ObjectiveTo develop and validate a risk prediction model for interstitial lung disease (ILD) in patients with rheumatoid arthritis (RA).MethodsThis retrospective study analyzed clinical data from 312 patients with RA treated at Guanghua Hospital Affiliated to Shanghai University of Traditional Chinese Medicine between January 1, 2021 and June 30, 2024. Patients were divided into a RA-only group and a RA-ILD group based on the presence of ILD. Demographic characteristics, laboratory parameters, clinical manifestations, disease activity scores, medication history, joint X-ray findings, and traditional Chinese medicine (TCM) syndrome types were collected as potential predictors. Variables were screened using univariable analysis and LASSO regression. A multivariate logistic regression model was then constructed. Model performance was assessed using the area under the receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis. Internal validation was performed using bootstrap resampling (1000 iterations). A LightGBM machine learning model was also developed based on the selected predictors, and its performance was evaluated using ROC and precision-recall (PR) curves. Five-fold cross-validation was employed to further assess the robustness of the predictors.ResultsMultivariate logistic regression identified sex, age, anti-cyclic citrullinated peptide (CCP) antibody, Disease Activity Score 28 (DAS28) based on erythrocyte sedimentation rate (ESR), Krebs von den Lungen-6 (KL-6), international normalized ratio (INR), activated partial thromboplastin time (APTT), and methotrexate use as independent predictors of RA-ILD (all PP=0.7462). Bootstrap validation confirmed high consistency between predicted and observed probabilities, with a calibration slope close to the ideal value (0.9973). The LightGBM model yielded an AUC of 0.8464 and a PR AUC of 0.9417. In five-fold cross-validation, all AUC values were greater than 0.65.ConclusionsThe developed risk prediction model for RA-ILD demonstrates high predictive ability and clinical utility. It may assist in assessing the risk of ILD in patients with RA, thereby facilitating clinical risk stratification and informing quantitative diagnostic approaches.
XU et al. (Sun,) studied this question.