Key result
Sitagliptin and teneligliptin HbA1c reductions plateau within approved dose ranges in real-world type 2 diabetes.
Why the study?
Real-world patients with type 2 diabetes receive varying DPP-4 inhibitor doses over time, and linear mixed-effects models cannot adequately capture the non-linear dose-response relationship.
Does the daily dose of DPP-4 inhibitors affect the change in HbA1c in patients with type 2 diabetes?
Observational (n=1,058)
Yes
Does the daily dose of DPP-4 inhibitors affect the change in HbA1c in patients with type 2 diabetes?
Machine-learning models applied to real-world electronic medical records demonstrate a non-linear, saturating dose-response relationship for the HbA1c-lowering effects of sitagliptin and teneligliptin.
Higher approved doses of sitagliptin or teneligliptin may not yield further HbA1c reduction; hypothesis-generating and requires randomized confirmation before practice change.
Many randomized, placebo-controlled trials suggest that the dose–response relationship between dipeptidyl peptidase-4 (DPP-4) inhibitors and change in HbA1c (ΔHbA1c) is non-linear. However, in the real world, patients with type 2 diabetes (T2D) receive varying doses over time depending on their glycemic control. Therefore, to accurately capture real-world HbA1c variability, longitudinal medical records reflecting these dose changes must be analyzed. Crucially, the analysis must also account for the influence of potential confounding factors on HbA1c. Linear mixed-effects models cannot adequately assess this non-linear relationship. The aim of this study was to evaluate the association between daily dose of DPP-4 inhibitors and ΔHbA1c in the real world by developing and interpreting tree-based machine-learning models with random effects. Longitudinal information on T2D patients was extracted from electronic medical records. Four machine-learning models with random effects were constructed to predict change in HbA1c: linear mixed-effects models (LMMs) with/without a backward elimination method, a mixed-effects random forest model (MERF), and a combining tree-boosting with Gaussian process and mixed-effects model (GPBoost). The MERF and GPBoost were interpreted by SHapley Additive exPlanations and partial dependence. Non-linear machine-learning models such as MERF and GPBoost had better predictive performance than LMMs. When interpreting MERF and GPBoost, HbA1c level decreased in a dose-dependent manner within the range of sitagliptin 0–50 mg/day, but no difference was observed between 50 and 100 mg/day. For teneligliptin, while 10 mg/day was suggested to have a slightly weaker HbA1c-lowering effect than 20 or 40 mg/day, there was no difference between 20 and 40 mg/day. Regarding vildagliptin, 100 mg/day showed a tendency to lower HbA1c level more than 50 mg/day. Non-linear machine-learning models can clearly demonstrate the dose–response relationship of the HbA1c-lowering effects of DPP-4 inhibitors in real-world T2D patients. For sitagliptin and teneligliptin, the HbA1c-lowering effect plateaued within the approved dose range. With regard to vildagliptin, it is unclear whether dose–response saturation was observed due to the limited number of dosing regimens. Our findings support the results of previous trials, and machine-learning models demonstrated that it is possible to evaluate the dose–response relationship in the real world.
No takes yet. Share an insight, caveat, or question.
Hayakawa et al. (2025) conducted an observational in Type 2 diabetes (n=1,058). Dipeptidyl peptidase-4 (DPP-4) inhibitors vs. Different doses of the same drug was evaluated on Change in HbA1c (ΔHbA1c). Mixed-effects machine-learning models revealed that the HbA1c-lowering effect of sitagliptin and teneligliptin plateaued within the approved dose range in real-world patients with type 2 diabetes.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: