Some patients with type 2 diabetes may benefit from intensive glycaemic and blood pressure control: A post‐hoc machine learning analysis of action to control cardiovascular risk in diabetes (ACCORD) trial data
Authors' conclusion
Our findings suggest heterogeneous treatment effects of intensive glucose and BP control and could provide biomarkers for future clinical trials to identify more precise HbA1c and BP treatment goals for individualized medicine.
Study context
- Population
- Individuals with T2D in the ACCORD trial; 68 candidate baseline effect modifiers (demographics, comorbidities, medications, biomarkers)
- Participants
- 10,251 individuals
- Comparison
- Intensive vs standard glucose control; intensive vs standard blood pressure (BP) control
- Primary endpoint
- Major adverse cardiovascular events (MACE)
Methodological detailspost-hoc analysis, causal forest and causal tree models
- Post-hoc analysis
- Causal forest and causal tree models
Primary result
As reported in the abstract
MACE in subgroups
Relative risk (95% CI)
Intensive glucose controlvs Standard glucose controlsubgroup baseline HbA1c <8.5%
0.79(0.67–0.93)
Intensive glucose controlvs Standard glucose controlsubgroup eGFR ≥106 ml/min/1.73 m²
0.74(0.55–0.99)
Intensive BP controlvs Standard BP controlsubgroup normal HDL (women >55 mg/dl, men >45 mg/dl)
0.51(0.34–0.74)
Original publication
Some patients with type 2 diabetes may benefit from intensive glycaemic and blood pressure control: A post‐hoc machine learning analysis of ACCORD trial data. Diabetes Obes Metab. Published 31 January 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →