An electronic health record-based prediction model successfully identified patients who were at the highest risk of developing type 2 diabetes up to 10 years later. Researchers from Kaiser Permanente presented the findings at the American Diabetes Association (ADA) meeting in New Orleans.

Over 60% of U.S. adults have risk factors for type 2 diabetes, far more than current diabetes prevention programs can realistically serve, the researchers note. Since diabetes often develops gradually over many years without clear warning signs, it can be difficult for healthcare systems and professionals to identify those most at risk who would benefit from prevention programs or early treatment.

The retrospective cohort study included 3,365,464 adults aged 18–70 receiving care at Kaiser Permanente Northern California from 2012 to 2024. The median patient age was 39, and 55% of patients were female. The study used a hazard-based super learning approach that combined multiple survival-analysis models to estimate each patient's risk of developing type 2 diabetes over the next one, three, and 10 years. The model used clinical and demographic information routinely collected at medical visits, such as age, weight, blood glucose (blood sugar) levels, medical history, and medications, along with publicly available data such as access to healthy food and walkable areas.

During a median follow-up of 5.4 years, the study found a type 2 diabetes incidence of 10.7/1,000 person-years. The training model effectively identified adults at high risk for type 2 diabetes with an area under the curve of 0.886 (95% Cl: 0.883–0.888). The validation model scored 0.883 (95% Cl: 0.88–0.886). The one-year follow-up resulted in a near-ideal calibration (mean predicted risk 1.03% vs. observed 1.01%). At the threshold defining high risk (>1.2% risk), the model had a sensitivity of 74% and a specificity of 82% over up to 10 years of follow-up.

"These findings represent a potential advancement over existing approaches for identifying individuals at risk of developing type 2 diabetes by enabling earlier, more precise detection and supporting a more targeted, proactive approach to prevention," said Luis A. Rodriguez, Ph.D., M.P.H., lead author of the study, in a statement. 

”Our model has the potential to create an opportunity for clinicians and health systems to focus prevention efforts on the high-risk individuals often missed by traditional screening who have the most to gain from prevention and treatment, added Rodriguez, who is a research scientist at the Kaiser Permanente Northern California Division of Research, assistant professor in the Department of Health System Sciences at the Kaiser Permanente Bernard J. Tyson School of Medicine, and assistant adjunct professor in the Department of Epidemiology & Biostatistics at the University of California, San Francisco.

The authors intend to test the model in a clinical setting to see if it helps increase engagement in type 2 diabetes prevention programs and reduce diabetes incidence.

ADA Innovation Fund Investment

Also announced at the ADA meeting was an investment by the American Diabetes Association in startup UpDoc, a company developing what it calls physician-grade agentic AI. ADA said the investment from the ADA's Innovation Fund validates UpDoc's evidence-based approach to chronic disease management and will accelerate the company's mission to deliver clinical-grade, agentic AI-powered interventions to millions of people living with diabetes and related conditions.

The ADA Innovation Fund was established to identify and accelerate transformative diabetes and cardiometabolic innovations that have the potential to fundamentally alter outcomes for people living with diabetes, obesity, or both. The fund's investment in UpDoc reflects the conviction that clinical AI, when deployed responsibly and at scale, can meaningfully close the gap between the care people need and the care they receive.

The ADA meeting was the site of some controversy, as the New York Times reported that “several diabetes experts were escorted out of an influential medical conference by the police on Friday after they handed out copies of an editorial criticizing the Trump administration’s attacks on scientific research."