Identifying subgroups benefiting from intensive glycaemic treatment to improve renal outcomes in type 2 diabetes: Insights from the ACCORD trial
Authors' conclusion
Through innovative machine learning, we identified ACCORD subgroups benefitting significantly from intensive glycaemic therapy for renal outcomes, without increased cardiovascular or hypoglycaemic risks.
Study context
- Population
- ACCORD trial population with T2D
- Comparison
- Intensive vs standard glucose-lowering therapy
- Primary endpoint
- ≥50% decline in baseline eGFR or end-stage renal disease (ESRD)
Methodological detailsmachine learning subgroup analysis, causal tree model, model-based recursive partitioning, internal cross-validation
- Machine learning subgroup analysis
- Causal tree model
- Model-based recursive partitioning
- Internal cross-validation
Primary result
As reported in the abstract
Primary composite renal outcome (≥50% eGFR decline or ESRD)
Fully adjusted HR (95% CI)P value
Node 4no CV history, SBP ≤142.67 mm Hg, TG ≤172 mg/dL
0.66(0.49–0.89)
P = 0.006Node 7no CV history, SBP 142.67-154 mm Hg
0.67(0.49–0.93)
P = 0.016Further findings
Doubling of serum creatinine, Node 4
| Fully adjusted HR (95% CI) | P value | ||
|---|---|---|---|
| Node 4 | 0.59 (0.36–0.98) | P = 0.041 | |
| 0.20.5125Fully adjusted HR (log scale) |
End-stage renal disease (ESRD), Node 7
| Fully adjusted HR (95% CI) | P value | ||
|---|---|---|---|
| Node 7 | 0.35 (0.17–0.74) | P = 0.0057 | |
| 0.10.31310Fully adjusted HR (log scale) |
Safety
CV risk and hypoglycaemic events, Nodes 4 and 7
- Neither node 4 nor node 7 displayed elevated cardiovascular risk or hypoglycaemic events
Original publication
Identifying subgroups benefiting from intensive glycaemic treatment to improve renal outcomes in type 2 diabetes: Insights from the ACCORD trial. Diabetes Obes Metab. Published 9 December 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →