Predicting diabetic cardiomyopathy in type 2 diabetes: development and validation of a nomogram based on clinical and echocardiographic parameters.

OBJECTIVE

Diabetic cardiomyopathy (DCM) is a myocardial dysfunction disorder driven by diabetes-associated metabolic disorders, significantly elevating the risk of heart failure in patients with type 2 diabetes mellitus (T2DM). We aimed to develop and validate a nomogram for individualized DCM risk prediction in T2DM populations.

METHODS

This retrospective study enrolled 525 consecutive T2DM patients admitted to our hospital (June 2022-June 2024). Participants were randomly allocated to training (70%) or validation (30%) cohorts. Baseline clinical characteristics, laboratory profiles, and echocardiographic parameters were collected. Predictors were identified via univariate then multivariate logistic regression, followed by nomogram construction. Model validation included: (1) internal validation via 1000 bootstrap resamples; (2) discrimination assessed by the area under the receiver operating characteristic curve (AUC-ROC); (3) calibration evaluated using calibration plots and the Hosmer-Lemeshow goodness-of-fit test; (4) clinical utility determined by decision curve analysis (DCA) and clinical impact curves (CIC).

RESULTS

Six independent predictors-age, duration of type 2 diabetes mellitus (T2DM Duration), systolic blood pressure (SBP), urinary albumin-to-creatinine ratio (UACR), left atrial diameter (LAD), and left ventricular posterior wall thickness at end-diastole (LVPWd)-were incorporated. The model showed excellent discrimination: AUC 0.947 (95% CI: 0.916-0.967) in training and 0.922 (95% CI: 0.870-0.956) in validation cohorts. Calibration indicated strong agreement (Hosmer-Lemeshow χ² = 9.2119, = 0.3247). DCA and CIC confirmed clinical utility.

CONCLUSIONS

This nomogram integrates routine clinical/echocardiographic parameters to predict DCM risk in T2DM patients, facilitating individualized risk stratification and guiding early cardioprotective interventions in high-risk populations.

CLINICAL TRIAL REGISTRATION

https://www.chictr.org.cn/index.html, identifier ChiCTR2400093755.