A new clinical risk model may transform how obesity is managed, by identifying which individuals are most likely to develop serious complications, regardless of their body mass index (BMI).
Developed by researchers at Queen Mary University of London and the Berlin Institute of Health, the tool, called OBSCORE, uses just 20 routinely collected clinical variables to predict the future risk of 18 obesity-related conditions, ranging from type 2 diabetes to cardiovascular disease.
Published in Nature Medicine, the study challenges the long-standing reliance on BMI as the primary metric for assessing obesity-related health risk.
Moving beyond BMI
BMI has long served as a simple proxy for obesity, but it fails to capture the biological heterogeneity of patients. Two individuals with similar BMI can have vastly different risks of developing complications.
The new model addresses this limitation directly. As described in the study, it “provides information beyond BMI” by integrating multiple dimensions of health into a unified risk score.
These include demographic data, clinical biomarkers, disease history, and lifestyle factors, variables already commonly available in healthcare settings.
The findings show that BMI alone is a poor discriminator of risk. The model consistently outperformed BMI-based approaches across all tested outcomes.
Large-scale data enables precision risk prediction
To build the model, researchers analyzed health data from nearly 200,000 individuals with overweight or obesity from the UK Biobank.
Using an interpretable machine learning framework, they screened more than 2,000 potential predictors and distilled them into a core set of 20 features that best predicted long-term health outcomes.
The resulting OBSCORE model estimates the 10-year risk of developing 18 conditions, including cardiovascular disease, kidney disease, sleep apnea, and metabolic disorders.
The model demonstrated strong predictive performance, with median concordance indices around 0.75 across outcomes, indicating robust discrimination between high- and low-risk individuals.
Hidden high-risk individuals
One of the most striking findings is that high-risk individuals are not always those with the highest BMI.
A substantial proportion of individuals classified as high risk fell into the “overweight” category (BMI 27–30 kg/m²), rather than obesity. In some outcomes, up to ~40% of those in the highest risk group had BMI below the obesity threshold.
This reveals a critical gap in current clinical practice: individuals who may benefit from intervention could be overlooked simply because they do not meet BMI-based criteria.
On the other hand, some individuals with obesity may have relatively low risk and may not require intensive intervention.
Strong risk stratification across diseases
Beyond prediction, the scientists believe that OBSCORE enables meaningful risk stratification. Individuals in the highest risk group showed dramatically higher rates of disease compared to those in the lowest group.
For example, the study reports:
- Up to 89-fold higher risk for chronic kidney disease
- 42-fold higher risk for type 2 diabetes
- 47-fold higher risk for cardiovascular mortality
These differences exceed those observed when comparing individuals based solely on BMI categories, underscoring the added value of multidimensional risk assessment.
Clinical and healthcare implications
The implications of these findings are significant, particularly in the context of emerging obesity therapies.
Highly effective drugs such as GLP-1 receptor agonists and dual incretin therapies have transformed treatment options, but their high cost and limited availability make patient prioritization essential.
As the authors note, current systems lack robust frameworks to identify which patients should receive treatment.
OBSCORE offers a potential solution by enabling risk-based allocation of interventions, ensuring that treatment is directed toward those most likely to benefit.
This could improve clinical outcomes while optimizing healthcare resource use.
Toward implementation in clinical practice
One of the key strengths of OBSCORE is its practicality. Unlike many predictive models, it relies on a small number of variables that are already routinely collected, making it suitable for integration into electronic health records.
The researchers envision the model being used as a decision-support tool in clinical settings, complementing rather than replacing existing frameworks.
External validation in independent cohorts—including populations of different ancestry, demonstrated strong generalizability, further supporting its potential for real-world deployment.
Limitations and next steps
Despite its promise, the model requires further validation in broader populations, including younger individuals and more diverse healthcare settings.
Additionally, while OBSCORE effectively stratifies risk, translating these predictions into actionable treatment thresholds will require clinical consensus and cost-effectiveness analyses.
The authors also emphasize that the model identifies predictive, not necessarily causal, factors, and should be interpreted accordingly.
Taken together, the findings mark a shift toward precision medicine in obesity, moving from simplistic metrics like BMI to data-driven, individualized risk assessment.
By capturing the complex interplay of metabolic, clinical, and behavioral factors, OBSCORE could enable earlier intervention, better targeting of therapies, and improved long-term outcomes for patients living with overweight and obesity.
The post Data-Driven Tool Identifies Individuals at Highest Risk of Obesity-Related Disease appeared first on Inside Precision Medicine.




