<?xml version="1.0" encoding="UTF-8"?><ns2:project xmlns:ns1="http://gtr.rcuk.ac.uk/gtr/api" xmlns:ns2="http://gtr.rcuk.ac.uk/gtr/api/project" xmlns:ns3="http://gtr.rcuk.ac.uk/gtr/api/fund" xmlns:ns4="http://gtr.rcuk.ac.uk/gtr/api/person" xmlns:ns5="http://gtr.rcuk.ac.uk/gtr/api/project/outcome" xmlns:ns6="http://gtr.rcuk.ac.uk/gtr/api/organisation" ns1:created="2026-06-03T15:52:43Z" ns1:href="http://gtr.ukri.org/gtr/api/projects/88769ADC-4897-4DA2-8F72-34EC782DA0A6" ns1:id="88769ADC-4897-4DA2-8F72-34EC782DA0A6"><ns1:links><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/persons/1718981A-FFA6-4B6A-8E17-978E016E9E41" ns1:rel="PM_PER"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/83F38FC9-FDC6-48BC-B7C9-29C6918B8449" ns1:rel="LEAD_ORG"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/83F38FC9-FDC6-48BC-B7C9-29C6918B8449" ns1:rel="PARTICIPANT_ORG"/><ns1:link ns1:end="2026-04-29T23:00:00Z" ns1:href="http://gtr.ukri.org/gtr/api/funds/0CF7FF52-13BA-4AA0-8063-425522FF47DD" ns1:rel="FUND" ns1:start="2025-11-01T00:00:00Z"/></ns1:links><ns2:identifiers><ns2:identifier ns2:type="RCUK">10171061</ns2:identifier></ns2:identifiers><ns2:title>AI-Guided Dementia Care: Predicting Behaviour to Prevent Distress</ns2:title><ns2:status>Closed</ns2:status><ns2:grantCategory>Fast Start Response</ns2:grantCategory><ns2:leadFunder>Innovate UK</ns2:leadFunder><ns2:abstractText>People living with dementia often struggle to communicate their needs, leading to distressed behaviours such as aggression, agitation, or withdrawal. Supporting these behaviours is one of the biggest challenges faced by caregivers and care providers, resulting in continued unmet needs, placement breakdowns, and over-reliance on antipsychotic medication. In many cases, distressed behaviours are preventable with the right support at the right time.

This project will develop a prototype of a digital service that helps predict and prevent distressed behaviour in people living with dementia. The service combines behavioural science with artificial intelligence to help caregivers understand why a behaviour might be happening, and what they can do in the moment to help prevent distressed behaviour. This is not a replacement for existing care systems, but a valuable addition that provides meaningful, person-centred insights and support, particularly where access to dementia behaviour specialists is limited.

The prototype will be developed and tested in partnership with a residential care home in the UK. We have had several care home chains and care app software providers across the UK express an interest in being part of the testing phase via our partnership with Alzheimer's Society. It will explore how routine care data, such as daily activities, care notes, or environmental factors, might be used to identify early warning signs and offer tailored suggestions for preventing distress. The tool will also act like an on-the-job guide, offering simple, practical tips that help care staff feel more confident, less stressed, and better able to support the people they care for.

This work will explore how artificial intelligence can be responsibly used to improve outcomes for people who may struggle to communicate their needs. It supports the wider ambition of making dementia care more compassionate, personalised, and effective, while easing pressure on an overstretched care workforce.

The project is led by Dr Emma Williams, one of only 80 specialists worldwide focused on distressed behaviour in dementia, with over 25 years of hands-on experience in care and behaviour analysis.</ns2:abstractText></ns2:project>