Malignancy in dermatomyositis: a mono-centric retrospective study of 134 patients in China and a potential predictive model

Abstract

Objectives: To describe the demographics and phenotypes of malignancies-associated dermatomyositis (MADM) in east China and pinpoint potential factors indicative of malignancies in patients with dermatomyositis and establish a predictive model.

Methods: We retrospectively analyzed clinical data from 134 patients with adult-onset dermatomyositis hospitalized between January 2019 and May 2022 in one comprehensive hospital. Clinical data including disease course, initial symptoms and signs, and demographic information were retrieved from the Electronic Medical Records System. Other parameters including myositis-specific autoantibodies profiles, ferritin, sedimentation, etc. were all referable. Multivariable multinomial logistic regression was employed to simulate a model to predict cancer risks. Receiver operating characteristic curve was adopted to evaluate the potency of the model.

Results: 134 patients with adult-onset dermatomyositis were aptly enrolled in this study based on inclusive and exclusive criteria: 12 (8.96%) with malignancies, 57 (42.53%) with aberrant tumor biomarkers but no malignancies, 65 (48.51%) with neither malignancies nor abnormal tumor biomarkers. Senior diagnostic age, higher LDH, higher ferritin, positive anti-TIF1γ and anti-Mi2 rather than anti-NXP2 autoantibodies were positive indicators of malignancies. Additionally, neither initial complaints nor signs were found to be correlated to a tendency towards malignancies. Digestive system, nasopharyngeal, and lung malignancies were mostly documented in east China. One multivariable multinomial logistic regression model was established to predict the phenotypes of dermatomyositis on the basis of potential malignancies and the overall sensitivity and specificity was satisfactory.

Conclusion: Positivity of anti-TIF1γ and anti-Mi2 autoantibodies are highly indicative of malignancies while the role of anti-NXP2 autoantibody in MADM in the Chinese population remains unclear. The phenotypes of malignancies can be predicted through the model and the predictive power is sufficient. More attention should be paid to malignancies screening in patients with aberrant tumor biomarkers but no malignancies, particularly digestive system, nasopharyngeal, and lung malignancies in patients with dermatomyositis but without malignancies.

Keywords: autoantibody; dermatomyositis; malignancies; predictive model; receiver operating characteristic curve; tumor biomarkers.

Figure 1

Patient collective flowchart. Initially, 477 records with concrete MSAs and MAAs were documented. Rough screening was conducted owing to diagnoses and 134 patients were duly enrolled. All the enrolled patients were then subdivided into three groups on the basis of malignancies and tumor biomarkers.

Figure 2

Age distribution pattern of patients with DM. The age pattern of either male or female patients was normally distributed. However, the mean age of initial diagnosis was higher in male patients. Notably, no statistical difference was noticed. X-axis: number of patients in each subgroup; Y-axis: 5 age intervals ranging from 1 to 29, 30 to 44, 45 to 59, 60 to 74, 75 to 100, respectively; blue columns: number of male patients; red columns: number of female patients; dash and solid black lines: reference line set for comparison.

Figure 3

ROC curves of the classifier performance for the selected features. The red, blue, and green curves indicate the predictive performance of MG, NMG, and ATBG. The predictive power of MG and NMG group is fairly good. X-axis: 1-specificity; Y-axis: sensitivity; ROC, Receiver Operating Characteristic Curve; AUC, area under curve.