Multimodal physiological sensing for the assessment of acute pain

Raul Fernandez Rojas; Niraj Hirachan; Nicholas Brown; Gordon Waddington; Luke Murtagh; Ben Seymour; Roland Goecke

doi:10.3389/fpain.2023.1150264

Multimodal physiological sensing for the assessment of acute pain

Front Pain Res (Lausanne). 2023 Jun 19:4:1150264. doi: 10.3389/fpain.2023.1150264. eCollection 2023.

Authors

Raul Fernandez Rojas¹, Niraj Hirachan¹, Nicholas Brown², Gordon Waddington^{3

4}, Luke Murtagh⁵, Ben Seymour^{6

7}, Roland Goecke¹

Affiliations

¹ Human-Centred Technology Research Centre, Faculty of Science and Technology, University of Canberra, Canberra, ACT, Australia.
² Faculty of Health, Queensland University of Technology, Brisbane, QLD, Australia.
³ Australian Institute of Sport, Canberra, ACT, Australia.
⁴ University of Canberra Research Institute for Sport and Exercise (UCRISE), University of Canberra, Canberra, ACT, Australia.
⁵ Department of Anaesthesia, Pain and Perioperative Medicine, The Canberra Hospital, Canberra, ACT, Australia.
⁶ Wellcome Centre for Integrative Neuroimaging, University of Oxford, John Radcliffe Hospital, Headington, UK.
⁷ Oxford Institute for Biomedical Engineering, University of Oxford, Headington, UK.

Abstract

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, $93.2 \pm 8 %$ in identification of pain, $68.9 \pm 10 %$ in the multiclass problem, and $56.0 \pm 8 %$ 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.

Keywords: EDA; Pain; data fusion; machine learning; non-verbal; physiology.