Multimodal physiological sensing for the assessment of acute pain
Pain assessment is a challenging task encountered by clinicians. In clinical settings, patients’ self-report is considered the gold standard in pain assessment. However, patients who are unable to self-report pain are at a higher risk of undiagnosed pain. In the present study, we explore the use of...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-06-01
|
| Series: | Frontiers in Pain Research |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpain.2023.1150264/full |
| _version_ | 1797799421205807104 |
|---|---|
| author | Raul Fernandez Rojas Niraj Hirachan Nicholas Brown Gordon Waddington Gordon Waddington Luke Murtagh Ben Seymour Ben Seymour Roland Goecke |
| author_facet | Raul Fernandez Rojas Niraj Hirachan Nicholas Brown Gordon Waddington Gordon Waddington Luke Murtagh Ben Seymour Ben Seymour Roland Goecke |
| author_sort | Raul Fernandez Rojas |
| collection | DOAJ |
| description | Pain assessment is a challenging task encountered by clinicians. In clinical settings, patients’ self-report is considered the gold standard in pain assessment. However, patients who are unable to self-report pain are at a higher risk of undiagnosed pain. In the present study, we explore the use of multiple sensing technologies to monitor physiological changes that can be used as a proxy for objective measurement of acute pain. Electrodermal activity (EDA), photoplethysmography (PPG), and respiration (RESP) signals were collected from 22 participants under two pain intensities (low and high) and on two different anatomical locations (forearm and hand). Three machine learning models were implemented, including support vector machines (SVM), decision trees (DT), and linear discriminant analysis (LDA) for the identification of pain. Various pain scenarios were investigated, identification of pain (no pain, pain), multiclass (no pain, low pain, high pain), and identification of pain location (forearm, hand). Reference classification results from individual sensors and from all sensors together were obtained. After feature selection, results showed that EDA was the most informative sensor in the three pain conditions, 93.2±8% in identification of pain, 68.9±10% in the multiclass problem, and 56.0±8% for the identification of pain location. These results identify EDA as the superior sensor in our experimental conditions. Future work is required to validate the obtained features to improve its feasibility in more realistic scenarios. Finally, this study proposes EDA as a candidate to design a tool that can assist clinicians in the assessment of acute pain of nonverbal patients. |
| first_indexed | 2024-03-13T04:19:36Z |
| format | Article |
| id | doaj.art-4c6216324b0946dcacbe3595732a69c7 |
| institution | Directory Open Access Journal |
| issn | 2673-561X |
| language | English |
| last_indexed | 2024-03-13T04:19:36Z |
| publishDate | 2023-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Pain Research |
| spelling | doaj.art-4c6216324b0946dcacbe3595732a69c72023-06-20T13:52:14ZengFrontiers Media S.A.Frontiers in Pain Research2673-561X2023-06-01410.3389/fpain.2023.11502641150264Multimodal physiological sensing for the assessment of acute painRaul Fernandez Rojas0Niraj Hirachan1Nicholas Brown2Gordon Waddington3Gordon Waddington4Luke Murtagh5Ben Seymour6Ben Seymour7Roland Goecke8Human-Centred Technology Research Centre, Faculty of Science and Technology, University of Canberra, Canberra, ACT, AustraliaHuman-Centred Technology Research Centre, Faculty of Science and Technology, University of Canberra, Canberra, ACT, AustraliaFaculty of Health, Queensland University of Technology, Brisbane, QLD, AustraliaAustralian Institute of Sport, Canberra, ACT, AustraliaUniversity of Canberra Research Institute for Sport and Exercise (UCRISE), University of Canberra, Canberra, ACT, AustraliaDepartment of Anaesthesia, Pain and Perioperative Medicine, The Canberra Hospital, Canberra, ACT, AustraliaWellcome Centre for Integrative Neuroimaging, University of Oxford, John Radcliffe Hospital, Headington, UKOxford Institute for Biomedical Engineering, University of Oxford, Headington, UKHuman-Centred Technology Research Centre, Faculty of Science and Technology, University of Canberra, Canberra, ACT, AustraliaPain assessment is a challenging task encountered by clinicians. In clinical settings, patients’ self-report is considered the gold standard in pain assessment. However, patients who are unable to self-report pain are at a higher risk of undiagnosed pain. In the present study, we explore the use of multiple sensing technologies to monitor physiological changes that can be used as a proxy for objective measurement of acute pain. Electrodermal activity (EDA), photoplethysmography (PPG), and respiration (RESP) signals were collected from 22 participants under two pain intensities (low and high) and on two different anatomical locations (forearm and hand). Three machine learning models were implemented, including support vector machines (SVM), decision trees (DT), and linear discriminant analysis (LDA) for the identification of pain. Various pain scenarios were investigated, identification of pain (no pain, pain), multiclass (no pain, low pain, high pain), and identification of pain location (forearm, hand). Reference classification results from individual sensors and from all sensors together were obtained. After feature selection, results showed that EDA was the most informative sensor in the three pain conditions, 93.2±8% in identification of pain, 68.9±10% in the multiclass problem, and 56.0±8% for the identification of pain location. These results identify EDA as the superior sensor in our experimental conditions. Future work is required to validate the obtained features to improve its feasibility in more realistic scenarios. Finally, this study proposes EDA as a candidate to design a tool that can assist clinicians in the assessment of acute pain of nonverbal patients.https://www.frontiersin.org/articles/10.3389/fpain.2023.1150264/fullPaindata fusionphysiologymachine learningnon-verbalEDA |
| spellingShingle | Raul Fernandez Rojas Niraj Hirachan Nicholas Brown Gordon Waddington Gordon Waddington Luke Murtagh Ben Seymour Ben Seymour Roland Goecke Multimodal physiological sensing for the assessment of acute pain Frontiers in Pain Research Pain data fusion physiology machine learning non-verbal EDA |
| title | Multimodal physiological sensing for the assessment of acute pain |
| title_full | Multimodal physiological sensing for the assessment of acute pain |
| title_fullStr | Multimodal physiological sensing for the assessment of acute pain |
| title_full_unstemmed | Multimodal physiological sensing for the assessment of acute pain |
| title_short | Multimodal physiological sensing for the assessment of acute pain |
| title_sort | multimodal physiological sensing for the assessment of acute pain |
| topic | Pain data fusion physiology machine learning non-verbal EDA |
| url | https://www.frontiersin.org/articles/10.3389/fpain.2023.1150264/full |
| work_keys_str_mv | AT raulfernandezrojas multimodalphysiologicalsensingfortheassessmentofacutepain AT nirajhirachan multimodalphysiologicalsensingfortheassessmentofacutepain AT nicholasbrown multimodalphysiologicalsensingfortheassessmentofacutepain AT gordonwaddington multimodalphysiologicalsensingfortheassessmentofacutepain AT gordonwaddington multimodalphysiologicalsensingfortheassessmentofacutepain AT lukemurtagh multimodalphysiologicalsensingfortheassessmentofacutepain AT benseymour multimodalphysiologicalsensingfortheassessmentofacutepain AT benseymour multimodalphysiologicalsensingfortheassessmentofacutepain AT rolandgoecke multimodalphysiologicalsensingfortheassessmentofacutepain |