OBSCORE: Obesity Complications Risk Score 

 

What Is OBSCORE?

     - OBSCORE was developed by Langenberg et al. and published i

n Nature Medicine in April 2026. It is a machine learning–derived risk

score built on data from approximately 200,000 UK Biobank

participants with a BMI of 27 kg/m² or higher. It uses 20 routinely

collected clinical and lifestyle variables — including age, sex, blood

pressure, laboratory values, smoking status, and BMI itself — to

predict a patient's 10-year risk across 18 obesity-related complications. 

​

Why Was It Developed?

     The authors argue that BMI alone is an incomplete measure of risk,

and that obesity assessment should incorporate broader measures

of health status and disease susceptibility. Yet the parameters

required to accurately identify "clinical obesity" and predict future

complications remained unclear, and no data-driven framework had existed to guide intervention allocation according to risk. To address this gap, the researchers developed OBSCORE — a single, integrated model designed to predict the future onset of 18 important cardiovascular, metabolic, and mechanical complications associated with obesity. 

​

How Was It Built?

     Researchers from Queen Mary University of London and the Berlin Institute of Health at Charité analysed UK Biobank health data from 200,000 participants with overweight or obesity. Using interpretable machine learning, they evaluated more than 2,000 general, lifestyle, clinical, blood test, body measurement, molecular, and other indicators of health, ultimately identifying 20 health indicators that most effectively predict future risk of developing 18 obesity-related diseases or complications, ensuring that the model would not only be accurate but also simple to use in clinical settings.

​

The 18 Conditions Predicted

     The 18 outcomes include type 2 diabetes, hypertension, coronary artery disease, heart failure, atrial fibrillation, stroke, chronic kidney disease, gout, obstructive sleep apnoea, metabolic dysfunction-associated steatotic liver disease, liver cirrhosis, gallbladder disease, gastroesophageal reflux disease, osteoarthritis/arthropathy, venous thromboembolism, obesity-related cancers, chronic obstructive pulmonary disease, and all-cause mortality. 

​

Performance and Validation

     OBSCORE has been validated in independent cohorts including individuals of both European and non-European ancestry, with median concordance indices of approximately 0.75 across outcomes — indicating reasonable predictive performance for a clinically applicable risk score.

     The researchers divided participants into five risk quintiles using OBSCORE predictions. For 12 of the 18 outcomes, OBSCORE demonstrated substantial risk stratification, with rate ratios exceeding 10 when comparing the highest- and lowest-risk quintiles.

     OBSCORE more effectively identified individuals at high risk, reflected by higher post-test probabilities for complications, especially for type 2 diabetes. While OBSCORE's calibration was generally strong, occasional overestimation of risk was noted, which was mitigated through further statistical adjustment. 

​

What BMI Gets Wrong

     Many people identified as high risk were overweight rather than obese, which exposes the limitations of relying solely on BMI for risk assessment. Risk also varied considerably within BMI categories, and OBSCORE offered much greater distinction between high- and low-risk groups than BMI alone, resulting in substantial differences in predicted outcomes. 

​

Clinical Applications

     Healthcare professionals can input the 20 health data measures for their patients to generate a personalised risk profile for the 18 obesity-related conditions. Using the OBSCORE model alongside BMI scores can help healthcare professionals better choose the most effective treatment for their patients — whether surgery, pharmacological intervention, or dietary changes — and to prioritise treatments to those who need them most. 

     Following further validation and evaluation of cost-effectiveness in appropriate clinical trials, OBSCORE could help doctors identify which people living with overweight or obesity may benefit most from early intervention, closer monitoring, or intensified treatment, which could not only help the NHS but also save lives. Q

​

Accessing the Tool

     The OBSCORE calculator is publicly available at no cost at omicscience.org. Entering basic clinical data — demographics, BMI, blood pressure, relevant laboratory values, smoking history — generates 10-year risk estimates for major obesity-related complications and an overall risk category for that patient. The tool does not require specialised testing or separate data collection steps; it is a computational layer on top of what is already in the clinical chart. 

​

Expert Reaction and Limitations

Professor Naveed Sattar of the University of Glasgow described it as a "well-executed study" that "makes a modest contribution to the existing literature," noting that combining self-reported disease and medication histories with circulating biomarkers and genetic information can modestly improve prediction of future risk across a range of obesity-related conditions. However, he cautioned that many of these outcomes are highly interrelated, and that for some — particularly cardiovascular disease and type 2 diabetes — well-established and more easily deployable risk scores are already in use, with incremental improvements being more substantial for certain outcomes such as chronic kidney disease, and relatively limited for others, including joint disease.

​

Summary

     In essence, OBSCORE represents a meaningful shift in how clinicians may approach obesity-related risk. Rather than treating BMI as the sole gatekeeper for intervention, it offers a nuanced, data-driven picture of an individual's vulnerability to a broad spectrum of serious conditions — enabling more targeted, equitable, and potentially life-saving clinical decisions.