Individual-Level Counterfactual Analysis of SGLT2 Inhibitors Versus DPP4 Inhibitors in Diabetic Kidney Disease Using Causal Machine Learning
- 1Juntendo University Faculty of Medicine
Abstract
BackgroundTraditional real-world studies comparing SGLT2 and DPP4 inhibitors on renal outcomes rely on propensity score matching, which causes high-dimensional data loss. We used causal machine learning (Causal ML) to unmask heterogeneous treatment effects in diabetic kidney disease (DKD).
MethodsUsing data from 4,588 patients within the Japanese J-CKD-DB-Ex registry, we implemented a doubly robust (DR) learning framework (Linear DR-learner with XGBoost) to compare SGLT2 and DPP4 inhibitors. Outcomes included the chronic eGFR slope and a composite renal endpoint ( 50% eGFR decline or end-stage kidney disease). Heterogeneity was explored via causal SHAP and decision trees.
ResultsAt the population level, SGLT2 inhibitors modestly slowed chronic eGFR decline (average treatment effect [ATE] = 0.14 [95% CI: -0.86, 1.15] mL/min/1.73m{superscript 2}/year) and reduced composite endpoint risk by 9% (ATE: -0.09 [-0.11, -0.08]) versus DPP4 inhibitors. However, individual-level counterfactual analysis suggested that for the chronic eGFR slope, non-glinide users with stable pre-treatment trajectories who were also taking ACE inhibitors had a greater benefit from SGLT2 inhibitors (ATE: 2.95 [-0.68, 6.58]). Conversely, glinide users with steep pre-treatment decline had a greater benefit from DPP4 inhibitors (ATE: -8.98 [-16.11, -1.85]). For composite renal events, SGLT2 inhibitors had a 28% absolute risk reduction within the algorithmically identified high-risk subgroup (eGFR 28.1 mL/min/1.73 m{superscript 2} and positive proteinuria; ATE: -0.28 [-0.33, -0.23]). Even non-proteinuric decliners demonstrated a 8% risk reduction with SGLT2 inhibitors (ATE: -0.08 [-0.10, -0.06]).
ConclusionCausal ML advances precision medicine in DKD, shifting from uniform prescribing to individualized, data-driven therapy targeting distinct intrarenal pathways.
Related
- Counterfactual Policy Learning for Personalized Treatment Using SGLT2 Inhibitors
- SGLT2 inhibitors attenuate diabetic kidney disease by suppressing YAP dependent ferroptosis
- SGLT2 inhibitors and exercise in diabetic kidney disease: mechanistic rationale, emerging clinical evidence, and future perspectives.
- Comparative Effectiveness of Individual DPP-4 Inhibitors on Kidney Outcomes in Type 2 Diabetes With Moderate Cardiovascular Risk: A Target Trial Emulation
- Comparative Effectiveness of Tricyclic Antidepressants, Serotonin–Norepinephrine Reuptake Inhibitors, and Anticonvulsants for Diabetic Painful Neuropathy: A Systematic Review and Meta-Analysis
BibTeX
@misc{yano2026individuallevel,
title = {{Individual-Level Counterfactual Analysis of SGLT2 Inhibitors Versus DPP4 Inhibitors in Diabetic Kidney Disease Using Causal Machine Learning}},
author = {Y. Yano and H. Nagasu and K. Hiroshi and M. Ohashi and Y. Isaka and H. Okada and M. Nangaku and N. Kashihara},
howpublished = {medRxiv},
year = {2026},
month = aug,
doi = {10.64898/2026.08.30.26361750},
url = {https://www.medrxiv.org/content/10.64898/2026.08.30.26361750v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Individual-Level Counterfactual Analysis of SGLT2 Inhibitors Versus DPP4 Inhibitors in Diabetic Kidney Disease Using Causal Machine Learning
AU - Y. Yano
AU - H. Nagasu
AU - K. Hiroshi
AU - M. Ohashi
AU - Y. Isaka
AU - H. Okada
AU - M. Nangaku
AU - N. Kashihara
PY - 2026
DA - 2026/08/30
PB - medRxiv
DO - 10.64898/2026.08.30.26361750
UR - https://www.medrxiv.org/content/10.64898/2026.08.30.26361750v1
AB - BackgroundTraditional real-world studies comparing SGLT2 and DPP4 inhibitors on renal outcomes rely on propensity score matching, which causes high-dimensional data loss. We used causal machine learning (Causal ML) to unmask heterogeneous treatment effects in diabetic kidney disease (DKD). MethodsUsing data from 4,588 patients within the Japanese J-CKD-DB-Ex registry, we implemented a doubly robust (DR) learning framework (Linear DR-learner with XGBoost) to compare SGLT2 and DPP4 inhibitors. Outcomes included the chronic eGFR slope and a composite renal endpoint ( 50% eGFR decline or end-stage kidney disease). Heterogeneity was explored via causal SHAP and decision trees. ResultsAt the population level, SGLT2 inhibitors modestly slowed chronic eGFR decline (average treatment effect [ATE] = 0.14 [95% CI: -0.86, 1.15] mL/min/1.73m{superscript 2}/year) and reduced composite endpoint risk by 9% (ATE: -0.09 [-0.11, -0.08]) versus DPP4 inhibitors. However, individual-level counterfactual analysis suggested that for the chronic eGFR slope, non-glinide users with stable pre-treatment trajectories who were also taking ACE inhibitors had a greater benefit from SGLT2 inhibitors (ATE: 2.95 [-0.68, 6.58]). Conversely, glinide users with steep pre-treatment decline had a greater benefit from DPP4 inhibitors (ATE: -8.98 [-16.11, -1.85]). For composite renal events, SGLT2 inhibitors had a 28% absolute risk reduction within the algorithmically identified high-risk subgroup (eGFR 28.1 mL/min/1.73 m{superscript 2} and positive proteinuria; ATE: -0.28 [-0.33, -0.23]). Even non-proteinuric decliners demonstrated a 8% risk reduction with SGLT2 inhibitors (ATE: -0.08 [-0.10, -0.06]). ConclusionCausal ML advances precision medicine in DKD, shifting from uniform prescribing to individualized, data-driven therapy targeting distinct intrarenal pathways.
ER -