Cargando…

Boosted-SpringDTW for Comprehensive Feature Extraction of PPG Signals

Goal: To achieve high-quality comprehensive feature extraction from physiological signals that enables precise physiological parameter estimation despite evolving waveform morphologies. Methods: We propose Boosted-SpringDTW, a probabilistic framework that leverages dynamic time warping (DTW) and min...

Descripción completa

Detalles Bibliográficos
Formato: Online Artículo Texto
Lenguaje:English
Publicado: IEEE 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9299207/
https://www.ncbi.nlm.nih.gov/pubmed/35873901
http://dx.doi.org/10.1109/OJEMB.2022.3174806
_version_ 1784750909468704768
collection PubMed
description Goal: To achieve high-quality comprehensive feature extraction from physiological signals that enables precise physiological parameter estimation despite evolving waveform morphologies. Methods: We propose Boosted-SpringDTW, a probabilistic framework that leverages dynamic time warping (DTW) and minimal domain-specific heuristics to simultaneously segment physiological signals and identify fiducial points that represent cardiac events. An automated dynamic template adapts to evolving waveform morphologies. We validate Boosted-SpringDTW performance with a benchmark PPG dataset whose morphologies include subject- and respiratory-induced variation. Results: Boosted-SpringDTW achieves precision, recall, and F1-scores over 0.96 for identifying fiducial points and mean absolute error values less than 11.41 milliseconds when estimating IBI. Conclusion: Boosted-SpringDTW improves F1-Scores compared to two baseline feature extraction algorithms by 35% on average for fiducial point identification and mean percent difference by 16% on average for IBI estimation. Significance: Precise hemodynamic parameter estimation with wearable devices enables continuous health monitoring throughout a patients’ daily life.
format Online
Article
Text
id pubmed-9299207
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher IEEE
record_format MEDLINE/PubMed
spelling pubmed-92992072022-07-22 Boosted-SpringDTW for Comprehensive Feature Extraction of PPG Signals IEEE Open J Eng Med Biol Article Goal: To achieve high-quality comprehensive feature extraction from physiological signals that enables precise physiological parameter estimation despite evolving waveform morphologies. Methods: We propose Boosted-SpringDTW, a probabilistic framework that leverages dynamic time warping (DTW) and minimal domain-specific heuristics to simultaneously segment physiological signals and identify fiducial points that represent cardiac events. An automated dynamic template adapts to evolving waveform morphologies. We validate Boosted-SpringDTW performance with a benchmark PPG dataset whose morphologies include subject- and respiratory-induced variation. Results: Boosted-SpringDTW achieves precision, recall, and F1-scores over 0.96 for identifying fiducial points and mean absolute error values less than 11.41 milliseconds when estimating IBI. Conclusion: Boosted-SpringDTW improves F1-Scores compared to two baseline feature extraction algorithms by 35% on average for fiducial point identification and mean percent difference by 16% on average for IBI estimation. Significance: Precise hemodynamic parameter estimation with wearable devices enables continuous health monitoring throughout a patients’ daily life. IEEE 2022-05-12 /pmc/articles/PMC9299207/ /pubmed/35873901 http://dx.doi.org/10.1109/OJEMB.2022.3174806 Text en https://creativecommons.org/licenses/by/4.0/This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
spellingShingle Article
Boosted-SpringDTW for Comprehensive Feature Extraction of PPG Signals
title Boosted-SpringDTW for Comprehensive Feature Extraction of PPG Signals
title_full Boosted-SpringDTW for Comprehensive Feature Extraction of PPG Signals
title_fullStr Boosted-SpringDTW for Comprehensive Feature Extraction of PPG Signals
title_full_unstemmed Boosted-SpringDTW for Comprehensive Feature Extraction of PPG Signals
title_short Boosted-SpringDTW for Comprehensive Feature Extraction of PPG Signals
title_sort boosted-springdtw for comprehensive feature extraction of ppg signals
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9299207/
https://www.ncbi.nlm.nih.gov/pubmed/35873901
http://dx.doi.org/10.1109/OJEMB.2022.3174806
work_keys_str_mv AT boostedspringdtwforcomprehensivefeatureextractionofppgsignals
AT boostedspringdtwforcomprehensivefeatureextractionofppgsignals
AT boostedspringdtwforcomprehensivefeatureextractionofppgsignals
AT boostedspringdtwforcomprehensivefeatureextractionofppgsignals