AUTHOR=Xue Yuan , Zhang Junmei , Li Chao , Liu Xuanyi , Kuang Weiying , Deng Jianghong , Wang Jiang , Tan Xiaohua , Li Shipeng , Li Caifeng 

TITLE=Machine learning for screening and predicting the risk of anti-MDA5 antibody in juvenile dermatomyositis children

JOURNAL=Frontiers in Immunology

VOLUME=Volume 13 - 2022

YEAR=2023

URL=https://www.frontiersin.org/journals/immunology/articles/10.3389/fimmu.2022.940802

DOI=10.3389/fimmu.2022.940802

ISSN=1664-3224

ABSTRACT=Objective. Anti-MDA5(anti-melanoma differentiation associated gene 5) antibody often reveals poor prognosis in juvenile dermatomyositis (JDM) patients. In many developing countries,there is limited ability to access myositis specific antibody due to financial and technological issues, especially in remote regions. This study was performed to develop a prediction model for screening anti-MDA5 antibody in JDM patients with commonly available clinical findings.
Methods. A cross-sectional study was applied with 152 patients enrolled from inpatient wards of the Beijing Children’s Hospital between June 2018 to September 2021. Stepwise logistic regression,least absolute shrinkage and selection operator(LASSO) regression and random forest (RF)method were used to fit the model. Model discrimination, calibration, and decision curve analysis were performed for validation.
Results. The final prediction model included 8 clinical variables(gender, fever, alopecica, periungual telangiectasia, digital ulcer, interstitial lung disease, arthritis/arthralgia, Gottron sign) and 4 auxilliary results (WBC,CK,CKMB,ALB). A anti-MDA5 antibody risk probability-predictive nomogram was established with a AUC of 0.975 predicted by random forest algorithm. The model was internally validated by Harrell’s concordance index (0.904), the Brier score (0.052), and a 500 boot-strapped satisfactory calibration curve. According to the net benefit and predicted probability thresholds of decision curve analysis, the established model showed a significant higher net benefit than traditional logistic regression model.
Conclusion. We developed a prediction model using routine clinical assessments to screen for JDM patients likely to be anti-MDA5 positive. This new tool may effectively predict the detection of anti-MDA5 in these patients using a non-invasive and efficient way.