基于孕期建档血液指标的妊娠期糖尿病风险联合预测模型构建及卫生管理应用探讨OA

Objective:To develop a risk prediction model for gestational diabetes melli-tus(GDM)using routine blood parameters collected during early pregnancy registration and to explore its application in health management services.Methods:Data were obtained from preg-nant women who registered at the Zibo Maternal and Child Health Hospital.Relevant blood pa-rameters,including inflammation indices[e.g.,neutrophil-to-lymphocyte ratio(NLR)and sys-temic immune inflammation index(SII)],lipid profiles,and liver function indicators,were col-lected and calculated.Univariate analysis and multivariate logistic regression were performed to identify significant predictors and construct a combined prediction model.The model's predic-tive performance was subsequently validated.Results:The combined prediction model demon-strated strong predictive efficacy,incorporating variables such as inflammation indices(NLR and SII),age,pre-pregnancy BMI,fasting blood glucose,alkaline phosphatase,and triglycerides.The area under the receiver operating characteristic(ROC)curve reached 0.734,with a sensitivity of 71％and specificity of 65％.Conclusion:This study successfully developed a combined pre-diction model,providing a novel approach and methodology for early GDM screening and mater-nal health management services.