A PIONEERING study led by researchers from Lund University Diabetes Centre and international partners has introduced a precision prediction algorithm that can detect subtypes of obesity, significantly improving the prediction of obesity-related health risks. The study shed light on how diverse obesity profiles influence risks of severe conditions, such as Type 2 diabetes and heart disease.
Obesity, defined as abnormal or excessive fat accumulation, has more than doubled among adults since 1990. According to the World Health Organization (WHO), obesity now affects 890 million adults worldwide. This global rise presents a critical challenge to healthcare systems, as obesity is linked to complications responsible for at least 2.8 million deaths per year. “Doctors face a major challenge in determining who with obesity is most likely to develop serious complications,” explained one of the researchers involved in the study.
The study, part of the IMI SOPHIA consortium, involved over 170,000 adults from the UK, the Netherlands, and Germany, collecting detailed clinical data. Using advanced machine learning techniques, the researchers identified five distinct obesity profiles, each with different health risks. “At a population level, being heavier is generally worse for health. But, when you look more closely, at an individual level, more complex patterns exist,” said another author.
The findings reveal that while most participants’ health markers aligned with their body weight, about 20% demonstrated unexpected health patterns. For instance, around 8% of women showed high blood pressure and high “good” cholesterol with a lower waist-to-hip ratio, while around 7% of men and 5% of women exhibited high “bad” cholesterol, high triglycerides, and elevated blood pressure.
This innovative algorithm could transform patient care, helping clinicians identify patients at risk sooner. “Obesity is both common and heterogeneous,” noted a senior author. “Identifying those at highest risk is crucial to achieving precise, timely treatment.”
This research was led by Lund University in collaboration with the Maastricht Centre for Systems Biology and Erasmus MC University Medical Centre, highlighting a significant step toward precision medicine for obesity-related diseases.
Reference
Coral DE et al. Subclassification of obesity for precision prediction of cardiometabolic diseases. Nat Med. 2024;DOI:10.1038/s41591-024-03299-7.
