AVACHAT: Co-design of an artificially intelligent virtual agent to support self-management in individuals with complex physical comorbidities

In this research project we have brought together expertise from three themes within the NIHR CLAHRC Yorkshire and Humber; Telehealth and Care Technologies, Mental Health and Comorbidities and Translating Knowledge into Action.

The problem: Individuals with physical long term health conditions are at a greater risk of experiencing common mental health problems, such as anxiety and depression, than are members of the general population. Not everyone who would benefit from support is able to access it; as supply of services is failing to meet demand. So patients are increasingly being encouraged to self-manage their health in their own homes. Managing your own health well can have significant positive implications, personally and economically.

What we are doing about it: Digitally technology may be able to support people to better self-manage their physical and emotional health. One potential technology for the delivery of personalised care is the autonomous virtual agent with speech-based natural language processing abilities.  We are working with patients, health professionals and an interdisciplinary team of researchers to co-develop the scope, content and functionality of an autonomous virtual agent prototype to support self-management for patients with an exemplar long-term condition (Chronic Pulmonary Obstructive Disease, COPD).

Workshops: We have now conducted two co-design workshops with patients, health professionals and computer scientists. In the first workshop we explored challenges of daily living and ways in which these challenges could be overcome. We critiqued existing avatar examples and designed our own ideal avatar.   

In the second workshop we role-played scenarios in order to develop content for the system. Finally, we conducted a proof-of-concept implementation, which was used in a video-based scenario testing of acceptability with older adults with a diagnosis of COPD and health professionals connected

with this patient group’s care in order further develop the prototype.

https://youtu.be/6rBAG-e9bXg


What does this mean? 
The prototype autonomous agent has been developed through co-design techniques. Future research is planned to further develop and evaluate the system for a range of patient samples and care settings. Clinical applications are broad. The impact of such a system could include personal gains in self-efficacy and self-confidence, reduction in social isolation, increased illness knowledge and better coping mechanisms. Clinical gains could include fewer exacerbations of condition and a decrease in unnecessary formal healthcare service utilisation.

This research was funded and supported by the National Institute for Health Research (NIHR) Collaboration for Leadership in Applied Health Research and Care Yorkshire and Humber. The views and opinions expressed are those of the authors and are not necessarily those of the NHS, the NIHR, or the Department of Health, United Kingdom.




Project team:
Principal Investigator: Mark Hawley
Centre for Assistive Technology and Connected Healthcare (CATCH), University of Sheffield, UK
School of Health and Related Research (ScHARR) University of Sheffield, UK

Co-Investigators: 
Katherine Easton
Centre for Assistive Technology and Connected Healthcare (CATCH), University of Sheffield, UK
School of Health and Related Research (ScHARR) University of Sheffield, UK

Heidi Christensen 
Centre for Assistive Technology and Connected Healthcare (CATCH), University of Sheffield, UK
Department of Computer Science, University of Sheffield, UK

Stephen Potter
Centre for Assistive Technology and Connected Healthcare (CATCH), University of Sheffield, UK
School of Health and Related Research (ScHARR) University of Sheffield, UK

Scott Weich 
School of Health and Related Research (ScHARR) University of Sheffield, UK

Luc de Witte 
Centre for Assistive Technology and Connected Healthcare (CATCH) and University of Sheffield, UK

Dan Wolstenholme, Cheryl Grindell and Remi Bec 
NIHR CLAHRC Yorkshire and Humber

Matthew Bennion
Centre for Assistive Technology and Connected Healthcare (CATCH), University of Sheffield, UK
Department of Psychology, University of Sheffield, UK

Bahman Mirheidari
Department of Computer Science, University of Sheffield, UK