Continuous Short-Term Pain Assessment in Temporomandibular Joint Therapy Using LSTM Models Supported by Heat-Induced Pain Data Patterns

This study aims to design a time-continuous pain level assessment system for temporomandibular joint therapy. Our objectives cover verifying literature suggestions on pain stimulus, protocols for collecting reference data, and continuous pain recognition models. We use two types of pain data acquire...

Full description

Saved in:
Bibliographic Details
Main Authors: Aleksandra Badura, Maria Bienkowska, Andrzej Mysliwiec, Ewa Pietka
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Transactions on Neural Systems and Rehabilitation Engineering
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10680582/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849735208802189312
author Aleksandra Badura
Maria Bienkowska
Andrzej Mysliwiec
Ewa Pietka
author_facet Aleksandra Badura
Maria Bienkowska
Andrzej Mysliwiec
Ewa Pietka
author_sort Aleksandra Badura
collection DOAJ
description This study aims to design a time-continuous pain level assessment system for temporomandibular joint therapy. Our objectives cover verifying literature suggestions on pain stimulus, protocols for collecting reference data, and continuous pain recognition models. We use two types of pain data acquired during 1) heat stimulation and 2) temporomandibular joint therapy. Thirty-six electrodermal activity (EDA) features are determined to build a binary classification model. The experimental dataset is used to train the initial model that produces pseudo-labels for weakly-labeled clinical data. In training the final long short-term memory (LSTM) model, we propose a novel multivariate loss involving, i.a., dynamometer data. Significant differences are found between EDA features extracted from experimental and clinical datasets in pain and no pain events. The classification model is validated at different stages of the model development. The final model classifies each four-second frame with a mean accuracy of 0.89 and an F1 score of 0.85. Our study introduces the dynamometer as a novel source of pain-feeling indications that meets the challenges given in the literature: data can be acquired in various procedures and from patients with limited abilities. The main contribution of the study is to design the first time-continuous and short-term pain assessment system for a clinical setting.
format Article
id doaj-art-0f75606c65ec44ecafa690c1cbfc64cc
institution DOAJ
issn 1534-4320
1558-0210
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Transactions on Neural Systems and Rehabilitation Engineering
spelling doaj-art-0f75606c65ec44ecafa690c1cbfc64cc2025-08-20T03:07:37ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1534-43201558-02102024-01-01323565357610.1109/TNSRE.2024.346158910680582Continuous Short-Term Pain Assessment in Temporomandibular Joint Therapy Using LSTM Models Supported by Heat-Induced Pain Data PatternsAleksandra Badura0https://orcid.org/0000-0001-7109-572XMaria Bienkowska1https://orcid.org/0000-0002-0226-4902Andrzej Mysliwiec2https://orcid.org/0000-0003-2183-1156Ewa Pietka3Faculty of Biomedical Engineering, Silesian University of Technology, Zabrze, PolandFaculty of Biomedical Engineering, Silesian University of Technology, Zabrze, PolandInstitute of Physiotherapy and Health Science, Academy of Physical Education in Katowice, Katowice, PolandFaculty of Biomedical Engineering, Silesian University of Technology, Zabrze, PolandThis study aims to design a time-continuous pain level assessment system for temporomandibular joint therapy. Our objectives cover verifying literature suggestions on pain stimulus, protocols for collecting reference data, and continuous pain recognition models. We use two types of pain data acquired during 1) heat stimulation and 2) temporomandibular joint therapy. Thirty-six electrodermal activity (EDA) features are determined to build a binary classification model. The experimental dataset is used to train the initial model that produces pseudo-labels for weakly-labeled clinical data. In training the final long short-term memory (LSTM) model, we propose a novel multivariate loss involving, i.a., dynamometer data. Significant differences are found between EDA features extracted from experimental and clinical datasets in pain and no pain events. The classification model is validated at different stages of the model development. The final model classifies each four-second frame with a mean accuracy of 0.89 and an F1 score of 0.85. Our study introduces the dynamometer as a novel source of pain-feeling indications that meets the challenges given in the literature: data can be acquired in various procedures and from patients with limited abilities. The main contribution of the study is to design the first time-continuous and short-term pain assessment system for a clinical setting.https://ieeexplore.ieee.org/document/10680582/Automated pain assessmentelectrodermal activity (EDA)pattern recognitionknowledge transferphysiotherapy
spellingShingle Aleksandra Badura
Maria Bienkowska
Andrzej Mysliwiec
Ewa Pietka
Continuous Short-Term Pain Assessment in Temporomandibular Joint Therapy Using LSTM Models Supported by Heat-Induced Pain Data Patterns
IEEE Transactions on Neural Systems and Rehabilitation Engineering
Automated pain assessment
electrodermal activity (EDA)
pattern recognition
knowledge transfer
physiotherapy
title Continuous Short-Term Pain Assessment in Temporomandibular Joint Therapy Using LSTM Models Supported by Heat-Induced Pain Data Patterns
title_full Continuous Short-Term Pain Assessment in Temporomandibular Joint Therapy Using LSTM Models Supported by Heat-Induced Pain Data Patterns
title_fullStr Continuous Short-Term Pain Assessment in Temporomandibular Joint Therapy Using LSTM Models Supported by Heat-Induced Pain Data Patterns
title_full_unstemmed Continuous Short-Term Pain Assessment in Temporomandibular Joint Therapy Using LSTM Models Supported by Heat-Induced Pain Data Patterns
title_short Continuous Short-Term Pain Assessment in Temporomandibular Joint Therapy Using LSTM Models Supported by Heat-Induced Pain Data Patterns
title_sort continuous short term pain assessment in temporomandibular joint therapy using lstm models supported by heat induced pain data patterns
topic Automated pain assessment
electrodermal activity (EDA)
pattern recognition
knowledge transfer
physiotherapy
url https://ieeexplore.ieee.org/document/10680582/
work_keys_str_mv AT aleksandrabadura continuousshorttermpainassessmentintemporomandibularjointtherapyusinglstmmodelssupportedbyheatinducedpaindatapatterns
AT mariabienkowska continuousshorttermpainassessmentintemporomandibularjointtherapyusinglstmmodelssupportedbyheatinducedpaindatapatterns
AT andrzejmysliwiec continuousshorttermpainassessmentintemporomandibularjointtherapyusinglstmmodelssupportedbyheatinducedpaindatapatterns
AT ewapietka continuousshorttermpainassessmentintemporomandibularjointtherapyusinglstmmodelssupportedbyheatinducedpaindatapatterns