A Computed Tomography Radiomics-Based Prediction Model on Interstitial Lung Disease in Anti-MDA5-Positive Dermatomyositis

Abstract

Objectives: Anti-melanoma differentiation-associated gene 5-positive dermatomyositis-associated interstitial lung disease (MDA5+ DM-ILD) is a life-threatening disease. The current study aimed to quantitatively assess the pulmonary high-resolution computed tomography (HRCT) images of MDA5+ DM-ILD by applying the radiomics approach and establish a multidimensional risk prediction model for the 6-month mortality.Methods: This retrospective study was conducted in 228 patients from two centers, namely, a derivation cohort and a longitudinal internal validation cohort in Renji Hospital, as well as an external validation cohort in Guangzhou. The derivation cohort was randomly divided into training and testing sets. The primary outcome was 6-month all-cause mortality since the time of admission. Baseline pulmonary HRCT images were quantitatively analyzed by radiomics approach, and a radiomic score (Rad-score) was generated. Clinical predictors selected by univariable Cox regression were further incorporated with the Rad-score, to enhance the prediction performance of the final model (Rad-score plus model). In parallel, an idiopathic pulmonary fibrosis (IPF)-based visual CT score and ILD-GAP score were calculated as comparators.Results: The Rad-score was significantly associated with the 6-month mortality, outperformed the traditional visual score and ILD-GAP score. The Rad-score plus model was successfully developed to predict the 6-month mortality, with C-index values of 0.88 [95% confidence interval (CI), 0.79–0.96] in the training set (n = 121), 0.88 (95%CI, 0.71–1.0) in the testing set (n = 31), 0.83 (95%CI, 0.68–0.98) in the internal validation cohort (n = 44), and 0.84 (95%CI, 0.64–1.0) in the external validation cohort (n = 32).Conclusions: The radiomic feature was an independent and reliable prognostic predictor for MDA5+ DM-ILD.

A New Predictive Model for the Prognosis of MDA5+ DM-ILD

“…For each patient, predominant CT patterns such as GGO, consolidation, reticulation, emphysema, thickening of the adjacent pleura, pleural effusion, presence of nodules or masses, honeycombing, bronchiectasis, and interlobar pleural traction were independently reviewed by two experienced observers according to the Fleischner Society glossary ( 21 ). CT evidence of fibrotic-like changes was defined as the presence of traction bronchiectasis, parenchymal bands ( 22 ), and/or honeycombing ( 21 , 23 , 24 ). To quantify the extent of pulmonary abnormalities (GGO, consolidation, reticulation, and fibrotic-like changes), a semiquantitative CT score ( 25 ) was assigned on the basis of the area involved in each of the five lung lobes (right upper, middle, and lower, and left upper and lower lobes): 0, no involvement; 1, <5%; 2, 5–25%; 3, 26–49%; 4, 50–75%, and 5, >75%.…”

A Matrix Prediction Model for the 6-Month Mortality Risk in Patients With Anti-Melanoma Differentiation-Associated Protein-5-Positive Dermatomyositis

“…Of note, in terms of impressively high mortality, compared to all other forms of myositis, anti-MDA5-positive DM remains the most intractable and challenging. Unfortunately, most fatalities occur within the first half-year of the disease despite intensive immunosuppressive treatment, which leads to high 6-month mortality reports varying from 33 to 66% according to the different cohort studies worldwide (6)(7)(8)(9)(10)(11).…”

“…Emerging cohort studies tried to seek clinical features to predict the 6-month mortality risk of patients with anti-MDA5positive DM (9)(10)(11)(12)(13)(14)(15). The poor survival rate of anti-MDA5positive DM could be explained by the rapidly progressive ILD (RP-ILD), which is definitely a risk factor for death in patients with anti-MDA5-positive DM.…”

“…The poor survival rate of anti-MDA5positive DM could be explained by the rapidly progressive ILD (RP-ILD), which is definitely a risk factor for death in patients with anti-MDA5-positive DM. The most striking results were from a recent study that quantitatively assessed pulmonary high-resolution computed tomography (HRCT) images by radiomic approach in deep learning algorithm (10). The applied radiomic score, forced vital capacity percentage of predicted (FVC%), and age were combined to establish a multidimensional risk prediction model for the 6-month mortality in anti-MDA5-positive with ILD (10).…”

“…The most striking results were from a recent study that quantitatively assessed pulmonary high-resolution computed tomography (HRCT) images by radiomic approach in deep learning algorithm (10). The applied radiomic score, forced vital capacity percentage of predicted (FVC%), and age were combined to establish a multidimensional risk prediction model for the 6-month mortality in anti-MDA5-positive with ILD (10). However, the intricate algorithm of radiomic score hinders its application in most medical facilities.…”