Use this URL to cite or link to this record in EThOS: https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.745670
Title: Applying digital technology to the prediction of depression and anxiety in older adults
Author: Andrews, Jacob A.
ISNI:       0000 0004 7226 7716
Awarding Body: University of Sheffield
Current Institution: University of Sheffield
Date of Award: 2018
Availability of Full Text:
Access from EThOS:
Access from Institution:
Abstract:
Background: Many older adults fail to seek treatment for depression and anxiety before crises occur due to stigma or misperception of the conditions as signs of ageing. The research presented in this thesis aimed to explore the potential application of machine learning and digital technology to predict future depression and anxiety status in older adults, in order to permit earlier intervention. Method: A narrative review and two mapping reviews were conducted to provide context and characterise existing literature in the area. Secondary data consisting of 40 older adults' self-reported mood and appetite scores were analysed with machine learning techniques to predict depression status according to the Geriatric Depression Scale (GDS) at nine weeks' follow-up. Primary data were then collected from 38 older people to validate the models developed earlier, and to develop a new model for the prediction of anxiety. Interactive group sessions were held with 15 older adults to explore their views on the use of digital technology to support mental health. Interviews were conducted with community healthcare staff to consider implementation in healthcare. Results: The predictive models had high predictive ability compared to studies presented in the mapping review. Using machine learning to predict anxiety status did not generate a useful model for this sample, suggesting the input data were not appropriate for this purpose. Interactive sessions with older adults raised important issues on usability and motivation. Interviews with healthcare staff permitted an exploration of existing practices and prior implementation of technology in a community healthcare setting. Conclusions: The work in this thesis has contributed to knowledge by proposing a new method of predicting depression and anxiety in older adults, and has demonstrated the potential of this approach. This is supported by an exploration of older adults' views of using digital technology to monitor mood and manage mental health, which has not been completed in prior work. The contribution of the work is further strengthened by the inclusion of a study which considers the implementation of the approach.
Supervisor: Hawley, Mark ; Harrison, Robert ; Brown, Laura ; Astell, Arlene Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID: uk.bl.ethos.745670  DOI: Not available
Share: