Joe Jeffcock
Transformers and human-robot interaction for delirium detection
Jeffcock, Joe; Hansen, Mark; Ruiz Garate, Virginia
Authors
Mark Hansen Mark.Hansen@uwe.ac.uk
Professor of Machine Vision and Machine Learning
Virginia Ruiz Garate
Abstract
An estimated 20% of patients admitted to hospital wards are affected by delirium. Early detection is recommended to treat underlying causes of delirium, however workforce strain in general wards often causes it to remain undetected. This work proposes a robotic implementation of the Confusion Assessment Method for the Intensive Care Unit (CAM-ICU) to aid early detection of delirium. Interactive features of the assessment are performed by Human-robot Interaction while a Transformer-based deep learning model predicts the Richmond Agitation Sedation Scale (RASS) level of the patient from image sequences; thermal imaging is used to maintain patient anonymity. A user study involving 18 participants role-playing each of alert, agitated, and sedated levels of the RASS is performed to test the HRI components and collect a dataset for deep learning. The HRI system achieved accuracies of 1.0 and 0.833 for the inattention and disorganised thinking features of the CAM-ICU, respectively, while the trained action recognition model achieved a mean accuracy of 0.852 on the classification of RASS levels during cross-validation. The three features represent a complete set of capabilities for automated delirium detection using the CAM-ICU, and the results demonstrate the feasibility of real-world deployment in hospital general wards.
Citation
Jeffcock, J., Hansen, M., & Ruiz Garate, V. (2023). Transformers and human-robot interaction for delirium detection. In 2023 ACM/IEEE International Conference on Human-Robot Interaction (466-474). https://doi.org/10.1145/3568162.3576971
Conference Name | HRI '23: Proceedings of 2023 ACM/IEEE International Conference on Human-Robot Interaction |
---|---|
Conference Location | Stockholm, Sweden |
Start Date | Mar 13, 2023 |
End Date | Mar 16, 2023 |
Acceptance Date | Feb 12, 2022 |
Online Publication Date | Mar 13, 2023 |
Publication Date | Mar 13, 2023 |
Deposit Date | Apr 26, 2023 |
Publicly Available Date | Apr 26, 2023 |
Publisher | Association for Computing Machinery (ACM) |
Pages | 466-474 |
Book Title | 2023 ACM/IEEE International Conference on Human-Robot Interaction |
DOI | https://doi.org/10.1145/3568162.3576971 |
Keywords | Transformers; human-robot interaction; delirium detection |
Public URL | https://uwe-repository.worktribe.com/output/10582571 |
Publisher URL | https://dl.acm.org/doi/10.1145/3568162.3576971 |
Related Public URLs | https://dl.acm.org/doi/proceedings/10.1145/3568162 |
Files
Transformers and human-robot interaction for delirium detection
(1.1 Mb)
PDF
Licence
http://www.rioxx.net/licenses/all-rights-reserved
Publisher Licence URL
http://www.rioxx.net/licenses/all-rights-reserved
Copyright Statement
This is the authors accepted manuscript of the article ‘Jeffcock, J., Hansen, M., & Ruiz Garate, V. (2023). Transformers and human-robot interaction for delirium detection. In 2023 ACM/IEEE International Conference on Human-Robot Interaction (466–474)’. DOI: https://doi.org/10.1145/3568162.3576971
The final published version is available here: https://dl.acm.org/doi/10.1145/3568162.3576971
You might also like
Open-source re-configurable interfacing of Tobii Pro Glasses 2 with ROS2
(2022)
Presentation / Conference
The case for an intervention scale to design the balance of authority for robotic assistance
(2021)
Conference Proceeding
A probabilistic shared-control framework for mobile robots
(2020)
Conference Proceeding
Downloadable Citations
About UWE Bristol Research Repository
Administrator e-mail: repository@uwe.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2024
Advanced Search