Statistical models to predict type 2 diabetes remission after bariatric surgery 预测2型糖尿病患者减肥手术后缓解情况的统计学模型

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 R² = 0.249; odds ratio [OR] 1.652, 95% confidence interval [CI] 1.181–2.309; P = 0.003), T2D duration (R² = 0.197; OR 0.869, 95% CI 0.808–0.935; P < 0.001), and previous insulin therapy (R² = 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.