UK researchers have developed a new tool that can identify individuals most at risk of obesity-related diseases, potentially helping the NHS prioritize who receives limited weight-loss medications. The tool, called Obscore, uses interpretable machine learning to analyze health, lifestyle, and demographic data, offering a personalized risk assessment for 18 different obesity-related complications, including type 2 diabetes, gout, and stroke.
Addressing the Obesity Crisis
Recent data indicates that approximately two-thirds of adults in England are overweight or obese, a situation that has raised significant health concerns. Currently, access to weight-loss interventions on the NHS, such as weight-loss jabs, is limited and largely based on having a high body mass index (BMI) and specific obesity-related health problems. The new tool aims to provide a more rational approach to resource allocation.
Professor Nick Wareham from the University of Cambridge, a co-author of the study, emphasized that the tool is not about extending the use of therapies but about developing a score that helps allocate resources more effectively. "We can prescribe therapy to those people who are most likely to need it and most likely to benefit from it – which is what we should do within the NHS," he said.
Development and Validation
Published in the journal Nature Medicine, the study applied interpretable machine learning to data from nearly 200,000 participants of the UK Biobank project, all with a BMI of 27 or higher (overweight or obese). The team identified 20 key features, including age, sex, total cholesterol, and creatinine levels, that could predict the 10-year risk of 18 obesity-related conditions.
For each condition, participants were placed into one of five equal-sized risk categories, from low to high. The team calculated the proportion of people in each category who developed the condition over a decade. The tool's validity was tested using UK Biobank data and datasets from two independent health studies.
Key Findings
The research demonstrated that individuals of the same age, sex, and BMI can have vastly different risks for various obesity-related conditions. This supports the idea that Obscore could help inform strategies for prioritizing weight-loss interventions. Notably, for conditions like type 2 diabetes, a significant proportion of those in the highest risk category were overweight rather than obese.
Kamil Demircan, a co-author from Queen Mary University of London, noted that these individuals might be overlooked if only BMI is considered. "These constitute a population of individuals who may be overlooked if we only look at BMI and not other risk factors," he said.
Practical Application
The team also applied a version of the tool to data from a randomized control trial for the weight-loss drug tirzepatide. They confirmed that individuals predicted to be at highest risk for obesity-related conditions experienced similar weight loss to others, indicating that the tool could effectively identify those who would benefit from treatment.
However, Dr. Naveed Sattar, a professor of cardiometabolic medicine at the University of Glasgow not involved in the study, pointed out that many obesity-related conditions are closely interrelated, and robust risk scores already exist for some. He also noted that several metrics used in the study are not routinely available within the NHS. "Overall, this work represents a thoughtful attempt to move towards more holistic risk prediction across multiple obesity-related conditions," Sattar said. "But substantial further development and validation will be required before such an approach can be translated into routine clinical practice."
