Key result
EHR-based XGBoost models predict 6-month HbA1c with ~0.72 RMSE in type 2 diabetes.
Why the study?
To identify real-world T2D treatment pathways and evaluate whether AI models trained on EHR medication histories can improve prediction of glycemic outcomes in routine clinical practice.
Cohort (n=3,000,000)
Yes
AI models trained on real-world EHR data can identify distinct diabetes treatment pathways and predict 6-month HbA1c, potentially informing equitable decision-support design.
May improve real-world glycemic prediction in T2D via AI medication histories; leaves open need for prospective validation before clinical adoption.
Objectives/Goals: To identify real-world type 2 diabetes (T2D) treatment pathways and evaluate whether AI models trained on electronic health record (EHR) medication histories can improve prediction of glycemic outcomes in routine clinical practice. Methods/Study Population: We conducted a retrospective cohort study using de-identified EHR data from the TriNetX Research Network (>3 M adults with T2D, 2019–2024). Medication, laboratory, and demographic data were standardized in PostgreSQL on the University of Utah CHPC. Patients with T1D, pregnancy, or incomplete follow-up were excluded. Longitudinal medication sequences were clustered using hierarchical agglomerative methods to identify treatment trajectories. Transformer-based models incorporating full prescription histories were trained to predict 6-month HbA1c, and performance (RMSE) was assessed overall and across demographic groups. Results/Anticipated Results: Among >3 M adults with T2D, we identified 40 distinct treatment clusters representing mono-, dual-, complex-, GLP-1–based, and variant pathways. GLP-1/GIP agents were typically used as 2nd–3rd-line therapy after metformin or SGLT2i and produced the largest BMI and HbA1c improvements. Baseline XGBoost models using EHR features predicted 6-month HbA1c with RMSE ≈ 0.72. The last HbA1c value was the most predictive feature, though additional labs and demographics modestly improved accuracy. Ongoing work is developing transformer models to capture longitudinal patterns and medication history effects. Discussion/Significance of Impact: National EHR networks can support development of trustworthy, fairness-aware AI to model diabetes pharmacotherapy. Insights reveal disparities in advanced therapy uptake and inform equitable decision-support design.
No takes yet. Share an insight, caveat, or question.
Kukhareva et al. (2026) conducted a cohort in Type 2 diabetes (n=3,000,000). XGBoost models using EHR features was evaluated on 6-month HbA1c prediction performance (RMSE). Baseline XGBoost models using electronic health record features predicted 6-month HbA1c with an RMSE of approximately 0.72 among over 3 million adults with type 2 diabetes.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: