Sensor-based agitation prediction in institutionalized people with dementia A systematic review

Jan Kleine Deters, Sarah Janus, J.A. Lima Silva, Heinrich J. Wörtche, Sytse U. Zuidema

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Early detection of agitation in individuals with dementia can lead to timely interventions, preventing the worsening of situations and enhancing their quality of life. The emergence of multi-modal sensing and advances in artificial intelligence make it feasible to explore and apply technology for this goal. We conducted a literature review to understand the current technical developments and challenges of its integration in caregiving institutions. Our systematic review used the Pubmed and IEEE scientific databases, considering studies from 2017 onwards. We included studies focusing on linking sensor data to vocal and/or physical manifestations of agitation. Out of 1622 identified studies, 12 were selected for the final review. Analysis was conducted on study design, technology, decisional data, and data analytics. We identified a gap in the standardized semantic representation of both behavioral descriptions and system event generation configurations. This research highlighted initiatives that leverage existing information in a caregiver's routine, such as correlating electronic health records with sensor data. As predictive systems become more integrated into caregiving routines, false positive reduction needs to be addressed as those will discourage their adoption. Therefore, to ensure adaptive predictive capacity and personalized system re-configuration, we suggest future work to evaluate a framework that incorporates a human-in-the-loop approach for detecting and predicting agitation.
Original languageEnglish
Number of pages16
JournalPervasive and Mobile Computing
Volume98
DOIs
Publication statusPublished - Feb 2024

Keywords

  • agitation
  • behavior
  • dementia
  • long-term monitoring
  • sensor system

Fingerprint

Dive into the research topics of 'Sensor-based agitation prediction in institutionalized people with dementia A systematic review'. Together they form a unique fingerprint.

Cite this