Construction of a cardiovascular disease risk prediction model for patients with rheumatic immune diseases based on echocardiography combined with clinical laboratory tests
10.3760/cma.j.cn131148-20250407-00192
- VernacularTitle:基于超声心动图联合临床实验室检查构建风湿免疫病患者心血管疾病风险预测模型
- Author:
Ting SONG
1
;
Yilu SHI
1
;
Shasha DUAN
1
;
Dan ZHANG
1
;
Ying JIANG
1
;
Yaxi WANG
1
;
Shurong YUN
1
;
Xiaoshan ZHANG
1
Author Information
1. 内蒙古医科大学附属医院超声医学科，呼和浩特 010000
- Publication Type:Journal Article
- Keywords:
Rheumatic immune;
Cardiovascular disease;
Risk factors;
Predictive models
- From:
Chinese Journal of Ultrasonography
2025;34(8):701-707
- CountryChina
- Language:Chinese
-
Abstract:
Objective:To investigate the incidence and high-risk pathogenic factors of cardiovascular disease（CVD）in patients with rheumatic and autoimmune diseases，and to construct and validate a predictive model for the risk of CVD occurrence in these patients.Methods:A retrospective analysis was conducted on 239 patients with rheumatic and autoimmune diseases who underwent treatment and echocardiography at the Affiliated Hospital of Inner Mongolia Medical University between June 2020 and June 2023. General patient data，laboratory test results，and echocardiographic findings were collected. Follow-up was performed via electronic medical records or telephone surveys until December 2024 to determine the incidence of CVD，starting from the date of the first echocardiographic examination. Predictive factors were screened using univariate analysis and Lasso regression，and a Logistic regression model was constructed. Internal validation was performed using the Bootstrap method. The model's accuracy and clinical utility were assessed using the Hosmer-Lemeshow test，calibration curve，and decision curve analysis.Results:Among the 239 patients，111 developed CVD. Logistic regression analysis identified age，diastolic blood pressure，use of immunosuppressants，lymphocyte count（LYM），α-hydroxybutyrate dehydrogenase（α-HBDH）level，serum cystatin C（CysC），and right ventricular fractional area change（RVFAC）as independent predictive factors for CVD in these patients（all P<0.05）. The area under the ROC curve（AUC）for the prediction model was 0.895（95% CI = 0.856 - 0.935），and after Bootstrap validation，it was 0.894（95% CI = 0.861-0.925）. The Hosmer-Lemeshow test，calibration curve，and decision curve analysis all indicated that the model had good accuracy and clinical utility. Conclusions:Age，diastolic blood pressure，use of immunosuppressants，LYM，α-HBDH，CysC，and RVFAC may serve as independent risk factors for CVD in patients with rheumatic and autoimmune diseases. The prediction model based on echocardiography combined with laboratory indicators can，to some extent，predict the risk of CVD occurrence in these patients.
