additional ECG and PPG sensor signals for reference. Using a super-resolution spectrogram and CNN model makes the method profitable in motion artifact removal, feature selection, and extraction. Hence the proposed framework becomes less complex for deployment on wearable devices having limited battery resources. The performance of the proposed framework is demonstrated on the publicly available larger dataset MIMIC-III. This work obtained a mean absolute error (MAE) of 2.71 mmHg and 2.42 mmHg for SBP and DBP, respectively. The classification accuracy for the SBP prediction is about 96.79%, whereas it is 98.94% for DBP. From a motion artifact-affected PPG signal, SBP and DBP are estimated. Then the estimated BP is classified into three categories: normotension, prehypertension, and hypertension, and is compared with the state of art methods to show the effectiveness of the proposed optimized framework.
引用
收藏
页码:1589 / 1605
页数:17
相关论文
共 50 条
  • [21] Blood Pressure Estimation from Photoplethysmography Signals by Applying Deep Learning Techniques
    Rodriguez-Marquez, Roy
    Moreno, Silvia
    COMPUTER INFORMATION SYSTEMS AND INDUSTRIAL MANAGEMENT (CISIM 2022), 2022, 13293 : 258 - 268
  • [22] Heartbeat Sound Signal Classification Using Deep Learning
    Raza, Ali
    Mehmood, Arif
    Ullah, Saleem
    Ahmad, Maqsood
    Choi, Gyu Sang
    On, Byung-Won
    SENSORS, 2019, 19 (21)
  • [23] Improving the Accuracy in Classification of Blood Pressure from Photoplethysmography Using Continuous Wavelet Transform and Deep Learning
    Wu, Jiaze
    Liang, Hao
    Ding, Changsong
    Huang, Xindi
    Huang, Jianhua
    Peng, Qinghua
    INTERNATIONAL JOURNAL OF HYPERTENSION, 2021, 2021
  • [24] Cuff-Less Blood Pressure Estimation Using Only the ECG Signal in Frequency Domain
    Mousavi, Seyedeh Somayyeh
    Hemmati, Mohammad
    Charmi, Mostafa
    Moghadam, Maryam
    Firouzmand, Mohammad
    Ghorbani, Yadollah
    2018 8TH INTERNATIONAL CONFERENCE ON COMPUTER AND KNOWLEDGE ENGINEERING (ICCKE), 2018, : 147 - 152
  • [25] Personalized Blood Pressure Estimation Using Photoplethysmography: A Transfer Learning Approach
    Leitner, Jared
    Chiang, Po-Han
    Dey, Sujit
    IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2022, 26 (01) : 218 - 228
  • [26] Cuffless blood pressure estimation from photoplethysmography using deep convolutional neural network and transfer learning
    Koparir, Hueseyin Murat
    Arslan, Ozkan
    BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2024, 93
  • [27] Deep Learning based Framework for Underwater Acoustic Signal Recognition and Classification
    Wu, Hao
    Song, Qingzeng
    Jin, Guanghao
    PROCEEDINGS OF 2018 THE 2ND INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND ARTIFICIAL INTELLIGENCE (CSAI 2018) / 2018 THE 10TH INTERNATIONAL CONFERENCE ON INFORMATION AND MULTIMEDIA TECHNOLOGY (ICIMT 2018), 2018, : 385 - 388
  • [28] DeepSIG: A Hybrid Heterogeneous Deep Learning Framework for Radio Signal Classification
    Qiu, Kunfeng
    Zheng, Shilian
    Zhang, Luxin
    Lou, Caiyi
    Yang, Xiaoniu
    IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2024, 23 (01) : 775 - 788
  • [29] Dynamic Estimation of Cerebral Blood Flow Using Photoplethysmography Signal during Simulated Apnea
    Zadi, Armin Soltan
    Alex, Raichel M.
    Zhang, Rong
    Watenpaugh, Donald E.
    Behbehani, Khosrow
    2019 41ST ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), 2019, : 5727 - 5730
  • [30] Optimized deep neural network models for blood pressure classification using Fourier analysis-based time-frequency spectrogram of photoplethysmography signal
    Pankaj
    Kumar, Ashish
    Kumar, Manjeet
    Komaragiri, Rama
    BIOMEDICAL ENGINEERING LETTERS, 2023, 13 (04) : 739 - 750