دورية أكاديمية
أعرض في EDS

Early identification of macrophage activation syndrome secondary to systemic lupus erythematosus with machine learning.

التفاصيل البيبلوغرافية
العنوان: Early identification of macrophage activation syndrome secondary to systemic lupus erythematosus with machine learning.
المؤلفون: Lin W; Department of Rheumatology, Union hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China., Xie X; Department of Rheumatology and Immunology, the Second Xiangya Hospital, Central South University, Changsha, Hunan, P.R. China.; Clinical Medical Research Center for Systemic Autoimmune Diseases in Hunan Province, Changsha, Hunan, P.R. China., Luo Z; Department of Rheumatology, Union hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China., Chen X; Department of Rheumatology, Zhongnan Hospital of Wuhan University, Wuhan, China., Cao H; Department of Rheumatology, The First Affiliated Hospital, College of Medicine, Zhejiang University, Hangzhou, China., Fang X; Department of Rheumatology, Tongji Medical College, The Central Hospital of Wuhan, Huazhong University of Science and Technology, Wuhan, China., Song Y; Department of Rheumatology, Union hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China., Yuan X; Department of Rheumatology, Union hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China., Liu X; Department of Rheumatology, Union hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China., Du R; Department of Rheumatology, Union hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China. dudurong2003@126.com.
المصدر: Arthritis research & therapy [Arthritis Res Ther] 2024 May 09; Vol. 26 (1), pp. 92. Date of Electronic Publication: 2024 May 09.
نوع المنشور: Journal Article; Research Support, Non-U.S. Gov't
اللغة: English
بيانات الدورية: Publisher: BioMed Central Country of Publication: England NLM ID: 101154438 Publication Model: Electronic Cited Medium: Internet ISSN: 1478-6362 (Electronic) Linking ISSN: 14786354 NLM ISO Abbreviation: Arthritis Res Ther Subsets: MEDLINE
أسماء مطبوعة: Original Publication: London : BioMed Central, 2003-
مواضيع طبية MeSH: Lupus Erythematosus, Systemic*/complications , Lupus Erythematosus, Systemic*/diagnosis , Machine Learning* , Macrophage Activation Syndrome*/diagnosis , Macrophage Activation Syndrome*/etiology, Humans ; Female ; Retrospective Studies ; Male ; Adult ; Middle Aged ; Early Diagnosis ; ROC Curve
مستخلص: Objective: The macrophage activation syndrome (MAS) secondary to systemic lupus erythematosus (SLE) is a severe and life-threatening complication. Early diagnosis of MAS is particularly challenging. In this study, machine learning models and diagnostic scoring card were developed to aid in clinical decision-making using clinical characteristics.
Methods: We retrospectively collected clinical data from 188 patients with either SLE or the MAS secondary to SLE. 13 significant clinical predictor variables were filtered out using the Least Absolute Shrinkage and Selection Operator (LASSO). These variables were subsequently utilized as inputs in five machine learning models. The performance of the models was evaluated using the area under the receiver operating characteristic curve (ROC-AUC), F1 score, and F2 score. To enhance clinical usability, we developed a diagnostic scoring card based on logistic regression (LR) analysis and Chi-Square binning, establishing probability thresholds and stratification for the card. Additionally, this study collected data from four other domestic hospitals for external validation.
Results: Among all the machine learning models, the LR model demonstrates the highest level of performance in internal validation, achieving a ROC-AUC of 0.998, an F1 score of 0.96, and an F2 score of 0.952. The score card we constructed identifies the probability threshold at a score of 49, achieving a ROC-AUC of 0.994 and an F2 score of 0.936. The score results were categorized into five groups based on diagnostic probability: extremely low (below 5%), low (5-25%), normal (25-75%), high (75-95%), and extremely high (above 95%). During external validation, the performance evaluation revealed that the Support Vector Machine (SVM) model outperformed other models with an AUC value of 0.947, and the scorecard model has an AUC of 0.915. Additionally, we have established an online assessment system for early identification of MAS secondary to SLE.
Conclusion: Machine learning models can significantly improve the diagnostic accuracy of MAS secondary to SLE, and the diagnostic scorecard model can facilitate personalized probabilistic predictions of disease occurrence in clinical environments.
(© 2024. The Author(s).)
References: Clin Rheumatol. 2018 Jan;37(1):93-100. (PMID: 28409239)
Front Oncol. 2023 Feb 21;13:1083088. (PMID: 36895490)
Ann Rheum Dis. 2021 Jun;80(6):758-766. (PMID: 33568388)
J Pediatr Hematol Oncol. 2022 Jan 1;44(1):e217-e222. (PMID: 34986134)
Clin Immunol. 2019 Nov;208:108255. (PMID: 31476438)
Clin Rheumatol. 2013 Jun;32(6):899-904. (PMID: 23483294)
Arthritis Rheumatol. 2023 Apr;75(4):609-619. (PMID: 35849805)
Sci Rep. 2022 May 4;12(1):7224. (PMID: 35508670)
Pediatr Blood Cancer. 2014 Nov;61(11):2101-3. (PMID: 24753034)
Semin Arthritis Rheum. 2017 Oct;47(2):216-221. (PMID: 28268026)
Lupus. 2019 Jul;28(8):986-994. (PMID: 31246559)
Front Immunol. 2022 Sep 15;13:955523. (PMID: 36189240)
Semin Arthritis Rheum. 2015 Feb;44(4):417-22. (PMID: 25300700)
Ann Rheum Dis. 2023 Mar;82(3):351-356. (PMID: 36241363)
Rheumatology (Oxford). 2021 Jan 5;60(1):231-238. (PMID: 32681176)
Dis Markers. 2015;2015:424381. (PMID: 26063955)
Pediatr Blood Cancer. 2007 Feb;48(2):124-31. (PMID: 16937360)
Clin Rheumatol. 2022 Jul;41(7):2021-2033. (PMID: 35179662)
NPJ Digit Med. 2020 Mar 9;3:30. (PMID: 32195365)
Rheumatology (Oxford). 2008 Nov;47(11):1686-91. (PMID: 18782855)
J Intern Med. 2018 Dec;284(6):603-619. (PMID: 30102808)
Pediatrics. 2006 Dec;118(6):2557-60. (PMID: 17142545)
Clin Chim Acta. 2020 Nov;510:408-415. (PMID: 32745577)
Scand J Rheumatol. 2017 Jan;46(1):44-48. (PMID: 27359073)
Ann Intern Med. 2020 Jun 2;172(11):ITC81-ITC96. (PMID: 32479157)
Eur J Haematol. 2020 Apr;104(4):344-351. (PMID: 31991015)
Ann Rheum Dis. 2019 Sep;78(9):1151-1159. (PMID: 31383717)
Front Immunol. 2019 Feb 01;10:119. (PMID: 30774631)
J Pediatr. 2013 Jun;162(6):1245-51. (PMID: 23333131)
NPJ Digit Med. 2023 Jul 31;6(1):136. (PMID: 37524859)
Case Rep Med. 2015;2015:294041. (PMID: 26064125)
معلومات مُعتمدة: 81900497 National Outstanding Youth Science Fund Project of National Natural Science Foundation of China
فهرسة مساهمة: Keywords: Machine learning; Macrophage activation syndrome; Systemic lupus erythematosus
تواريخ الأحداث: Date Created: 20240509 Date Completed: 20240510 Latest Revision: 20240512
رمز التحديث: 20240512
مُعرف محوري في PubMed: PMC11080238
DOI: 10.1186/s13075-024-03330-9
PMID: 38725078
قاعدة البيانات: MEDLINE
الوصف
تدمد:1478-6362
DOI:10.1186/s13075-024-03330-9