INFLAMMATION, NUTRITION, AND THE EVOLUTION OF MULTIPLE LONG TERM CONDITIONS – AN AI-BASED ANALYSIS OF INTERSECTIONALITY IN LONGITUDINAL HEALTH DATA (THE INFLAIM PROJECT)

We aim to understand why some people are more prone than others to developing multiple long term medical conditions (MLTC) and why differences exist across communities.
Specifically:
 Does exposure to chronic inflammation allow us to predict MLTC?
 Do factors including poor diet, age, sex, and ethnicity combine to influence chronic inflammation and MLTC?
 Can this information help prevent the onset and progression of MLTC in people most at risk?

Background
‘Multimorbidity’ describes two or more (multiple) long term conditions (MLTC) in one person. A common example is the presence of diabetes, arthritis and high blood pressure. One in four of the UK population have MLTC. It is one of the greatest challenges currently facing individuals and health services. We will focus on the role of chronic inflammation and nutrition. Chronic inflammation refers to the body’s natural ability to respond to outside threats, such as fighting an infection. This lies at the root of many diseases including heart disease, type 2 diabetes, arthritis, and dementia. Some people are more likely to experience chronic inflammation. Foods and nutrients, for instance vitamin C, can reduce inflammation. People who are less well-off are more likely to eat a poor diet and may struggle to get enough of these nutrients. Stress, especially for people on low incomes, may play a role.

Design and methods
We will apply advanced statistical and computing tools (artificial intelligence) to large scale electronic health datasets to examine how MLTC develops in individuals over their lives. We will focus on how inflammation, diet and poor nutrition predict the onset and progression of MLTC and also look at how these acts together (‘intersectionality’) with an individual’s characteristics including ethnicity and social status. We will use our results to develop and test an ‘early warning’ system to predict MLTC, allowing GPs and health professionals to deliver the best prevention at the right time. We will link to policymakers to deliver support to communities most at risk of developing MLTC.