Clinical Characteristics and Risk of Diabetic Complications in Data-Driven Clusters Among Type 2 Diabetes

Area of Science:

• Endocrinology
• Metabolic Diseases
• Clinical Research

Background:

• Type 2 diabetes (T2D) management requires understanding patient heterogeneity.
• Existing classifications may not fully capture distinct T2D patient profiles.

Purpose of the Study:

• To cluster newly diagnosed and long-term T2D patients into distinct groups.
• To explore clinical characteristics, complication risks, and medication use within each cluster.

Main Methods:

• K-means clustering applied to 1,060 Chinese T2D patients.
• Variables included HbA1c, age at diagnosis, BMI, HOMA2-IR, and HOMA2-B.
• Chi-square and Tukey-Kramer methods used for analysis.

Main Results:

• Four clusters identified: severe insulin-resistant diabetes (SIRD), severe insulin-deficient diabetes (SIDD), mild obesity-related diabetes (MOD), and mild age-related diabetes (MARD).
• Significant differences observed in blood pressure, renal function, and lipids across clusters.
• SIRD showed high rates of chronic kidney disease (CKD) and diabetic peripheral neuropathy (DPN); SIDD had higher risks of diabetic retinopathy, albuminuria, and lower extremity arterial disease (LEAD).
• Medication use varied significantly, including metformin, alpha-glucosidase inhibitors (AGI), dipeptidyl peptidase 4 inhibitors (DPP-4), glucagon-like peptide-1 (GLP-1), insulin, and statins.

Conclusions:

• Consistent clustering of T2D patients is achievable.
• Each identified cluster presents distinct clinical features, complication risks, and medication profiles.
• These findings support tailored therapeutic strategies for different T2D patient subgroups.