Blood Pressure Estimation using Photoplethysmography only: Comparison between Different Machine Learning Approaches

Khalid, Syed G. and Zhang, Jufen and Chen, Fei and Zheng, Dingchang (2018) Blood Pressure Estimation using Photoplethysmography only: Comparison between Different Machine Learning Approaches. Journal of Healthcare Engineering, 2018. p. 1548647. ISSN 2040-2309

[img] Text
Published Version
Available under the following license: Creative Commons Attribution Non-commercial No Derivatives.

Download (1MB)
[img] Text
Accepted Version
Restricted to Repository staff only
Available under the following license: Creative Commons Attribution Non-commercial No Derivatives.

Download (1MB)
Official URL: https://doi.org/10.1155/2018/1548647

Abstract

Introduction: Blood pressure (BP) has been a potential risk factor for cardiovascular diseases. BP measurement is one of the useful parameters for early diagnosis, prevention, and treatment of cardiovascular diseases. At present, BP measurement mainly relies on cuff-based techniques that cause inconvenience and discomfort to users. Although some of the present prototype cuffless BP measurement techniques are able to reach overall acceptable accuracies, they require an electrocardiogram (ECG) and photoplethysmograph (PPG) that makes them unsuitable for true wearable applications. Therefore, developing a single PPG based cuffless BP estimation algorithm with enough accuracy would be clinically and practically useful. Methods: The University of Queensland vital sign dataset (Online database) was accessed to extract raw PPG signals and its corresponding reference BPs (Systolic BP & Diastolic BP). The online database consisted of PPG waveforms of 32 cases from whom 8133 (good quality) signal segments (5s for each) were extracted, pre-processed and normalised in both width and amplitude. Three most significant features (Pulse area, Pulse Rising Time and Width 25%) with their corresponding reference BPs were used to train and test three machine learning algorithms (Regression Tree, Multiple Linear Regression (MLR) and Support Vector Machine (SVM)). A 10-fold cross-validation was applied to obtain over-all BP estimation accuracy, separately for the three machine learning algorithms. Their estimation accuracies were further analysed separately for three clinical BP categories (Normotensive, Hypertensive and Hypotensive). Finally, they were compared with the ISO standard for non-invasive BP device validation (average difference no greater than 5mmHg and SD no greater than 8mmHg). Results: In terms of overall measurement accuracy, the Regression Tree achieved the best overall accuracy for SBP (mean and SD of difference: -0.1±6.5mmHg) & DBP (mean and SD of difference: -0.6±5.2mmHg). MLR and SVM achieved the overall mean difference less than 5mmHg for both SBP and DBP but their SD of difference was >8mmHg. Regarding the measurement accuracy in each BP categories, only the Regression Tree achieved acceptable ISO standard for SBP (-1.1±5.7mmHg) & DBP (-0.03±5.6 mmHg) in the Normotensive category. MLR and SVM did not achieve acceptable accuracies in any BP categories. Conclusion: This study developed and compared three machine learning algorithms to estimate BPs using PPG only, and revealed that the Regression Tree algorithm was the best approach with overall acceptable accuracy to ISO standard for BP device validation. Furthermore, this study demonstrated that the Regression Tree algorithm achieved acceptable measurement accuracy only in the Normotensive category, suggesting that future algorithm development for BP estimation should be more specific for different BP categories.

Item Type: Journal Article
Keywords: Photoplethysmography, Blood Pressure, Machine Learning
Faculty: Faculty of Medical Science
Depositing User: Professor D Zheng
Date Deposited: 03 Oct 2018 15:46
Last Modified: 18 Jul 2019 16:19
URI: http://arro.anglia.ac.uk/id/eprint/703637

Actions (login required)

Edit Item Edit Item