Background: Understanding diabetes at the molecular level can help refine diagnostic approaches and personalized treatment efforts.
Methods: We generated proteomic data from plasma collected from participants enrolled in the longitudinal observational cohort study Project Baseline Health Study (PBHS) (evaluated cohort, n = 738, 27.9% of the total PBHS cohort), and integrated those data with information from their medical history and laboratory tests to determine diabetes status. We then identified biomarker proteins associated with diabetes status.
Results: Here we identify 87 differentially expressed proteins in people with diabetes compared to those without diabetes, 71 of which show higher expression. This proteomic profile, integrated with clinical data into a logistic regression model, can discriminate diabetes status with over 85% balanced accuracy.
Conclusions: Our approach indicates that proteomic data can enhance diabetes phenotyping, showing potential for marker-based stratification of diabetes diagnosis. These results suggest that a holistic molecular-clinical approach to diagnosis might help personalize treatments or interventions for people with diabetes.
Diabetes is a complex disease in which people’s blood sugar levels become too high. People are diagnosed and monitored using conventional blood tests. We took a group of people, analyzed their blood proteins, and used computational methods to match blood protein profiles with clinical information about who had diabetes. We could thus classify individuals in detail; we could identify people who may have blood protein profiles resembling people with diabetes, even if they do not have a diabetes diagnosis. Our method could be further developed to improve the identification of people at higher risk of developing diabetes.
© 2025. The Author(s).