Personalising domiciliary dementia care via co-designed computational matching: a study protocol

The delivery of person-centred dementia care in community settings is undermined by high levels of care worker stress, burnout, and turnover. Improving the experience of domiciliary care for all stakeholders is paramount. Previous research suggests that matching the skills and characteristics of care workers to the needs and preferences of people living with dementia can enhance the quality of domiciliary care. This study aims to personalise domiciliary care through the co-design and development of an empirically informed novel Web platform that, through machine learning, matches the preferences of people living with dementia, to their family/friend supporters and care providers. It will also enable ‘live’, needs-informed rostering. Our study is novel in how it will enable evidence-informed and co-production-based design, meaningfully and extensively involving people living with dementia throughout. This interdisciplinary study will consist of three work packages (WPs): WP1 - a review summarising evidence on what 'good' domiciliary care is for key stakeholder groups; WP2 - eight focus groups with key stakeholder groups of community-dwelling people with dementia, their supporters, and domiciliary care professionals; and WP3 - the iterative co-design of the platform, which will involve co-design workshops with representatives from key stakeholder groups, iterative development of the computational elements of the platform, and development of the interface. Intersectoral costs and outcomes will be considered throughout the project, which will inform a full economic evaluation in the future. We will document the development process, and pursue additional funding for further development and pilot-testing of the prototype. The study will commence in September 2024 and is jointly funded by the National Institute for Health Research and the Alzheimer’s Society.