Female doctor consulting with overweight patient
The study, published in Nature Medicine, shows that future risk of 18 obesity-related diseases can be predicted using 20 commonly collected health measures, such as blood test results and demographic information. The tool could complement the use of BMI to offer a more accurate, personalised way to identify individuals at a higher risk of developing conditions like heart disease or cancer, leading to better monitoring, earlier interventions and improved health outcomes.
Obesity is a major global health challenge, with 60-70 per cent of adults in the Western countries living with overweight or obesity. If untreated, obesity can lead to several conditions ranging from type 2 diabetes and heart disease to other chronic illnesses. However, people living with overweight or obesity can have vastly different health trajectories, with some remaining healthy for years and others developing health problems. Identifying those at highest risk early of developing conditions could help healthcare professionals better choose the appropriate intervention and prioritise treatments to those that need them most.
To address this clinical challenge, researchers from Queen Mary and the Berlin Institute of Health at Charité developed and validated an obesity risk model that can accurately identify individuals at highest risk of obesity-related complications early.
The researchers analysed health data from 200,000 participants with overweight or obesity, for whom data is held in the UK Biobank, a large population study that links detailed health assessments with long-term medical records. Using interpretable machine-learning, they evaluated more than 2,000 measures of health including blood test data, body measurements, lifestyle information and molecular data.
From this evaluation, the team identified 20 health indicators that most effectively predicts future risk of developing 18 obesity-related diseases or complications, which they called the OBSCORE model. The model, which is simple to use in clinical settings, was also validated by the researchers in the independent Genes & Health and the European Investigation into Cancer (EPIC) - Norfolk studies. Following further validation and evaluation of cost-effectiveness in appropriate clinical trials, OBSCORE could help doctors identify which people living with overweight or obesity who may benefit most from early intervention, closer monitoring, or intensified treatment, which could not only help the NHS but also save lives. The researchers have used their findings to create an open access risk prediction tool for obesity-related complications.
The study's lead author, Professor Claudia Langenberg, Director of Queen Mary University of London's Precision Healthcare University Research Institute and head of the Computational Medicine group at Berlin Institute of Health said: "With obesity affecting a growing proportion of the global population, preventing its long-term health complications has become a major challenge for healthcare systems. Our work shows how deeply phenotyped large-scale health data can be used to develop data-driven frameworks that identify individuals at higher risk of developing complications and may help support more risk-based approaches to manage obesity."
The researchers also found substantial differences in risk profiles for the 18 obesity-related complications tested among individuals within the same BMI category. Importantly, those people identified as being at the highest risk were not always those with the highest BMI. A considerable proportion of individuals predicted to be at highest risk were people living with overweight rather than obesity, whose combination of metabolic and clinical factors increased their likelihood of developing complications.
Dr Kamil Demircan, DFG Walter Benjamin Fellow at Queen Mary University of London's Precision Healthcare University Research Institute and at the Berlin Institute of Health added: "Two people with similar body weight can have very different risks of developing diseases such as diabetes or heart conditions. By systematically analysing a wide range of health factors in a data-driven manner, we identified a small set of factors that together may help detect individuals at highest risk earlier, providing a clearer picture of their future risk for obesity-related conditions."
