Related Experiment Video
Updated: Sep 9, 2025

Modeling and Evaluation of Murine Diabetic Cardiomyopathy Model
Published on: November 29, 2024
Heterogeneous cardiovascular effects of sodium-glucose cotransporter 2 inhibitors in type 2 diabetes: a causal forest
Yuichiro Mori1, Toshiaki Komura2, Motohiko Adomi3
1Department of Human Health Sciences, Graduate School of Medicine, Kyoto University, Kyoto, Japan.
Aims:
Evidence is limited as to who benefit the most from sodium-glucose cotransporter 2 inhibitors (SGLT2i), especially among people without elevated cardiovascular disease (CVD) risk. To address this knowledge gap, we investigated the heterogeneity in the effect of SGLT2i across CVD risk profiles.
Methods And Results:
Using a target trial emulation framework, we compared SGLT2i vs. dipeptidyl peptidase 4 inhibitors (DPP4i) in a nationwide insurer-based database of working-age Japanese citizens in 2015-23. The primary outcome was a composite of all-cause death, myocardial infarction, stroke, or heart failure over 3 years. Machine learning causal forest was applied to assess heterogeneity by predicting individual-level risk reduction in primary outcomes by SGLT2i and its correlation with CVD risk score. Overall, among 150 830 individuals included in this study (mean age, 54 years; female, 13.3%), SGLT2i was associated with decreased risk of primary outcomes {3-year risk difference, +0.38 [95% confidence interval (CI): 0.16-0.61] percentage points}. The causal forest model revealed heterogeneity in the effectiveness of SGLT2i, with estimated benefit correlating weakly with CVD risk score (r = 0.287, P < 0.001). In particular, among 107 425 individuals with low CVD risk, 97 757 (91.0%) were predicted to benefit from SGLT2i. This subpopulation was characterized as individuals with higher blood pressure, body mass index, and fasting plasma glucose levels even with low CVD risk score.
Conclusion:
The cardioprotective effect of SGLT2i was heterogeneous and more strongly predicted by individual patient characteristics than by overall CVD risk score, highlighting the importance of considering its benefit beyond the conventional risk stratification approach.
Insights
Sodium-glucose cotransporter-2 inhibitors (SGLT2i) offer benefits beyond traditional cardiovascular disease (CVD) risk scores. Individual patient factors, not just CVD risk, better predict SGLT2i effectiveness in reducing adverse outcomes.
Area of Science:
- Cardiology
- Pharmacology
- Data Science
Background:
- Sodium-glucose cotransporter-2 inhibitors (SGLT2i) are increasingly used for cardiovascular risk reduction.
- Evidence is limited regarding optimal patient selection for SGLT2i, particularly in those without high cardiovascular disease (CVD) risk.
Purpose of the Study:
- To investigate the heterogeneity in SGLT2i effectiveness across different CVD risk profiles.
- To identify patient characteristics that predict benefit from SGLT2i beyond conventional CVD risk scores.
Main Methods:
- A target trial emulation framework compared SGLT2i with dipeptidyl peptidase 4 inhibitors (DPP4i) in Japanese working-age adults (2015-2023).
- A composite outcome of all-cause death, myocardial infarction, stroke, or heart failure over three years was assessed.
- Machine-learning causal forest models were used to evaluate heterogeneity in treatment effect and its correlation with CVD risk.
Main Results:
- SGLT2i use was associated with a decreased risk of the primary composite outcome (3-year risk difference, +0.38 percentage points).
- The causal forest analysis revealed significant heterogeneity in SGLT2i effectiveness, with benefit weakly correlated with CVD risk score (r=0.287).
- Among individuals with low CVD risk, 91.0% were predicted to benefit, characterized by higher blood pressure, BMI, and fasting glucose levels.
Conclusions:
- The cardioprotective effects of SGLT2i are heterogeneous.
- Individual patient characteristics, rather than overall CVD risk score, are stronger predictors of SGLT2i benefit.
- This highlights the need to consider individual factors for SGLT2i therapy selection beyond standard risk stratification.
Related Concept Videos
Glucose Transporters
Facilitated diffusion-glucose transporters (GLUTs) are encoded by the solute-linked carrier (SLC) family 2, subfamily A gene family, or SLC2A. The 14 GLUT protein members are distributed into three classes:
Oral Hypoglycemic Agents: Biguanides and Glitazones
Dipeptidyl Peptidase 4 Inhibitors
Diabetes Mellitus: Type 2 and Gestational
Oral Hypoglycemic Agents: Sulfonylureas
Oral Hypoglycemic Agents: Glinides

