12 million to support data science and AI in health and social care
The National Institute for Health Research (NIHR) has awarded almost £12 million to new research that will use advanced data science and artificial intelligence (AI) methods to identify and understand clusters of multiple long-term conditions and develop ways to prevent and treat them.
An estimated 14 million people in England are living with two or more long-term conditions, with two-thrids of adults aged over 65 expected to be living with multiple long-term conditions by 2035.
People who develop multiple long-term conditions 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, requires novel research and analytical tools that can operate across complex datasets.
The Artificial Intelligence for Multiple Long-Term Conditions (AIM) call, in partnership with NHSX NHS AI Lab, 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.
The call will fund up to £23 million of research in two waves, supporting a pipeline of research and capacity building in multiple long-term conditions research. The first wave has invested nearly £12 million into three Research Collaborations, nine Development Awards and a Research Support Facility.
Artificial Intelligence and Multimorbidity: Clustering in Individuals, Space and Clinical Context (AIM-CISC)
Professor Bruce Guthrie will lead one of the three Research Collaborations with the support of Research Training Centre Director, Dr Alan Marshall. The Artificial Intelligence and Multimorbidity: Clustering in Individuals, Space and Clinical Context (AIM-CISC) project will identify the most common clusters of long-term conditions and examine whether people inherit a tendency to get particular combinations of conditions from their parents. It will also consider how socioeconomic and geographical factors contribute to multiple long-term conditions.
Dr Alan Marshall will lead a programme of research that will model the ways in which patterns of different morbidities (or health problems) vary systematically across places and communities. The project will exploit data from the Scottish Longitudinal Study and Dataloch (a repository of administrative health data) linked to individual’s Unique Property Reference Number to connect to finer geographical areas than in much of the existing research. Collaborations with colleagues in Geography and Informatics will drive new measures of the characteristics of place such as area reputation and stigma as informed by natural language processing of media and social media data.
The collaboration will develop new methods to help GPs or hospital doctors predict when a patient might be at high risk of adverse outcomes because they have other conditions, and develop new models of care to improve the outcomes of those at highest risk.