Statistical models to predict type 2 diabetes remission after bariatric surgery
Loading...
Official URL
Full text at PDC
Publication date
2014
Advisors (or tutors)
Editors
Journal Title
Journal ISSN
Volume Title
Publisher
Wiley
Citations
Exportar
Citation
Ramos-Levi AM, Matia P, Cabrerizo L, Barabash A, Sanchez-Pernaute A, Calle- Pascual AL, Torres AJ, Rubio MA. Statistical models to predict type 2 diabetes remission after bariatric surgery. J Diabetes. 2014 Sep;6(5):472-7. doi: 10.1111/1753-0407.12127. Epub 2014 Feb 26. PMID: 24433454.
Abstract
Background: Type 2 diabetes (T2D) remission may be achieved after bariatric surgery (BS), but rates vary according to patients' baseline characteristics. The present study evaluates the relevance of several preoperative factors and develops statistical models to predict T2D remission 1 year after BS.
Methods: We retrospectively studied 141 patients (57.4% women), with a preoperative diagnosis of T2D, who underwent BS in a single center (2006-2011). Anthropometric and glucose metabolism parameters before surgery and at 1-year follow-up were recorded. Remission of T2D was defined according to consensus criteria: HbA1c <6%, fasting glucose (FG) <100 mg/dL, absence of pharmacologic treatment. The influence of several preoperative factors was explored and different statistical models to predict T2D remission were elaborated using logistic regression analysis.
Results: Three preoperative characteristics considered individually were identified as the most powerful predictors of T2D remission: C-peptide (R-2 = 0.249; odds ratio [OR] 1.652, 95% confidence interval [CI] 1.181-2.309; P = 0.003), T2D duration (R-2 = 0.197; OR 0.869, 95% CI 0.808-0.935; P < 0.001), and previous insulin therapy (R-2 = 0.165; OR 4.670, 95% CI 2.257-9.665; P < 0.001). High C-peptide levels, a shorter duration of T2D, and the absence of insulin therapy favored remission. Different multivariate logistic regression models were designed. When considering sex, T2D duration, and insulin treatment, remission was correctly predicted in 72.4% of cases. The model that included age, FG and C-peptide levels resulted in 83.7% correct classifications. When sex, FG, C-peptide, insulin treatment, and percentage weight loss were considered, correct classification of T2D remission was achieved in 95.9% of cases.
Conclusion: Preoperative characteristics determine T2D remission rates after BS to different extents. The use of statistical models may help clinicians reliably predict T2D remission rates after BS.