Certain characteristics can help predict benefit and harm from intensive glycemic therapy, according to a study involving >10,250 individuals. Investigators used machine learning to understand the variation in all-cause mortality in intensively treated ACCORD trial participants with type 2 diabetes, HbA1c ≥7.5%, and cardiovascular disease (CVD) or multiple CVD risk factors. Among the results:
- 4 groups defined by age, BMI, and HbA1c glycation index (HGI) were identified as having varied mortality risk when receiving intensive glycemic therapy.
- Patients <61 years of age with an HGI <0.44 and BMI <30 kg/m2 had a 2.3% decreased risk of mortality attributable to intensive therapy (number needed to treat: 43).
- Those with higher HGI had a 3.7% increased risk attributable to intensive therapy (number needed to harm: 27).
Basu S, Raghavan S, Wexler D, Berkowitz S. Characteristics associated with decreased or increased mortality risk from glycemic therapy among patients with type 2 diabetes and high cardiovascular risk: Machine learning analysis of the ACCORD trial. [Published online ahead of print December 20, 2017]. Diabetes Care. doi:10.2337/dc17-2252.