Background Cardiovascular disease (CVD) is a leading cause of mortality in systemic sclerosis (SSc). Early risk identification is crucial for improving prognosis. Objectives The aim of this study was to develop a clinical prediction model for assessing cardiovascular disease risk in SSc patients via integrating clinical and imaging data. Methods We retrospectively analyzed the occurrence of CVD among 245 SSc patients and 245 controls. SSc patients were stratified by CVD event. Independent predictors of CVD risk were identified using Cox regression analysis in SSc patients. Receiver operator characteristic (ROC) curves assessed the model's predictive performance. Kaplan–Meier (KM) curves evaluated the association of these factors with event-free survival. Results SSc patients exhibited significantly higher CVD events than controls. Significant differences were observed between SSc patients with and without events regarding age, sex, disease duration, modified Rodnan skin score (mRSS), erythrocyte sedimentation rate (ESR), anti-Scl-70 antibody (ATA), anti-U3 RNP, pulmonary arterial hypertension (PAH), interstitial lung disease (ILD), coronary artery calcium score (CACS) and epicardial adipose tissue (EFV). Cox regression identified CACS, mRSS, EFV, and ATA as independent predictors of increased CVD risk. The combined model (CACS, EFV, mRSS, ATA) achieved an area under the curve (AUC) of 0.910, showing high accuracy for predicting CVD events in SSc. KM analysis confirmed significantly reduced event-free survival in patients with high CACS, high mRSS, ATA positivity, or high EFV (all P < 0.05). Conclusion CACS, mRSS, EFV, and ATA are independent risk factors for CVD events in SSc patients. A model combining these factors effectively predicts CVD incidence in this population. <Table Float="No" ID="Taba"> <tgroup cols="2"> <colspec align="justify" colname="c1" colnum="1" /> <colspec align="justify" colname="c2" colnum="2" /> <tbody> <row> <entry nameend="c2" namest="c1"> Key Points • CACS, mRSS, EFV, and ATA were identified as independent predictors of cardiovascular events. • The combination of CACS, EFV, mRSS, and ATA yielded a high AUC of 0.910, demonstrating strong predictive capability with high specificity and sensitivity for cardiovascular events in SSc individuals. </entry> </row> </tbody> </tgroup> </Table>

Predictive modeling of cardiovascular risk in systemic sclerosis: a single-center retrospective study integrating clinical and imaging data

期刊论文
发表日期：

2025年11月25日

查看全文

Jingfeng Huang,
Le Yang,
Binhua Xie,
Xiaowei Lu,
Fangjie Shen,
Xiaodong Zheng,
Qianjiang Ding,
Yuning Pan,
Xinzhong Ruan

摘要

Background

Cardiovascular disease (CVD) is a leading cause of mortality in systemic sclerosis (SSc). Early risk identification is crucial for improving prognosis.

Objectives

The aim of this study was to develop a clinical prediction model for assessing cardiovascular disease risk in SSc patients via integrating clinical and imaging data.

Methods

We retrospectively analyzed the occurrence of CVD among 245 SSc patients and 245 controls. SSc patients were stratified by CVD event. Independent predictors of CVD risk were identified using Cox regression analysis in SSc patients. Receiver operator characteristic (ROC) curves assessed the model's predictive performance. Kaplan–Meier (KM) curves evaluated the association of these factors with event-free survival.

Results

SSc patients exhibited significantly higher CVD events than controls. Significant differences were observed between SSc patients with and without events regarding age, sex, disease duration, modified Rodnan skin score (mRSS), erythrocyte sedimentation rate (ESR), anti-Scl-70 antibody (ATA), anti-U3 RNP, pulmonary arterial hypertension (PAH), interstitial lung disease (ILD), coronary artery calcium score (CACS) and epicardial adipose tissue (EFV). Cox regression identified CACS, mRSS, EFV, and ATA as independent predictors of increased CVD risk. The combined model (CACS, EFV, mRSS, ATA) achieved an area under the curve (AUC) of 0.910, showing high accuracy for predicting CVD events in SSc. KM analysis confirmed significantly reduced event-free survival in patients with high CACS, high mRSS, ATA positivity, or high EFV (all P < 0.05).

Conclusion

CACS, mRSS, EFV, and ATA are independent risk factors for CVD events in SSc patients. A model combining these factors effectively predicts CVD incidence in this population.

Key Points

• CACS, mRSS, EFV, and ATA were identified as independent predictors of cardiovascular events.

• The combination of CACS, EFV, mRSS, and ATA yielded a high AUC of 0.910, demonstrating strong predictive capability with high specificity and sensitivity for cardiovascular events in SSc individuals.