An Experimental and Clinical Physiological Signal Dataset for Automated Pain Recognition

Philip Gouverneur; Aleksandra Badura; Frédéric Li; Maria Bieńkowska; Luisa Luebke; Wacław M. Adamczyk; Tibor M. Szikszay; Andrzej Myśliwiec; Kerstin Luedtke; Marcin Grzegorzek; Ewa Piętka

doi:10.1038/s41597-024-03878-w

An Experimental and Clinical Physiological Signal Dataset for Automated Pain Recognition

Philip Gouverneur^*, Aleksandra Badura, Frédéric Li, Maria Bieńkowska, Luisa Luebke, Wacław M. Adamczyk, Tibor M. Szikszay, Andrzej Myśliwiec, Kerstin Luedtke, Marcin Grzegorzek, Ewa Piętka

^*Corresponding author for this work

6 Citations (Scopus)

Abstract

Access to large amounts of data is essential for successful machine learning research. However, there is insufficient data for many applications, as data collection is often challenging and time-consuming. The same applies to automated pain recognition, where algorithms aim to learn associations between a level of pain and behavioural or physiological responses. Although machine learning models have shown promise in improving the current gold standard of pain monitoring (self-reports) only a handful of datasets are freely accessible to researchers. This paper presents the PainMonit Dataset for automated pain detection using physiological data. The dataset consists of two parts, as pain can be perceived differently depending on its underlying cause. (1) Pain was triggered by heat stimuli in an experimental study during which nine physiological sensor modalities (BVP, 2×EDA, skin temperature, ECG, EMG, IBI, HR, respiration) were recorded from 55 healthy subjects. (2) Eight modalities (2×BVP, 2×EDA, EMG, skin temperature, respiration, grip) were recorded from 49 participants to assess their pain during a physiotherapy session.

Original language	English
Article number	1051
Journal	Scientific Data
Volume	11
Issue number	1
Pages (from-to)	1051
ISSN	2052-4463
DOIs	https://doi.org/10.1038/s41597-024-03878-w
Publication status	Published - 27.09.2024

Funding

Funders	Funder number
PMED
Bundesministerium für Bildung und Forschung	01DS19008B
Polish Ministry of Science, Poland	07/010/BK_24/1034
Narodowe Centrum Badań i Rozwoju	FESL.10.25-IZ.01-07G5/23, WPN-3/1/2019

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being
SDG 4 Quality Education
SDG 9 Industry, Innovation, and Infrastructure
SDG 11 Sustainable Cities and Communities
SDG 12 Responsible Consumption and Production
SDG 14 Life Below Water
SDG 15 Life on Land

Research Areas and Centers

Health Sciences
Centers: Center for Artificial Intelligence Luebeck (ZKIL)
Centers: Center for Open Innovation in Connected Health (COPICOH)

DFG Research Classification Scheme

2.23-08 Human Cognitive and Systems Neuroscience
4.43-04 Artificial Intelligence and Machine Learning Methods

Access to Document

10.1038/s41597-024-03878-w

Cite this

@article{e1ce06392e294b98a2aa1a9268f1ed0e,

title = "An Experimental and Clinical Physiological Signal Dataset for Automated Pain Recognition",

abstract = "Access to large amounts of data is essential for successful machine learning research. However, there is insufficient data for many applications, as data collection is often challenging and time-consuming. The same applies to automated pain recognition, where algorithms aim to learn associations between a level of pain and behavioural or physiological responses. Although machine learning models have shown promise in improving the current gold standard of pain monitoring (self-reports) only a handful of datasets are freely accessible to researchers. This paper presents the PainMonit Dataset for automated pain detection using physiological data. The dataset consists of two parts, as pain can be perceived differently depending on its underlying cause. (1) Pain was triggered by heat stimuli in an experimental study during which nine physiological sensor modalities (BVP, 2×EDA, skin temperature, ECG, EMG, IBI, HR, respiration) were recorded from 55 healthy subjects. (2) Eight modalities (2×BVP, 2×EDA, EMG, skin temperature, respiration, grip) were recorded from 49 participants to assess their pain during a physiotherapy session.",

author = "Philip Gouverneur and Aleksandra Badura and Fr{\'e}d{\'e}ric Li and Maria Bie{\'n}kowska and Luisa Luebke and Adamczyk, \{Wac{\l}aw M.\} and Szikszay, \{Tibor M.\} and Andrzej My{\'s}liwiec and Kerstin Luedtke and Marcin Grzegorzek and Ewa Pi{\c e}tka",

note = "Publisher Copyright: {\textcopyright} The Author(s) 2024.",

year = "2024",

month = sep,

day = "27",

doi = "10.1038/s41597-024-03878-w",

language = "English",

volume = "11",

pages = "1051",

journal = "Scientific Data",

issn = "2052-4463",

publisher = "Nature Publishing Group",

number = "1",

}

TY - JOUR

T1 - An Experimental and Clinical Physiological Signal Dataset for Automated Pain Recognition

AU - Gouverneur, Philip

AU - Badura, Aleksandra

AU - Li, Frédéric

AU - Bieńkowska, Maria

AU - Luebke, Luisa

AU - Adamczyk, Wacław M.

AU - Szikszay, Tibor M.

AU - Myśliwiec, Andrzej

AU - Luedtke, Kerstin

AU - Grzegorzek, Marcin

AU - Piętka, Ewa

PY - 2024/9/27

Y1 - 2024/9/27

N2 - Access to large amounts of data is essential for successful machine learning research. However, there is insufficient data for many applications, as data collection is often challenging and time-consuming. The same applies to automated pain recognition, where algorithms aim to learn associations between a level of pain and behavioural or physiological responses. Although machine learning models have shown promise in improving the current gold standard of pain monitoring (self-reports) only a handful of datasets are freely accessible to researchers. This paper presents the PainMonit Dataset for automated pain detection using physiological data. The dataset consists of two parts, as pain can be perceived differently depending on its underlying cause. (1) Pain was triggered by heat stimuli in an experimental study during which nine physiological sensor modalities (BVP, 2×EDA, skin temperature, ECG, EMG, IBI, HR, respiration) were recorded from 55 healthy subjects. (2) Eight modalities (2×BVP, 2×EDA, EMG, skin temperature, respiration, grip) were recorded from 49 participants to assess their pain during a physiotherapy session.

AB - Access to large amounts of data is essential for successful machine learning research. However, there is insufficient data for many applications, as data collection is often challenging and time-consuming. The same applies to automated pain recognition, where algorithms aim to learn associations between a level of pain and behavioural or physiological responses. Although machine learning models have shown promise in improving the current gold standard of pain monitoring (self-reports) only a handful of datasets are freely accessible to researchers. This paper presents the PainMonit Dataset for automated pain detection using physiological data. The dataset consists of two parts, as pain can be perceived differently depending on its underlying cause. (1) Pain was triggered by heat stimuli in an experimental study during which nine physiological sensor modalities (BVP, 2×EDA, skin temperature, ECG, EMG, IBI, HR, respiration) were recorded from 55 healthy subjects. (2) Eight modalities (2×BVP, 2×EDA, EMG, skin temperature, respiration, grip) were recorded from 49 participants to assess their pain during a physiotherapy session.

UR - https://www.scopus.com/pages/publications/85205276003

UR - https://www.mendeley.com/catalogue/3c93bd7e-2340-37c9-9110-333ebb9ee901/

U2 - 10.1038/s41597-024-03878-w

DO - 10.1038/s41597-024-03878-w

M3 - Journal articles

C2 - 39333541

AN - SCOPUS:85205276003

SN - 2052-4463

VL - 11

SP - 1051

JO - Scientific Data

JF - Scientific Data

IS - 1

M1 - 1051

ER -

An Experimental and Clinical Physiological Signal Dataset for Automated Pain Recognition

Abstract

Funding

UN SDGs

Research Areas and Centers

DFG Research Classification Scheme

Access to Document

Other files and links

Fingerprint

Cite this