Zhou Wenyi, Yang Yeying, Su Li
Longhua Hospital Affiliated to Shanghai University of Traditional Chinese Medicine, Shanghai, 200032, China.
Clin Rheumatol. 2025 Feb;44(2):601-613. doi: 10.1007/s10067-024-07282-y. Epub 2024 Dec 26.
This study is aimed at identifying key risk factors associated with the onset of rheumatoid arthritis-associated interstitial lung disease (RA-ILD) and developing and validating a novel risk prediction model for RA-ILD.
This is a hospital-based retrospective cohort study. A total of 459 RA patients were selected from Longhua Hospital Affiliated with Shanghai University of Traditional Chinese Medicine between 2015 and 2020 as observation subjects. Demographic and clinical data were collected through the hospital's medical record system. The analysis involved evaluating demographic factors, joint clinical characteristics, traditional Chinese medicine (TCM) syndrome classification, laboratory indicators, medication history, and their associations with RA-ILD. Subsequently, a machine learning model was applied to create and validate a novel risk prediction model for the onset of RA-ILD.
The overall frequency of RA-ILD was 42.70%. Advanced age, smoking, elevated rheumatoid DAS28 score, higher radiographic joint staging (Phases II and III), strong positive CCP status (above 200), and methotrexate therapy were identified as independent risk factors for RA-ILD. Conversely, hormone therapy was found to be a protective factor against RA-ILD development. The RA-ILD prediction model, formulated based on these risk factors, exhibited superior predictive performance compared to existing models, with an AUC of 0.8914 (95% CI 0.8593-0.9234), a sensitivity of 74.5%, and a specificity of 89.7%.
The study results highlighted the risk factors for the onset of RA-ILD and underscored the utility of the established RA-ILD nomogram model for early identification of RA-ILD patients and predicting the future risk of RA-ILD in individuals with rheumatoid arthritis.
本研究旨在识别与类风湿关节炎相关间质性肺病（RA-ILD）发病相关的关键危险因素，并开发和验证一种针对RA-ILD的新型风险预测模型。
这是一项基于医院的回顾性队列研究。2015年至2020年间，从上海中医药大学附属龙华医院选取了459例类风湿关节炎患者作为观察对象。通过医院病历系统收集人口统计学和临床数据。分析涉及评估人口统计学因素、关节临床特征、中医证候分类、实验室指标、用药史及其与RA-ILD的关联。随后，应用机器学习模型创建并验证一种针对RA-ILD发病的新型风险预测模型。
RA-ILD的总体发生率为42.70%。高龄、吸烟、类风湿DAS28评分升高、更高的影像学关节分期（II期和III期）、抗环瓜氨酸肽抗体强阳性（高于200）以及甲氨蝶呤治疗被确定为RA-ILD的独立危险因素。相反，激素治疗被发现是预防RA-ILD发生的保护因素。基于这些危险因素制定的RA-ILD预测模型与现有模型相比，具有更好的预测性能，曲线下面积为0.8914（95%可信区间0.8593-0.9234），灵敏度为74.5%，特异度为89.7%。
研究结果突出了RA-ILD发病的危险因素，并强调了所建立的RA-ILD列线图模型在早期识别RA-ILD患者以及预测类风湿关节炎患者未来发生RA-ILD风险方面的实用性。
