EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Improving the Accuracy in Classification of Blood Pressure from Photoplethysmography Using Continuous Wavelet Transform and Deep Learning

Jiaze Wu iD, Hao Liang iD, Changsong Ding, Xindi Huang, Jianhua Huang iD, Qinghua Peng iD

International Journal of Hypertension · 2021-01 · 2021 (1)

DOI: 10.1155/2021/9938584 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Hypertension, online erschienen am 05.08.2021. Verfasst von Jiaze Wu und 5 weiteren Autor:innen. Beteiligte Einrichtung: Institute of TCM Diagnostics, Hunan University of Chinese Medicine, Changsha, Hunan 410208, China. Die Arbeit wurde bisher 37-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: China Postdoctoral Science Foundation, Education Department of Hunan Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Continuous wavelet transform (CWT) based scalogram can be used for photoplethysmography (PPG) signal transformation to classify blood pressure (BP) with deep learning. We aimed to investigate the determinants that can improve the accuracy of BP classification based on PPG and deep learning and establish a better algorithm for the prediction.

Methods

The dataset from PhysioNet was accessed to extract raw PPG signals for testing and its corresponding BPs as category labels. The BP category of normal or abnormal followed the criteria of the 2017 American College of Cardiology/American Heart Association (ACC/AHA) Hypertension Guidelines. The PPG signals were transformed into 224 ∗ 224 ∗ 3‐pixel scalogram via different CWTs and segment units. All of them are fed into different convolutional neural networks (CNN) for training and validation. The receiver‐operating characteristic and loss and accuracy curves were used to evaluate and compare the performance of different methods.

Results

Both wavelet type and segment length could affect the accuracy, and Cgau1 wavelet and segment‐300 revealed the best performance (accuracy 90%) without obvious overfitting. This method performed better than previously reported MATLAB Morse wavelet transformed scalogram on both of our proposed CNN and CNN‐GoogLeNet.

Conclusions

We have established a new algorithm with high accuracy to predict BP classification from PPG via matching of CWT type and segment length, which is a promising solution for rapid prediction of BP classification from real‐time processing of PPG signal on a wearable device.

Autor:innen und Institutionen

  • Institute of TCM Diagnostics, Hunan University of Chinese Medicine, Changsha, Hunan 410208, China.
  • Post-Doctoral Research Station of Integrative Medicine, Hunan University of Chinese Medicine, Changsha, Hunan 410208, China.
  • School of Informatics and Engineering, Hunan University of Chinese Medicine, Changsha, Hunan 410208, China.
  • Institute of Herbs, Hunan Academy of Chinese Medicine, Changsha, Hunan 410208, China.

ORCID-Profile: Jiaze Wu, Hao Liang, Jianhua Huang, Qinghua Peng

Förderung

  • China Postdoctoral Science Foundation
  • Education Department of Hunan Province

Zitieren

APA

Wu, J., Liang, H., Ding, C., Huang, X., Huang, J., & Peng, Q. (2021). Improving the Accuracy in Classification of Blood Pressure from Photoplethysmography Using Continuous Wavelet Transform and Deep Learning. International Journal of Hypertension, 2021(1). https://doi.org/10.1155/2021/9938584

Vancouver

Wu J, Liang H, Ding C, Huang X, Huang J, Peng Q. Improving the Accuracy in Classification of Blood Pressure from Photoplethysmography Using Continuous Wavelet Transform and Deep Learning. International Journal of Hypertension. 2021;2021(1). doi:10.1155/2021/9938584

BibTeX
@article{Wu2021,
  author = {Wu, Jiaze and Liang, Hao and Ding, Changsong and Huang, Xindi and Huang, Jianhua and Peng, Qinghua},
  title = {Improving the Accuracy in Classification of Blood Pressure from Photoplethysmography Using Continuous Wavelet Transform and Deep Learning},
  journal = {International Journal of Hypertension},
  year = {2021},
  volume = {2021},
  number = {1},
  doi = {10.1155/2021/9938584}
}
Kostenlos starten →