Cargando…

Comparison of Feature Extraction Methods for Physiological Signals for Heat-Based Pain Recognition

While even the most common definition of pain is under debate, pain assessment has remained the same for decades. But the paramount importance of precise pain management for successful healthcare has encouraged initiatives to improve the way pain is assessed. Recent approaches have proposed automati...

Descripción completa

Detalles Bibliográficos
Autores principales: Gouverneur, Philip, Li, Frédéric, Adamczyk, Wacław M., Szikszay, Tibor M., Luedtke, Kerstin, Grzegorzek, Marcin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8309734/
https://www.ncbi.nlm.nih.gov/pubmed/34300578
http://dx.doi.org/10.3390/s21144838
_version_ 1783728590743928832
author Gouverneur, Philip
Li, Frédéric
Adamczyk, Wacław M.
Szikszay, Tibor M.
Luedtke, Kerstin
Grzegorzek, Marcin
author_facet Gouverneur, Philip
Li, Frédéric
Adamczyk, Wacław M.
Szikszay, Tibor M.
Luedtke, Kerstin
Grzegorzek, Marcin
author_sort Gouverneur, Philip
collection PubMed
description While even the most common definition of pain is under debate, pain assessment has remained the same for decades. But the paramount importance of precise pain management for successful healthcare has encouraged initiatives to improve the way pain is assessed. Recent approaches have proposed automatic pain evaluation systems using machine learning models trained with data coming from behavioural or physiological sensors. Although yielding promising results, machine learning studies for sensor-based pain recognition remain scattered and not necessarily easy to compare to each other. In particular, the important process of extracting features is usually optimised towards specific datasets. We thus introduce a comparison of feature extraction methods for pain recognition based on physiological sensors in this paper. In addition, the PainMonit Database (PMDB), a new dataset including both objective and subjective annotations for heat-induced pain in 52 subjects, is introduced. In total, five different approaches including techniques based on feature engineering and feature learning with deep learning are evaluated on the BioVid and PMDB datasets. Our studies highlight the following insights: (1) Simple feature engineering approaches can still compete with deep learning approaches in terms of performance. (2) More complex deep learning architectures do not yield better performance compared to simpler ones. (3) Subjective self-reports by subjects can be used instead of objective temperature-based annotations to build a robust pain recognition system.
format Online
Article
Text
id pubmed-8309734
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-83097342021-07-25 Comparison of Feature Extraction Methods for Physiological Signals for Heat-Based Pain Recognition Gouverneur, Philip Li, Frédéric Adamczyk, Wacław M. Szikszay, Tibor M. Luedtke, Kerstin Grzegorzek, Marcin Sensors (Basel) Article While even the most common definition of pain is under debate, pain assessment has remained the same for decades. But the paramount importance of precise pain management for successful healthcare has encouraged initiatives to improve the way pain is assessed. Recent approaches have proposed automatic pain evaluation systems using machine learning models trained with data coming from behavioural or physiological sensors. Although yielding promising results, machine learning studies for sensor-based pain recognition remain scattered and not necessarily easy to compare to each other. In particular, the important process of extracting features is usually optimised towards specific datasets. We thus introduce a comparison of feature extraction methods for pain recognition based on physiological sensors in this paper. In addition, the PainMonit Database (PMDB), a new dataset including both objective and subjective annotations for heat-induced pain in 52 subjects, is introduced. In total, five different approaches including techniques based on feature engineering and feature learning with deep learning are evaluated on the BioVid and PMDB datasets. Our studies highlight the following insights: (1) Simple feature engineering approaches can still compete with deep learning approaches in terms of performance. (2) More complex deep learning architectures do not yield better performance compared to simpler ones. (3) Subjective self-reports by subjects can be used instead of objective temperature-based annotations to build a robust pain recognition system. MDPI 2021-07-15 /pmc/articles/PMC8309734/ /pubmed/34300578 http://dx.doi.org/10.3390/s21144838 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Gouverneur, Philip
Li, Frédéric
Adamczyk, Wacław M.
Szikszay, Tibor M.
Luedtke, Kerstin
Grzegorzek, Marcin
Comparison of Feature Extraction Methods for Physiological Signals for Heat-Based Pain Recognition
title Comparison of Feature Extraction Methods for Physiological Signals for Heat-Based Pain Recognition
title_full Comparison of Feature Extraction Methods for Physiological Signals for Heat-Based Pain Recognition
title_fullStr Comparison of Feature Extraction Methods for Physiological Signals for Heat-Based Pain Recognition
title_full_unstemmed Comparison of Feature Extraction Methods for Physiological Signals for Heat-Based Pain Recognition
title_short Comparison of Feature Extraction Methods for Physiological Signals for Heat-Based Pain Recognition
title_sort comparison of feature extraction methods for physiological signals for heat-based pain recognition
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8309734/
https://www.ncbi.nlm.nih.gov/pubmed/34300578
http://dx.doi.org/10.3390/s21144838
work_keys_str_mv AT gouverneurphilip comparisonoffeatureextractionmethodsforphysiologicalsignalsforheatbasedpainrecognition
AT lifrederic comparisonoffeatureextractionmethodsforphysiologicalsignalsforheatbasedpainrecognition
AT adamczykwacławm comparisonoffeatureextractionmethodsforphysiologicalsignalsforheatbasedpainrecognition
AT szikszaytiborm comparisonoffeatureextractionmethodsforphysiologicalsignalsforheatbasedpainrecognition
AT luedtkekerstin comparisonoffeatureextractionmethodsforphysiologicalsignalsforheatbasedpainrecognition
AT grzegorzekmarcin comparisonoffeatureextractionmethodsforphysiologicalsignalsforheatbasedpainrecognition