UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Falls Prediction in Care Homes Using Mobile App Data Collection

Dvir, O; Wolfson, P; Lovat, L; Moskovitch, R; (2020) Falls Prediction in Care Homes Using Mobile App Data Collection. In: Michalowski, M and Moskovitch, R, (eds.) Artificial Intelligence in Medicine: 18th International Conference on Artificial Intelligence in Medicine, AIME 2020, Minneapolis, MN, USA, August 25–28, 2020, Proceedings. (pp. pp. 403-413). Springer: Cham, Switzerland. Green open access

[thumbnail of AIME_2020__Falls Prediction in Care Homes Using Mobile.pdf]
Preview
Text
AIME_2020__Falls Prediction in Care Homes Using Mobile.pdf - Accepted version

Download (559kB) | Preview

Abstract

Falls are one of the leading causes of unintentional injury related deaths in older adults. Although, falls among elderly is a well documented phenomena; falls of care homes’ residents was under-researched, mainly due to the lack of documented data. In this study, we use data from over 1,769 care homes and 68,200 residents across the UK, which is based on carers who routinely documented the residents’ activities, using the Mobile Care Monitoring mobile app over three years. This study focuses on predicting the first fall of elderly living in care homes a week ahead. We intend to predict continuously based on a time window of the last weeks. Due to the intrinsic longitudinal nature of the data and its heterogeneity, we employ the use of Temporal Abstraction and Time Intervals Related Patterns discovery, which are used as features for classification. We had designed an experiment that reflects real-life conditions to evaluate the framework. Using four weeks of observation time window performed best.

Type: Proceedings paper
Title: Falls Prediction in Care Homes Using Mobile App Data Collection
Event: 18th International Conference on Artificial Intelligence in Medicine, AIME 2020
ISBN-13: 9783030591366
Open access status: An open access version is available from UCL Discovery
DOI: 10.1007/978-3-030-59137-3_36
Publisher version: https://doi.org/10.1007/978-3-030-59137-3_36
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Temporal data mining, Outcomes prediction, Falls prediction
UCL classification: UCL
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Medical Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Medical Sciences > Div of Surgery and Interventional Sci
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Medical Sciences > Div of Surgery and Interventional Sci > Department of Targeted Intervention
URI: https://discovery.ucl.ac.uk/id/eprint/10115379
Downloads since deposit
3Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item