The Alan Turing Institute, in conjunction with Swansea University, MRC Harwell and the University of Edinburgh, is developing data standards, disseminating best practices, and building community around researchers, patients and the public involved in AI for multiple long-term conditions research.
The innovative Research Support Facility is part of a £23 million investment by the NIHR in AI, and will connect researchers across the consortia, to ensure the investment delivers long-term, real-world impact for the programme and beyond.
Explaining the science
The new Research Support Facility (RSF), based at the Turing in conjunction with Swansea University, University of Edinburgh and MRC Harwell, will offer AI and advanced data science support to the research teams funded by AIM and foster collaboration. The facility, led by Dr Kirstie Whitaker and Professor Chris Holmes, will embed best practices in data security and standards, reproducibility, and public and patient engagement across the research collaborations funded by the programme, ensuring effective knowledge sharing and reinforcing the Turing’s role as a national convenor and capacity builder in data science and artificial intelligence.
The Research Support Facility work is split across five, interconnected themes:
Theme 1: Reproducible, secure and interoperable infrastructure
This theme will bring different research collaborations across the UK together within a trusted research environment to facilitate data, software and analysis sharing. This will support a progressive move from reproducible, to reproduced, to reused research artefacts and outputs, maximizing the return on the NIHR’s investment in the overall research programme.
Theme 2: Accessible, research ready data
Data wranglers, experts in data curation and quality control, will work with the Research Collaborations to align datasets and standards. This will enable a broad range of data to be incorporated into extended analyses within AIM and beyond.
Theme 3: Community building and training
This theme aims to build connections between early career researchers across the AIM programme so their existing expertise can be shared across AIM and into the wider network. The other core aspect of the theme will be training and mentorship in the digital skills researchers need to deliver open source outputs from their Research Collaborations.
Theme 4: Patient and public involvement and engagement
Enhancing existing patient and public involvement networks across the AIM programme, this theme will support and empower people with lived experience of MLTC to co-create the research with the teams. Online engagement activities such as talks and seminars that are accessible to all will set the standard for patient involvement in other healthcare areas in the future.
Theme 5: Sustainability and legacy
This theme will work with researchers to embed outputs in existing communities, both clinical and academic, and engage with policy makers to coordinate a long term investment in MLTC research. It is a key part of ensuring that AIM research continues beyond the end of this specific investment and the impact of the work conducted benefits as many people as possible.
An estimated 14 million people in England are living with two or more long-term conditions, with two-thirds of adults aged over 65 expected to be living with multiple long-term conditions by 2035.
People who develop multiple long-term conditions (MLTC) often do not have a random assortment of diseases but rather a largely predictable cluster of conditions. Developing a better understanding of these disease clusters, including how they develop over the course of a person’s life and are influenced by wider determinants of health, requir es novel research and analytical tools that can operate across complex datasets.
The Artificial Intelligence for Multiple Long-Term Conditions (AIM) call, from the National Institute for Health Research (NIHR), in partnership with NHSX, funds research that combines data science and AI methods with health, care and social science expertise to identify new clusters of disease and understand how multiple long-term conditions develop over the life course.