A Novel Respiratory Rate Estimation Algorithm from Photoplethysmogram Using Deep Learning Model
Respiratory rate (RR) is a critical vital sign that can provide valuable insights into various medical conditions, including pneumonia. Unfortunately, manual RR counting is often unreliable and discontinuous. Current RR estimation algorithms either lack the necessary accuracy or demand extensive win...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2024-01-01
|
Series: | Diagnostics |
Subjects: | |
Online Access: | https://www.mdpi.com/2075-4418/14/3/284 |
_version_ | 1797318921183821824 |
---|---|
author | Wee Jian Chin Ban-Hoe Kwan Wei Yin Lim Yee Kai Tee Shalini Darmaraju Haipeng Liu Choon-Hian Goh |
author_facet | Wee Jian Chin Ban-Hoe Kwan Wei Yin Lim Yee Kai Tee Shalini Darmaraju Haipeng Liu Choon-Hian Goh |
author_sort | Wee Jian Chin |
collection | DOAJ |
description | Respiratory rate (RR) is a critical vital sign that can provide valuable insights into various medical conditions, including pneumonia. Unfortunately, manual RR counting is often unreliable and discontinuous. Current RR estimation algorithms either lack the necessary accuracy or demand extensive window sizes. In response to these challenges, this study introduces a novel method for continuously estimating RR from photoplethysmogram (PPG) with a reduced window size and lower processing requirements. To evaluate and compare classical and deep learning algorithms, this study leverages the BIDMC and CapnoBase datasets, employing the Respiratory Rate Estimation (RRest) toolbox. The optimal classical techniques combination on the BIDMC datasets achieves a mean absolute error (MAE) of 1.9 breaths/min. Additionally, the developed neural network model utilises convolutional and long short-term memory layers to estimate RR effectively. The best-performing model, with a 50% train–test split and a window size of 7 s, achieves an MAE of 2 breaths/min. Furthermore, compared to other deep learning algorithms with window sizes of 16, 32, and 64 s, this study’s model demonstrates superior performance with a smaller window size. The study suggests that further research into more precise signal processing techniques may enhance RR estimation from PPG signals. |
first_indexed | 2024-03-08T03:58:30Z |
format | Article |
id | doaj.art-41ae45ca3a2f40a8bed152e0f196848b |
institution | Directory Open Access Journal |
issn | 2075-4418 |
language | English |
last_indexed | 2024-03-08T03:58:30Z |
publishDate | 2024-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Diagnostics |
spelling | doaj.art-41ae45ca3a2f40a8bed152e0f196848b2024-02-09T15:10:05ZengMDPI AGDiagnostics2075-44182024-01-0114328410.3390/diagnostics14030284A Novel Respiratory Rate Estimation Algorithm from Photoplethysmogram Using Deep Learning ModelWee Jian Chin0Ban-Hoe Kwan1Wei Yin Lim2Yee Kai Tee3Shalini Darmaraju4Haipeng Liu5Choon-Hian Goh6Department of Mechatronics and Biomedical Engineering, Lee Kong Chian Faculty of Engineering and Science, Universiti Tunku Abdul Rahman, Kajang 43000, Selangor, MalaysiaDepartment of Mechatronics and Biomedical Engineering, Lee Kong Chian Faculty of Engineering and Science, Universiti Tunku Abdul Rahman, Kajang 43000, Selangor, MalaysiaElectrical and Computer Systems Engineering, School of Engineering and Advanced Engineering Platform, Monash University Malaysia, Bandar Sunway 47500, Selangor, MalaysiaDepartment of Mechatronics and Biomedical Engineering, Lee Kong Chian Faculty of Engineering and Science, Universiti Tunku Abdul Rahman, Kajang 43000, Selangor, MalaysiaDepartment of Mechatronics and Biomedical Engineering, Lee Kong Chian Faculty of Engineering and Science, Universiti Tunku Abdul Rahman, Kajang 43000, Selangor, MalaysiaCentre for Intelligent Healthcare, Coventry University, Coventry CV1 5RW, UKDepartment of Mechatronics and Biomedical Engineering, Lee Kong Chian Faculty of Engineering and Science, Universiti Tunku Abdul Rahman, Kajang 43000, Selangor, MalaysiaRespiratory rate (RR) is a critical vital sign that can provide valuable insights into various medical conditions, including pneumonia. Unfortunately, manual RR counting is often unreliable and discontinuous. Current RR estimation algorithms either lack the necessary accuracy or demand extensive window sizes. In response to these challenges, this study introduces a novel method for continuously estimating RR from photoplethysmogram (PPG) with a reduced window size and lower processing requirements. To evaluate and compare classical and deep learning algorithms, this study leverages the BIDMC and CapnoBase datasets, employing the Respiratory Rate Estimation (RRest) toolbox. The optimal classical techniques combination on the BIDMC datasets achieves a mean absolute error (MAE) of 1.9 breaths/min. Additionally, the developed neural network model utilises convolutional and long short-term memory layers to estimate RR effectively. The best-performing model, with a 50% train–test split and a window size of 7 s, achieves an MAE of 2 breaths/min. Furthermore, compared to other deep learning algorithms with window sizes of 16, 32, and 64 s, this study’s model demonstrates superior performance with a smaller window size. The study suggests that further research into more precise signal processing techniques may enhance RR estimation from PPG signals.https://www.mdpi.com/2075-4418/14/3/284photoplethysmogramrespiratory ratedeep learningneural network |
spellingShingle | Wee Jian Chin Ban-Hoe Kwan Wei Yin Lim Yee Kai Tee Shalini Darmaraju Haipeng Liu Choon-Hian Goh A Novel Respiratory Rate Estimation Algorithm from Photoplethysmogram Using Deep Learning Model Diagnostics photoplethysmogram respiratory rate deep learning neural network |
title | A Novel Respiratory Rate Estimation Algorithm from Photoplethysmogram Using Deep Learning Model |
title_full | A Novel Respiratory Rate Estimation Algorithm from Photoplethysmogram Using Deep Learning Model |
title_fullStr | A Novel Respiratory Rate Estimation Algorithm from Photoplethysmogram Using Deep Learning Model |
title_full_unstemmed | A Novel Respiratory Rate Estimation Algorithm from Photoplethysmogram Using Deep Learning Model |
title_short | A Novel Respiratory Rate Estimation Algorithm from Photoplethysmogram Using Deep Learning Model |
title_sort | novel respiratory rate estimation algorithm from photoplethysmogram using deep learning model |
topic | photoplethysmogram respiratory rate deep learning neural network |
url | https://www.mdpi.com/2075-4418/14/3/284 |
work_keys_str_mv | AT weejianchin anovelrespiratoryrateestimationalgorithmfromphotoplethysmogramusingdeeplearningmodel AT banhoekwan anovelrespiratoryrateestimationalgorithmfromphotoplethysmogramusingdeeplearningmodel AT weiyinlim anovelrespiratoryrateestimationalgorithmfromphotoplethysmogramusingdeeplearningmodel AT yeekaitee anovelrespiratoryrateestimationalgorithmfromphotoplethysmogramusingdeeplearningmodel AT shalinidarmaraju anovelrespiratoryrateestimationalgorithmfromphotoplethysmogramusingdeeplearningmodel AT haipengliu anovelrespiratoryrateestimationalgorithmfromphotoplethysmogramusingdeeplearningmodel AT choonhiangoh anovelrespiratoryrateestimationalgorithmfromphotoplethysmogramusingdeeplearningmodel AT weejianchin novelrespiratoryrateestimationalgorithmfromphotoplethysmogramusingdeeplearningmodel AT banhoekwan novelrespiratoryrateestimationalgorithmfromphotoplethysmogramusingdeeplearningmodel AT weiyinlim novelrespiratoryrateestimationalgorithmfromphotoplethysmogramusingdeeplearningmodel AT yeekaitee novelrespiratoryrateestimationalgorithmfromphotoplethysmogramusingdeeplearningmodel AT shalinidarmaraju novelrespiratoryrateestimationalgorithmfromphotoplethysmogramusingdeeplearningmodel AT haipengliu novelrespiratoryrateestimationalgorithmfromphotoplethysmogramusingdeeplearningmodel AT choonhiangoh novelrespiratoryrateestimationalgorithmfromphotoplethysmogramusingdeeplearningmodel |