MELD-B project
Watch our animation
Our aim and plan
Our aim
To use an Artificial Intelligence (AI) enhanced analysis of birth cohort data and electronic health records to identify lifecourse time points and targets for the prevention of early-onset, burdensome MLTC-M.
Our plan
-
Undertake a qualitative evidence synthesis and a consensus study (Delphi) to develop deeper understanding of what ‘burdensomeness’ and ‘complexity’ mean to people living with early-onset (by age 65) MLTC-M, carers and healthcare professionals
2. Develop a safe data environments and readiness for AI analyses across large, representative routine healthcare datasets and birth cohorts.
3. In those safe data environments, using the WP1 burdensomeness/complexity indicators and applying AI methods, identify novel early-onset, burdensome MLTC-M clusters. Also in this work package, we will match individuals in birth cohorts into routine data MLTC-M clusters and then identify determinants of burdensome clusters and model trajectories of long-term conditions (LTCs) and burden accrual.
4. By characterising clusters of early-life (pre-birth to 18 years) risk factors for early-onset, burdensome MLTC-M and sentinel conditions (the first LTC to occur in the lifecourse), we will define population groups in early life at risk of future MLTC-M, identify critical time points and targets for prevention, and model counterfactual prevention scenarios of interventions acting on combined risk factors at key timepoints.
5. Engage key stakeholders to prioritise timepoints and targets to prevent/delay specified sentinel conditions and early-onset, burdensome MLTC-M. Partnering with our PPI Advisory Board, and through further stakeholder engagement, we will co-produce public health implementation recommendations
Frequently Asked Questions (FAQs)
What do people often ask us?
By the National Institute of Health and Care Research as part of its AI for Multiple Long-term Conditions funding call.
MELD-B ends at the end of November 2025.
We hope to continue related work after that time depending on success in funding applications
AI stands for artificial intelligence, which is an umbrella term for computational techniques that carry out tasks in a way that mimics human intelligence. AI can also be thought of as a collection of methods for analysing data computationally.
In MELD-B we are using AI to cluster people with similar patterns of burden and to analyse whether the timing and order of acquiring long-term conditions makes a difference to burden outcomes.
Work packages are a way of describing discrete components of a research study. They are often used in large research studies like MELD-B to break up the work into manageable areas, often using different methodologies.
In MELD-B we have five work packages. For example Work Package one is working on a qualitative evidence syntheses and a Delphi consensus study, while work package three is working on AI analyses in big datasets.
MELD-B aims to understand more about the things that influence whether people develop multiple long-term conditions over their lifetime and the impact this has on their lives. The number of people with multiple long-term conditions is growing and the NHS and social care are struggling to cope with the growing demand.
Prevention is an extremely important part of the solution to this and MELD-B hopes to identify the most important times in life, particularly early in life, when intervening might reduce the risk.
This matters to the public because we can help to reduce the impact not only for ourselves, but for our children and grandchildren, as well as protecting the NHS and social care from being overwhelmed in the future.
MELD-B is interested in all types of long-term conditions. Information such as when they are diagnosed and the impact that specific combinations of conditions have on people over time will be studied carefully. As the research develops, combinations of specific conditions may emerge that become of particular interest due to their association with early life factors or due to the age they begin and the amount of impact they have on people’s lives.
Our active Patient and Public Involvement and Engagement (PPIE) team members are integral to the development of the research and success of the study. They help shape the things we focus on, how we communicate our findings to other people, and ensure we maximise our impact. Our PPIE members have helped develop videos, web content, policy briefs and attended conferences.
MELD-B is a collaboration between University of Southampton, Swansea University, University of Aberdeen, University of Glasgow, Kings College London, and Southampton City Council.