ADA26: Machine Learning Predicts Type 2 Diabetes Risk Across 3 Million Adults: New Findings from Kaiser Permanente
Dr. Rodriguez[/caption]
Luis A. Rodriguez, PhD, MPH, RD
Research Scientist, Kaiser Permanente Northern California Division of Research
Assistant Professor, Department of Health System Sciences
Kaiser Permanente Bernard J. Tyson School of Medicine
Assistant Adjunct Professor, Department of Epidemiology & Biostatistics
University of California, San Francisco
ADA 2026 Poster Presentation: Machine-Learning Modeling for T2DM Prediction in over 3 Million Adults
American Diabetes Association 85th Scientific Sessions, June 2026
MedicalResearch.com: What is the background for this study? What are the risk factors used to develop the prediction model? Response: Type 2 diabetes develops gradually over many years, often without clear warning signs. As a result, it can be difficult for health systems to identify which adults are most likely to benefit from prevention efforts before the disease develops. In this study, we used electronic health record data from more than 3 million adults in Kaiser Permanente Northern California to develop a prediction model that estimates an individual's risk of developing type 2 diabetes over 1, 3, and 10 years. The model is based on information routinely collected during clinical care, including age, sex, race/ethnicity, body mass index, blood glucose levels, smoking, physical activity, medical and family history, and medication use. By combining these clinical, biological and behavioral factors, the model provides a more comprehensive assessment of diabetes risk than traditional screening approaches.
Dr. Klonoff[/caption]
Prof. Michaelides[/caption]
Professor Michel Michaelides BSc MB BS MD(Res) FRCOphth FACS
Professor of Ophthalmology and Consultant Ophthalmic Surgeon
UCL Institute of Ophthalmology and Moorfields Eye Hospital
MedicalResearch.com: What is the background for this study?
Dr. Hagobian[/caption]
Todd Hagobian, Ph.D.
pronouns he/him/his
Department Chair & Professor, Kinesiology and Public Health
Cal Poly, San Luis Obispo, CA
MedicalResearch.com: What is the background for this study?
Response: Previous observational studies have shown that urinary BPA is related to Type 2 diabetes risk. Meaning, higher urinary BPA is related to an increased risk of Type 2 diabetes. However, no published study to date has determined whether several days of BPA administration (participants consume BPA) increases the risk of Type 2 diabetes.
MedicalResearch.com: Where is bisphenol found? Can exposure to bisphenol be limited in everyday life?
Response: BPA and other bisphenols are found in canned foods and plastics. BPA is one of the most widely used synthetic chemicals and we consume foods that are packed in this chemical. Most of BPA exposure comes from canned foods, and 93% of the US populations has detectable urine levels of BPA. We can limit BPA by reducing canned foods (or purchased BPA free cans) and plastic use.
Dr. Hafezi-Moghadam[/caption]
Ali Hafezi-Moghadam, Ph.D., M.D
Director, Molecular Biomarkers Nano-Imaging Laboratory (MBNI)
Associate Professor of Radiology, Harvard Medical School
Brigham and Women’s Hospital
MedicalResearch.com: What is the background for this study?
Response: “It is very easy to answer many fundamental biological questions” said Richard Feynman in his 1959 address, where he also offered his simple and ingenious solution: “you just look at the thing!”
Prof. Hiddo Lambers Heerspink, PhD PHARMD
Department of Clinical Pharmacy and Pharmacology
University Medical Center Groningen
Groningen
Yuxia Wei[/caption]
Yuxia Wei | PhD Student
Unit of Epidemiology
Institute of Environmental Medicine
Karolinska Institutet
Stockholm | Sweden
MedicalResearch.com: What is the background for this study?
Response: Diabetes is traditionally known for having two types (type 1 diabetes and type 2 diabetes). However, it is becoming increasingly clear that diabetes is much more complex than this traditional classification. Several attempts have been made to address this heterogeneity and in 2018, a Swedish ground-breaking study proposed that there are five distinct subtypes of diabetes in adults. They have been replicated in different populations and it has been shown that there are differences between the subtypes in terms of genetics and risks of complications. Another way of elucidating the relevance of these subtypes is to investigate whether the influence of known risk factors for diabetes is different on different subtypes. Our study is one of the first attempts to address this. We used a study design known as Mendelian randomization, to investigate the influence of childhood obesity on these diabetes subtypes that typically occur after age 35. This work was a collaboration between Karolinska institutet in Stockholm, University of Bristol in the UK and Sun Yat-Sen University in China.