TAME Pain: Trustworthy AssessMEnt of Pain from Speech and Audio for the Empowerment of Patients

Schneiders, Eike; Williams, Jennifer; Farahi, Arya; Seabrooke, Tina; Vigneswaran, Ganesh; Bautista, John Robert; Dowthwaite, Liz; Piskopani, Anna Maria

Abstract

Precise pain assessment is crucial for medical professionals to provide appropriate treatment. However, not every patient can verbalise the experienced pain for various reasons (e.g., speech disorders or language barriers). In these cases, medical practitioners must provide treatment based on non-verbal signs. The TAME Pain project aims to provide medical professionals with an additional pain assessment tool using audio analysis. We seek to develop an algorithm that functions as an autonomous system and evaluate its trustworthiness. This proof-of-concept study will investigate whether the acoustic signal extracted from healthy individuals subjected to pain can predict pain accurately. We will assess the system's trustworthiness by surveying medical professionals. By comparing their assessments with and without our algorithm against pain levels reported by the participants, we evaluate the trustworthiness and feasibility of clinical implementation. Our project aims at empowering patients, including non-verbal and second-language speakers. Our work also supports healthcare professionals with an accessible decision support tool, ultimately reducing the risk of potential physical harm and improving patient experience. This paper describes the planned study to collect data for the system that assesses bioacoustic pain markers in the speech signal and outlines our project plan for achieving this.

Citation

Schneiders, E., Williams, J., Farahi, A., Seabrooke, T., Vigneswaran, G., Bautista, J. R., Dowthwaite, L., & Piskopani, A. M. (2023, July). TAME Pain: Trustworthy AssessMEnt of Pain from Speech and Audio for the Empowerment of Patients. Presented at TAS'23: First International Symposium on Trustworthy Autonomous Systems, Edinburgh, UK

• Presentation Conference Type: Edited Proceedings
• Conference Name: TAS'23: First International Symposium on Trustworthy Autonomous Systems
• Start Date: Jul 11, 2023
• End Date: Jul 12, 2023
• Acceptance Date: May 14, 2023
• Online Publication Date: Jul 11, 2023
• Publication Date: Jul 11, 2023
• Deposit Date: Aug 8, 2023
• Series Title: International Symposium on Trustworthy Autonomous Systems
• Book Title: TAS'23: Proceedings of the First International Symposium on Trustworthy Autonomous Systems
• ISBN: 9798400707346
• DOI: https://doi.org/10.1145/3597512.3597513
• Public URL: https://nottingham-repository.worktribe.com/output/22726797
• Publisher URL: https://dl.acm.org/doi/abs/10.1145/3597512.3597513
• Additional Information: Article No. 27