A machine learning model can help forecast patients’ risk for 18 obesity-related complications and guide treatment prioritization, according to a study published April 30 in Nature Medicine.
Researchers analyzed data from about 200,000 adults with overweight or obesity to develop the model, called OBSCORE, which uses 20 clinical variables to predict 10-year risk across conditions including cardiovascular disease, Type 2 diabetes and chronic kidney disease.
The model outperformed traditional approaches such as body mass index alone, more accurately identifying patients at elevated risk. Investigators found some individuals classified as overweight — not obese — still fell into high-risk categories, underscoring limitations of BMI-based screening.
OBSCORE stratified patients into risk groups with wide variation in outcomes. For example, it predicted 10-year cardiovascular mortality ranged from 0.1% in the lowest-risk group to 5.7% in the highest-risk group.
The researchers said the framework could support more targeted use of obesity treatments and improve resource allocation, particularly as demand rises for GLP-1 therapies and other weight-loss interventions.
At the Becker's 11th Annual IT + Revenue Cycle Conference: The Future of AI & Digital Health, taking place September 14–17 in Chicago, healthcare executives and digital leaders from across the country will come together to explore how AI, interoperability, cybersecurity, and revenue cycle innovation are transforming care delivery, strengthening financial performance, and driving the next era of digital health. Apply for complimentary registration now.