Heterogeneous blood pressure treatment effects on cognitive decline in type 2 diabetes: A machine learning analysis of a randomized clinical trial
Authors' conclusion
Patients with type 2 diabetes with high UACR, or with low UACR and low TG, but high predicted cardiovascular risk and long diabetes duration were likely to derive cognitive benefits from intensive BP treatment.
Study context
- Population
- Patients with T2D in the ACCORD-MIND study who underwent blood pressure (BP) treatment
- Participants
- 1,349 patients
- Comparison
- Intensive vs standard BP treatment
- Primary endpoint
- Heterogeneous BP treatment effects on cognitive decline
Methodological detailsmachine learning, causal forest and causal tree models
- Machine learning
- Causal forest and causal tree models
Primary result
As reported in the abstract
Cognitive decline by subgroup (4 variables: UACR, FRS, TG, diabetes duration; 5 subgroups)
Each group vs standardEstimate (95% CI)
Intensive
HR, subgroup 1 (UACR ≥65 mg/g) 0.36(0.18–0.73)
Intensive
HR, subgroup 2 (UACR <65 mg/g, FRS ≥26%, TG <2.3 mmol/L, diabetes duration ≥9 years) 0.34(0.15–0.77)
- Intensive
- absolute risk reduction, subgroup 1 (urinary albumin-to-creatinine ratio (UACR) ≥65 mg/g) 15.36% (95% CI 5.01%–25.46%)
- Intensive
- absolute risk reduction, subgroup 2 (UACR <65 mg/g, FRS ≥26%, triglycerides (TG) <2.3 mmol/L, diabetes duration ≥9 years) 14.74% (95% CI 4.56%–24.59%)
Original publication
Heterogeneous blood pressure treatment effects on cognitive decline in type 2 diabetes: A machine learning analysis of a randomized clinical trial. Diabetes Obes Metab. Published 26 December 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →