LAUSR

BACKGROUND Glycosylated hemoglobin (HbA1c) is directly proportional to the level of glucose in the blood, and it has been the gold standard to evaluate the status of long-term blood glucose levels. Exploring the factors that lead to HbA1c improvement is beneficial for effectively controlling of HbA1c levels. METHODS Data collected from 52 hospitals in five cities in northern China were divided into training and test sets at a ratio of 7:3. The training set was used to build models, and the test set was used to evaluate the generalizability of the models. The performance of multivariate adaptive regression splines (MARS) models and logistic regression was evaluated, namely, the accuracy, Youden's index, recall rate, G-mean and area under the ROC curve (AUC) with 95% confidence intervals (CIs). RESULTS The prevalence of improvements in HbA1c levels was 38.35%. Doses of insulin less than 13 U, more than 3 kinds of oral medicine, exercise frequency greater than once per week and 2 h postprandial blood glucose (2hPBG) less than 10.56 mmol/L were found to improve HbA1c. The following interactions were negatively associated with improvement in HbA1c levels: patients with relative complications and 2hPBG less than 10.56 mmol/L, type 2 diabetes mellitus (T2DM) duration more than 7 years and insulin dose less than 13U. Compared to logistic regression, the MARS model performed better in the above aspects, except for accuracy. CONCLUSIONS Given the interaction between factors affecting HbA1c improvement, medical staff should conduct comprehensive interventions to further reduce HbA1c levels in patients. In this study, the MARS model was superior to the traditional logistic regression in improving HbA1c levels. MARS had greater generalizability because it not only considered nonlinear relations in the process of model fitting but also adopted cross-validation. Nevertheless, more studies are needed to provide evidence for this result.