Risk Factors and Predictive Model for Dermatomyositis Associated with Rapidly Progressive Interstitial Lung Disease
Kai Wang, Yian Tian, Shanshan Liu, Zhongyuan Zhang, Leilei Shen, Deqian Meng, Ju Li Department of Rheumatology, the Affiliated Huaian No.1 People’s Hospital of Nanjing Medical University, Huaian, 223001, People’s Republic of ChinaCorrespondence: Ju Li; Deqian Meng, Department of Rheumatology, the af...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Dove Medical Press
2022-09-01
|
Series: | Pharmacogenomics and Personalized Medicine |
Subjects: | |
Online Access: | https://www.dovepress.com/risk-factors-and-predictive-model-for-dermatomyositis-associated-with--peer-reviewed-fulltext-article-PGPM |
_version_ | 1797999008849854464 |
---|---|
author | Wang K Tian Y Liu S Zhang Z Shen L Meng D Li J |
author_facet | Wang K Tian Y Liu S Zhang Z Shen L Meng D Li J |
author_sort | Wang K |
collection | DOAJ |
description | Kai Wang, Yian Tian, Shanshan Liu, Zhongyuan Zhang, Leilei Shen, Deqian Meng, Ju Li Department of Rheumatology, the Affiliated Huaian No.1 People’s Hospital of Nanjing Medical University, Huaian, 223001, People’s Republic of ChinaCorrespondence: Ju Li; Deqian Meng, Department of Rheumatology, the affiliated Huaian No.1 People’s Hospital of Nanjing Medical University, Huaian, 223001, People’s Republic of China, Email liju198461@163.com; deqianmeng2016njmc@163.comBackground: Rapidly progressive interstitial lung disease (RP-ILD) is a significant complication that determines the prognosis of dermatomyositis (DM). Early RP-ILD diagnosis can improve screening and diagnostic efficiency and provide meaningful guidance to carry out early and aggressive treatment.Methods: A retrospective screening of 284 patients with DM was performed. Clinical and laboratory characteristics of the patients were recorded. The risk factors of RP-ILD in DM patients were screened by logistic regression (LR) and machine learning methods, and the prediction models of RP-ILD were developed by machine learning methods, namely least absolute shrinkage and selection operator (LASSO), random forest (RF), and extreme gradient boosting (XGBoost).Results: According to the result of univariate LR, disease duration is a protective factor for RP-ILD, and ESR, CRP, anti-Ro-52 antibody and anti-MDA5 antibody are risk factors for RP-ILD. The top 10 important variables of the 3 machine learning models were intersected to obtain common important variables, and there were 5 common important variables, namely disease duration, LDH, CRP, anti-Ro-52 antibody and anti-MDA5 antibody. The AUC of LASSO, RF and XGBoost test set were 0.661, 0.667 and 0.867, respectively. We further validated the performance of these three models on validation set, and the results showed that, the AUC of LASSO, RF and XGBoost were 0.764, 0.727 and 0.909, respectively. Based on the results of the models, XGBoost is the optimal model in this study.Conclusion: Disease duration, LDH, CRP, anti-Ro-52 antibody and anti-MDA5 antibody are vital risk factors for RP-ILD in DM. The prediction model constructed using XGBoost can be used for risk identification and early intervention in DM patients with RP-ILD and practical application.Keywords: dermatomyositis, interstitial lung disease, risk factor, predictive model, logistic regression, least absolute shrinkage and selection operator, random forest, extreme gradient boosting |
first_indexed | 2024-04-11T10:57:51Z |
format | Article |
id | doaj.art-bc29d66b0a7840df9fdc4bc19478ee1b |
institution | Directory Open Access Journal |
issn | 1178-7066 |
language | English |
last_indexed | 2024-04-11T10:57:51Z |
publishDate | 2022-09-01 |
publisher | Dove Medical Press |
record_format | Article |
series | Pharmacogenomics and Personalized Medicine |
spelling | doaj.art-bc29d66b0a7840df9fdc4bc19478ee1b2022-12-22T04:28:43ZengDove Medical PressPharmacogenomics and Personalized Medicine1178-70662022-09-01Volume 1577578377867Risk Factors and Predictive Model for Dermatomyositis Associated with Rapidly Progressive Interstitial Lung DiseaseWang KTian YLiu SZhang ZShen LMeng DLi JKai Wang, Yian Tian, Shanshan Liu, Zhongyuan Zhang, Leilei Shen, Deqian Meng, Ju Li Department of Rheumatology, the Affiliated Huaian No.1 People’s Hospital of Nanjing Medical University, Huaian, 223001, People’s Republic of ChinaCorrespondence: Ju Li; Deqian Meng, Department of Rheumatology, the affiliated Huaian No.1 People’s Hospital of Nanjing Medical University, Huaian, 223001, People’s Republic of China, Email liju198461@163.com; deqianmeng2016njmc@163.comBackground: Rapidly progressive interstitial lung disease (RP-ILD) is a significant complication that determines the prognosis of dermatomyositis (DM). Early RP-ILD diagnosis can improve screening and diagnostic efficiency and provide meaningful guidance to carry out early and aggressive treatment.Methods: A retrospective screening of 284 patients with DM was performed. Clinical and laboratory characteristics of the patients were recorded. The risk factors of RP-ILD in DM patients were screened by logistic regression (LR) and machine learning methods, and the prediction models of RP-ILD were developed by machine learning methods, namely least absolute shrinkage and selection operator (LASSO), random forest (RF), and extreme gradient boosting (XGBoost).Results: According to the result of univariate LR, disease duration is a protective factor for RP-ILD, and ESR, CRP, anti-Ro-52 antibody and anti-MDA5 antibody are risk factors for RP-ILD. The top 10 important variables of the 3 machine learning models were intersected to obtain common important variables, and there were 5 common important variables, namely disease duration, LDH, CRP, anti-Ro-52 antibody and anti-MDA5 antibody. The AUC of LASSO, RF and XGBoost test set were 0.661, 0.667 and 0.867, respectively. We further validated the performance of these three models on validation set, and the results showed that, the AUC of LASSO, RF and XGBoost were 0.764, 0.727 and 0.909, respectively. Based on the results of the models, XGBoost is the optimal model in this study.Conclusion: Disease duration, LDH, CRP, anti-Ro-52 antibody and anti-MDA5 antibody are vital risk factors for RP-ILD in DM. The prediction model constructed using XGBoost can be used for risk identification and early intervention in DM patients with RP-ILD and practical application.Keywords: dermatomyositis, interstitial lung disease, risk factor, predictive model, logistic regression, least absolute shrinkage and selection operator, random forest, extreme gradient boostinghttps://www.dovepress.com/risk-factors-and-predictive-model-for-dermatomyositis-associated-with--peer-reviewed-fulltext-article-PGPMdermatomyositisinterstitial lung diseaserisk factorpredictive modellogistic regressionleast absolute shrinkage and selection operatorrandom forestextreme gradient boosting |
spellingShingle | Wang K Tian Y Liu S Zhang Z Shen L Meng D Li J Risk Factors and Predictive Model for Dermatomyositis Associated with Rapidly Progressive Interstitial Lung Disease Pharmacogenomics and Personalized Medicine dermatomyositis interstitial lung disease risk factor predictive model logistic regression least absolute shrinkage and selection operator random forest extreme gradient boosting |
title | Risk Factors and Predictive Model for Dermatomyositis Associated with Rapidly Progressive Interstitial Lung Disease |
title_full | Risk Factors and Predictive Model for Dermatomyositis Associated with Rapidly Progressive Interstitial Lung Disease |
title_fullStr | Risk Factors and Predictive Model for Dermatomyositis Associated with Rapidly Progressive Interstitial Lung Disease |
title_full_unstemmed | Risk Factors and Predictive Model for Dermatomyositis Associated with Rapidly Progressive Interstitial Lung Disease |
title_short | Risk Factors and Predictive Model for Dermatomyositis Associated with Rapidly Progressive Interstitial Lung Disease |
title_sort | risk factors and predictive model for dermatomyositis associated with rapidly progressive interstitial lung disease |
topic | dermatomyositis interstitial lung disease risk factor predictive model logistic regression least absolute shrinkage and selection operator random forest extreme gradient boosting |
url | https://www.dovepress.com/risk-factors-and-predictive-model-for-dermatomyositis-associated-with--peer-reviewed-fulltext-article-PGPM |
work_keys_str_mv | AT wangk riskfactorsandpredictivemodelfordermatomyositisassociatedwithrapidlyprogressiveinterstitiallungdisease AT tiany riskfactorsandpredictivemodelfordermatomyositisassociatedwithrapidlyprogressiveinterstitiallungdisease AT lius riskfactorsandpredictivemodelfordermatomyositisassociatedwithrapidlyprogressiveinterstitiallungdisease AT zhangz riskfactorsandpredictivemodelfordermatomyositisassociatedwithrapidlyprogressiveinterstitiallungdisease AT shenl riskfactorsandpredictivemodelfordermatomyositisassociatedwithrapidlyprogressiveinterstitiallungdisease AT mengd riskfactorsandpredictivemodelfordermatomyositisassociatedwithrapidlyprogressiveinterstitiallungdisease AT lij riskfactorsandpredictivemodelfordermatomyositisassociatedwithrapidlyprogressiveinterstitiallungdisease |