A nomogram based on clinical factors and CT radiomics for predicting anti-MDA5+ DM complicated by RP-ILD

Abstract

Objectives Anti-melanoma differentiation-associated gene 5 (anti-MDA5) antibody-positive dermatomyositis (DM) complicated by rapidly progressive interstitial lung disease (RP-ILD) has a high incidence and poor prognosis. The objective of this study was to establish a model for the prediction and early diagnosis of anti-MDA5+ DM-associated RP-ILD based on clinical manifestations and imaging features. Materials and Methods A total of 103 patients with anti-MDA5+ DM were included. The patients were randomly split into training and testing sets of 72 and 31 patients, respectively. After image analysis, we collected clinical, imaging, and radiomics features from each patient. Feature selection was performed first with the minimum redundancy and maximum relevance (mRMR) algorithm and then with the best subset selection method. The final remaining features comprised the radscore. Then, a clinical model and imaging model were constructed with the selected independent risk factors for the prediction of non-RP-ILD and RP-ILD. We also combined these models in different ways and compared their predictive abilities. A nomogram was also established. The predictive performances of the models were assessed based on receiver operating characteristic curves, calibration curves, discriminability, and clinical utility. Results : The analyses showed that 2 clinical factors, dyspnea (p = 0.000) and duration of illness in months (p = 0.001), and 3 radiomics features (p = 0.001, 0.044, 0.008, separately) were independent predictors of non-RP-ILD and RP-ILD. However, no imaging features were significantly different between the two groups. The radiomics model built with the 3 radiomics features performed worse than the clinical model and showed areas under the curve (AUCs) of 0.805 and 0.754 in the training and test sets, respectively. The clinical model demonstrated a good predictive ability for RP-ILD in MDA5+ DM patients, with an AUC, sensitivity, specificity, and accuracy of 0.954, 0.931, 0.837, and 0.847 in the training set and 0.890, 0.875, 0.800, and 0.774 in the testing set, respectively. The combination model built with clinical and radiomics features performed slightly better than the clinical model, with an AUC, sensitivity, specificity, and accuracy of 0.994, 0.966, 0.977, and 0.931 in the training set and 0.890, 0.812, 1.000, and 0.839 in the testing set, respectively. The calibration curve and decision curve analyses showed satisfactory consistency and clinical utility of the nomogram. Conclusion Our results suggest that the combination model built with clinical and radiomics features could reliably predict the occurrence of RP-ILD in MDA5+ DM patients.