07 Jul 2025
A ground-breaking study using artificial intelligence (AI) has uncovered the significant role that loneliness plays in adults entering care homes earlier than necessary – highlighting a major opportunity for improving how social care is delivered and targeted.
In an NIHR-funded project, researchers from LSE analysed over one million free-text case notes from social care records in a London borough, covering more than 3,000 older adults from 2008 to 2020.
Using advanced AI-powered natural Large Language Models, they were able identify signs of loneliness and social isolation in care notes with 97% accuracy.
The resultant findings are striking:
- 44% of older people were identified as lonely or isolated during their first care assessment.
- Lonely individuals entered care homes around 7-9 months earlier than others with similar needs.
- Loneliness was the strongest predictor of use of day centres – services designed to promote social inclusion.
- There was also a strong link between loneliness and cognitive decline, such as memory problems.
Dr Sam Rickman of LSE’s Care Policy and Evaluation Centre, the study’s lead researcher, said:
“Loneliness is just as significant a risk factor for care home entry as living alone or even a person’s gender or ethnicity. But unlike many of those factors, it’s something we can change.”
“The social care system is under growing pressure, with rising demand and tight budgets. The implications of this study are that funding and retaining services that help reduce loneliness may reduce social care costs and pressure.
“Meanwhile, much of the information we hold about people’s care needs is locked away in hard-to-use text records. This research demonstrates that AI can unlock this data - providing insights that help local authorities better plan and target services, such as day centres, that may delay or prevent entry into expensive residential care.”
Beyond its findings on loneliness, the research offers a blueprint for future care data analysis. It shows how machine learning can extract valuable, structured information from vast volumes of text – saving time for social care staff, supporting better decisions, and improving the overall effectiveness of care systems.
The open-source tool used in the study is available for other councils, researchers, and developers to explore, adapt, and apply.
The findings are being shared with local policymakers, social care providers, and the Department of Health and Social Care, with the goal of informing future decisions on social care funding and service delivery.
This work was supported by the UK National Institute of Health and Care Research (NIHR) Policy Research Unit in Adult Social Care. Funding was also received from the NIHR Applied Research Collaboration (ARC) North Thames.
Explore both papers: