Development and validation of a prediction model for microvascular complications of type 2 diabetes based on inflammation-metabolism composite indicators.
This study aimed to evaluate the clinical utility of novel inflammatory and metabolic composite indices in early risk prediction of microvascular complications in patients with type 2 diabetes mellitus (T2DM), and to provide reliable evidence for early precision risk stratification.
A retrospective analysis was conducted on 964 hospitalized patients with T2DM admitted to the Department of Endocrinology, First Affiliated Hospital of Xinjiang Medical University, from September 2023 to March 2025. Patients were randomly assigned to a training cohort and a validation cohort at a ratio of 7:3 using a random number table. In the training cohort, least absolute shrinkage and selection operator (LASSO) regression was applied for variable selection and to reduce multicollinearity, followed by univariate and multivariate logistic regression analyses to identify independent risk factors for T2DM related microvascular complications. Receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA) were employed to comprehensively assess the predictive performance and clinical utility of the model.
Multifactorial logistic regression analysis showed that age, duration of diabetes, duration of hypertension, urine albumin-to-creatinine ratio (UACR) > 30 mg/g, as well as core indicators SIRI and TyG index, were significantly associated with the occurrence of microvascular complications in type 2 diabetes mellitus (T2DM) (P < 0.05). The predictive model constructed based on LASSO-logistic regression demonstrated an AUC of 0.869 (95% CI: 0.842-0.895) in the training set and an AUC of 0.864 (95% CI: 0.824-0.905) in the validation set, indicating stable and excellent discriminatory ability.
This study confirms that SIRI and TyG index can serve as independent risk factors for microvascular complications in T2DM. The nomogram model constructed based on LASSO-logistic regression shows significantly better predictive performance than single indicators, with good model calibration, demonstrating excellent clinical net benefit. This model can accurately assess the risk of microvascular complications, providing reliable decision support for early clinical screening and risk stratification management.
A retrospective analysis was conducted on 964 hospitalized patients with T2DM admitted to the Department of Endocrinology, First Affiliated Hospital of Xinjiang Medical University, from September 2023 to March 2025. Patients were randomly assigned to a training cohort and a validation cohort at a ratio of 7:3 using a random number table. In the training cohort, least absolute shrinkage and selection operator (LASSO) regression was applied for variable selection and to reduce multicollinearity, followed by univariate and multivariate logistic regression analyses to identify independent risk factors for T2DM related microvascular complications. Receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA) were employed to comprehensively assess the predictive performance and clinical utility of the model.
Multifactorial logistic regression analysis showed that age, duration of diabetes, duration of hypertension, urine albumin-to-creatinine ratio (UACR) > 30 mg/g, as well as core indicators SIRI and TyG index, were significantly associated with the occurrence of microvascular complications in type 2 diabetes mellitus (T2DM) (P < 0.05). The predictive model constructed based on LASSO-logistic regression demonstrated an AUC of 0.869 (95% CI: 0.842-0.895) in the training set and an AUC of 0.864 (95% CI: 0.824-0.905) in the validation set, indicating stable and excellent discriminatory ability.
This study confirms that SIRI and TyG index can serve as independent risk factors for microvascular complications in T2DM. The nomogram model constructed based on LASSO-logistic regression shows significantly better predictive performance than single indicators, with good model calibration, demonstrating excellent clinical net benefit. This model can accurately assess the risk of microvascular complications, providing reliable decision support for early clinical screening and risk stratification management.