Acta diabetologica · 2025
Development and validation of a risk predictive nomogram for carotid intima-media thickening in patients with type 2 diabetes.
СтатьяВалидационное исследованиеНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Zheng Yongqi, Tuo Luni, Xiao Jie, Ling Runzi, Yan Lei
Аннотация
AIM: Carotid intima-media thickness (CIMT) serves as a valuable cardiovascular risk marker in type 2 diabetes mellitus (T2DM). We aimed to develop and validate a nomogram incorporating novel indicators, including the triglyceride-glucose (TyG) index, to predict CIMT thickening in T2DM.
METHODS: In this retrospective study of 804 patients with T2DM, we employed least absolute shrinkage and selection operator regression followed by stepwise regression for predictor selection. Six machine learning models were evaluated, with model selection based on the area under the receiver operating characteristic curve (AUROC). The optimal model was used to develop the nomogram, assessed using AUROC, calibration curves, decision curve analysis (DCA), and SHapley Additive exPlanations (SHAP) for feature importance.
RESULTS: Independent predictors of CIMT thickening in T2DM included age, body mass index, current smoking status, regular exercise habits, glycated hemoglobin, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, and TyG index. Logistic regression demonstrated excellent predictive performance and was selected for nomogram development. The predictive model showed strong discriminative ability and good calibration in both the training and testing datasets. DCA confirmed its clinical utility across relevant risk thresholds, with SHAP analysis identifying age as the most influential predictor.
CONCLUSIONS: This study developed and validated a nomogram integrating routine clinical parameters and novel indicators, including the TyG index, to assess the risk of CIMT thickening in T2DM patients. This nomogram provides an evidence-based tool to help clinicians identify high-risk patients and guide early therapeutic interventions.
METHODS: In this retrospective study of 804 patients with T2DM, we employed least absolute shrinkage and selection operator regression followed by stepwise regression for predictor selection. Six machine learning models were evaluated, with model selection based on the area under the receiver operating characteristic curve (AUROC). The optimal model was used to develop the nomogram, assessed using AUROC, calibration curves, decision curve analysis (DCA), and SHapley Additive exPlanations (SHAP) for feature importance.
RESULTS: Independent predictors of CIMT thickening in T2DM included age, body mass index, current smoking status, regular exercise habits, glycated hemoglobin, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, and TyG index. Logistic regression demonstrated excellent predictive performance and was selected for nomogram development. The predictive model showed strong discriminative ability and good calibration in both the training and testing datasets. DCA confirmed its clinical utility across relevant risk thresholds, with SHAP analysis identifying age as the most influential predictor.
CONCLUSIONS: This study developed and validated a nomogram integrating routine clinical parameters and novel indicators, including the TyG index, to assess the risk of CIMT thickening in T2DM patients. This nomogram provides an evidence-based tool to help clinicians identify high-risk patients and guide early therapeutic interventions.