Project overview
This project will both develop and validate population clusters that consider health and social care determinants and subsequent need for people with MLTC using data-driven Artificial Intelligence (AI) methods, which will be compared with expert-driven approaches to validate efficacy of the machine learning methodology. This will be followed by evaluation of cluster trajectories and efficacy in relation to improved health outcomes and reduction in costs/resources.
Background
An estimated 14 million people in England are living with multiple long-term health conditions (MLTC). Efforts to improve care mainly focus on biological markers or medical features of disease such as blood pressure or cholesterol, without adequately addressing other non-medical factors that contribute to good health. This may include social, economic and environmental factors such as mobility, housing conditions, finances or social isolation.
A shift towards integrated care that considers the ‘whole person’ and their environment is essential in addressing the complex individual needs of people living with MLTC. One approach to delivering more personalised care is to 'cluster' or group people based on similarities in their medical and non-medical needs. This approach has been adopted in other countries but not in the UK due to uncertainty about how to develop clusters, and a lack of evidence linking this approach to improved health or reduced costs.
Aims
1. To generate evidence on how to cluster people by health and social need using machine learning, in other words, we will use a computer system to help us identify and group people with similar needs together.
2. To use this information to develop tailored approaches for clusters that join up health and social care, and in doing so, improve the lives of people with MLTC.
Methods
1. We will undertake interviews to ask patients, carers and professionals for their views on what is important in MLTC when considering both medical and social needs.
2. We will bring together a panel of lay people, professionals and experts to ask for their views on what medical and non-medical factors are key to improving the care, and addressing the wider needs, of people with multiple long term conditions.
3. We will use millions of anonymised patient records to test machine learning and generate clusters that will be compared to those developed through patient/professional opinions to see which are better at predicting outcomes.
4. We will study clusters to learn what happens over time in terms of health/social costs, and to understand the profiles of people within each cluster.
5. We will use this information to develop tailored care for each cluster for people with MLTC.
Our findings
We will make our findings available and accessible to people with MLTC, and those who work and make decisions in health and social care. We will co-host information events with a range of audiences to share the results and discuss the wider implications for improving the health and social care of people experiencing MLTC.
Ethics Number 67953
Background
An estimated 14 million people in England are living with multiple long-term health conditions (MLTC). Efforts to improve care mainly focus on biological markers or medical features of disease such as blood pressure or cholesterol, without adequately addressing other non-medical factors that contribute to good health. This may include social, economic and environmental factors such as mobility, housing conditions, finances or social isolation.
A shift towards integrated care that considers the ‘whole person’ and their environment is essential in addressing the complex individual needs of people living with MLTC. One approach to delivering more personalised care is to 'cluster' or group people based on similarities in their medical and non-medical needs. This approach has been adopted in other countries but not in the UK due to uncertainty about how to develop clusters, and a lack of evidence linking this approach to improved health or reduced costs.
Aims
1. To generate evidence on how to cluster people by health and social need using machine learning, in other words, we will use a computer system to help us identify and group people with similar needs together.
2. To use this information to develop tailored approaches for clusters that join up health and social care, and in doing so, improve the lives of people with MLTC.
Methods
1. We will undertake interviews to ask patients, carers and professionals for their views on what is important in MLTC when considering both medical and social needs.
2. We will bring together a panel of lay people, professionals and experts to ask for their views on what medical and non-medical factors are key to improving the care, and addressing the wider needs, of people with multiple long term conditions.
3. We will use millions of anonymised patient records to test machine learning and generate clusters that will be compared to those developed through patient/professional opinions to see which are better at predicting outcomes.
4. We will study clusters to learn what happens over time in terms of health/social costs, and to understand the profiles of people within each cluster.
5. We will use this information to develop tailored care for each cluster for people with MLTC.
Our findings
We will make our findings available and accessible to people with MLTC, and those who work and make decisions in health and social care. We will co-host information events with a range of audiences to share the results and discuss the wider implications for improving the health and social care of people experiencing MLTC.
Ethics Number 67953
Staff
Lead researcher
Other researchers
Research outputs
Ralph K Akyea,
Jon Gibson,
Jonathan Stokes,
Beth Stuart,
Francesco Zaccardi,
Zlatko Zlatev,
Karen Jones,
Paul Roderick,
& Andrew Farmer
, 2022
, JMIR Research Protocols
, 11 (6)
DOI: 10.2196/34405
Type: article