Dataset Information

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.

ABSTRACT: OBJECTIVE:Identifying patients who may experience decreased or increased mortality risk from intensive glycemic therapy for type 2 diabetes remains an important clinical challenge. We sought to identify characteristics of patients at high cardiovascular risk with decreased or increased mortality risk from glycemic therapy for type 2 diabetes using new methods to identify complex combinations of treatment effect modifiers. RESEARCH DESIGN AND METHODS:The machine learning method of gradient forest analysis was applied to understand the variation in all-cause mortality within the Action to Control Cardiovascular Risk in Diabetes (ACCORD) trial (N = 10,251), whose participants were 40-79 years old with type 2 diabetes, hemoglobin A1c (HbA1c) ≥7.5% (58 mmol/mol), cardiovascular disease (CVD) or multiple CVD risk factors, and randomized to target HbA1c <6.0% (42 mmol/mol; intensive) or 7.0-7.9% (53-63 mmol/mol; standard). Covariates included demographics, BMI, hemoglobin glycosylation index (HGI; observed minus expected HbA1c derived from prerandomization fasting plasma glucose), other biomarkers, history, and medications. RESULTS:The analysis identified four groups defined by age, BMI, and HGI with varied risk for mortality under intensive glycemic therapy. The lowest risk group (HGI <0.44, BMI <30 kg/m2, age <61 years) had an absolute mortality risk decrease of 2.3% attributable to intensive therapy (95% CI 0.2 to 4.5, P = 0.038; number needed to treat: 43), whereas the highest risk group (HGI ≥0.44) had an absolute mortality risk increase of 3.7% attributable to intensive therapy (95% CI 1.5 to 6.0; P < 0.001; number needed to harm: 27). CONCLUSIONS:Age, BMI, and HGI may help individualize prediction of the benefit and harm from intensive glycemic therapy.

SUBMITTER: Basu S

PROVIDER: S-EPMC5829969 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundAlthough recent guidelines advocate for HbA1c target individualization, a comprehensive criterion for patient categorization remains absent. This study aimed to categorize HbA1c variability levels and explore the relationship between glycemic control, cardiovascular outcomes, and mortality across different degrees of variability.MethodsAction to Control Cardiovascular Risk in Diabetes study data were used. HbA1c variability was measured using the HbA1c variability score (HVS) and standard deviation (SD). K-means and K-medians clustering were used to combine the HVS and SD.ResultsK-means clustering was the most stable algorithm with the lowest clustering similarities. In the low variability group, intensive glucose-lowering treatment significantly reduced the risk of adverse cardiovascular outcomes (HR: 0·78 [95% CI: 0·63, 0·97]) without increasing mortality risk (HR: 1·07 [0.81, 1·42]); the risk of adverse cardiovascular events (HR: 1·33 [1·14, 1·56]) and all-cause mortality (HR: 1·23 [1·01,1·51]) increased with increasing mean HbA1c. In the high variability group, treatment increased the risk of cardiovascular events (HR: 2.00 [1·54, 2·60]) and mortality (HR: 2·20 [1·66, 2·92]); a higher mean HbA1c (7·86%, [7·66%, 8·06%]) had the lowest mortality risk, when the mean HbA1c was < 7·86%, a higher mean HbA1c was associated with a lower mortality risk (HR: 0·63 [0·42, 0·95]). In the medium variability group, a mean HbA1c around 7·5% was associated with the lowest risk.ConclusionsHbA1c variability can guide glycemic control targets for patients with type 2 diabetes. For patients with low variability, the lower the HbA1c, the lower the risk. For those with medium variability, controlling HbA1c at 7·5% provides the maximum benefit. For patients with high variability, a mean HbA1c of around 7·8% presents the lowest risk of all-cause mortality, a lower HbA1c did not provide cardiovascular benefits but instead increased the mortality risk. Further studies, especially those with patients that reflect the general population with type 2 diabetes undergoing the latest therapeutic approaches, are essential to validate the conclusions of this study.

Dataset Information

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.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets