Early identification of macrophage activation syndrome secondary to systemic lupus erythematosus with machine learning.
Machine learning
Macrophage activation syndrome
Systemic lupus erythematosus
Journal
Arthritis research & therapy
ISSN: 1478-6362
Titre abrégé: Arthritis Res Ther
Pays: England
ID NLM: 101154438
Informations de publication
Date de publication:
09 May 2024
09 May 2024
Historique:
received:
02
02
2024
accepted:
24
04
2024
medline:
10
5
2024
pubmed:
10
5
2024
entrez:
9
5
2024
Statut:
epublish
Résumé
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. 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. 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. 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.
Identifiants
pubmed: 38725078
doi: 10.1186/s13075-024-03330-9
pii: 10.1186/s13075-024-03330-9
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
92Subventions
Organisme : National Outstanding Youth Science Fund Project of National Natural Science Foundation of China
ID : 81900497
Informations de copyright
© 2024. The Author(s).
Références
Kiriakidou M, Ching CL. Systemic Lupus Erythematosus. Ann Intern Med. 2020;172(11):Itc81–96.
doi: 10.7326/AITC202006020
pubmed: 32479157
Tian J, Zhang D, Yao X, Huang Y, Lu Q. Global epidemiology of systemic lupus erythematosus: a comprehensive systematic analysis and modelling study. Ann Rheum Dis. 2023;82(3):351–6.
doi: 10.1136/ard-2022-223035
pubmed: 36241363
Vilaiyuk S, Sirachainan N, Wanitkun S, Pirojsakul K, Vaewpanich J. Recurrent macrophage activation syndrome as the primary manifestation in systemic lupus erythematosus and the benefit of serial ferritin measurements: a case-based review. Clin Rheumatol. 2013;32(6):899–904.
doi: 10.1007/s10067-013-2227-1
pubmed: 23483294
Fukaya S, Yasuda S, Hashimoto T, Oku K, Kataoka H, Horita T, Atsumi T, Koike T. Clinical features of haemophagocytic syndrome in patients with systemic autoimmune diseases: analysis of 30 cases. Rheumatology (Oxford). 2008;47(11):1686–91.
doi: 10.1093/rheumatology/ken342
pubmed: 18782855
Granata G, Didona D, Stifano G, Feola A, Granata M. Macrophage Activation Syndrome as Onset of Systemic Lupus Erythematosus: A Case Report and a Review of the Literature. Case Rep Med 2015, 2015:294041.
Wafa A, Hicham H, Naoufal R, Hajar K, Rachid R, Souad B, Mouna M, Zoubida MT, Mohamed A. Clinical spectrum and therapeutic management of systemic lupus erythematosus-associated macrophage activation syndrome: a study of 20 Moroccan adult patients. Clin Rheumatol. 2022;41(7):2021–33.
doi: 10.1007/s10067-022-06055-9
pubmed: 35179662
Liu AC, Yang Y, Li MT, Jia Y, Chen S, Ye S, Zeng XZ, Wang Z, Zhao JX, Liu XY, et al. Macrophage activation syndrome in systemic lupus erythematosus: a multicenter, case-control study in China. Clin Rheumatol. 2018;37(1):93–100.
doi: 10.1007/s10067-017-3625-6
pubmed: 28409239
Usami M, Shimizu M, Mizuta M, Inoue N, Irabu H, Sakumura N, Nakagishi Y, Yachie A. Extensive serum biomarker analysis in patients with macrophage activation syndrome associated with systemic lupus erythematosus. Clin Immunol. 2019;208:108255.
doi: 10.1016/j.clim.2019.108255
pubmed: 31476438
Nishino A, Katsumata Y, Kawasumi H, Hirahara S, Kawaguchi Y, Yamanaka H. Usefulness of soluble CD163 as a biomarker for macrophage activation syndrome associated with systemic lupus erythematosus. Lupus. 2019;28(8):986–94.
doi: 10.1177/0961203319860201
pubmed: 31246559
Stafford IS, Kellermann M, Mossotto E, Beattie RM, MacArthur BD, Ennis S. A systematic review of the applications of artificial intelligence and machine learning in autoimmune diseases. NPJ Digit Med. 2020;3:30.
doi: 10.1038/s41746-020-0229-3
pmcid: 7062883
pubmed: 32195365
Adamichou C, Genitsaridi I, Nikolopoulos D, Nikoloudaki M, Repa A, Bortoluzzi A, Fanouriakis A, Sidiropoulos P, Boumpas DT, Bertsias GK. Lupus or not? SLE risk Probability Index (SLERPI): a simple, clinician-friendly machine learning-based model to assist the diagnosis of systemic lupus erythematosus. Ann Rheum Dis. 2021;80(6):758–66.
doi: 10.1136/annrheumdis-2020-219069
pubmed: 33568388
Matsuo H, Kamada M, Imamura A, Shimizu M, Inagaki M, Tsuji Y, Hashimoto M, Tanaka M, Ito H, Fujii Y. Machine learning-based prediction of relapse in rheumatoid arthritis patients using data on ultrasound examination and blood test. Sci Rep. 2022;12(1):7224.
doi: 10.1038/s41598-022-11361-y
pmcid: 9068780
pubmed: 35508670
Xu L, You H, Wang L, Lv C, Yuan F, Li J, Wu M, Da Z, Wei H, Yan W, et al. Identification of three different phenotypes in Anti-melanoma differentiation-Associated Gene 5 antibody-positive Dermatomyositis patients: implications for prediction of Rapidly Progressive interstitial lung disease. Arthritis Rheumatol. 2023;75(4):609–19.
doi: 10.1002/art.42308
pubmed: 35849805
Aringer M, Costenbader K, Daikh D, Brinks R, Mosca M, Ramsey-Goldman R, Smolen JS, Wofsy D, Boumpas DT, Kamen DL, et al. 2019 European League Against Rheumatism/American College of Rheumatology classification criteria for systemic lupus erythematosus. Ann Rheum Dis. 2019;78(9):1151–9.
doi: 10.1136/annrheumdis-2018-214819
pubmed: 31383717
Henter JI, Horne A, Aricó M, Egeler RM, Filipovich AH, Imashuku S, Ladisch S, McClain K, Webb D, Winiarski J, et al. HLH-2004: Diagnostic and therapeutic guidelines for hemophagocytic lymphohistiocytosis. Pediatr Blood Cancer. 2007;48(2):124–31.
doi: 10.1002/pbc.21039
pubmed: 16937360
Yang H, Luo YM, Ma CY, Zhang TY, Zhou T, Ren XL, He XL, Deng KJ, Yan D, Tang H, et al. A gender specific risk assessment of coronary heart disease based on physical examination data. NPJ Digit Med. 2023;6(1):136.
doi: 10.1038/s41746-023-00887-8
pmcid: 10390496
pubmed: 37524859
Lin WX, MAS Secondary To SLE, Risk Score. Card. 2023. http://yzy120.gitee.io/sle_mas_card/ . Accessed 12 Dec 2023.
Batu ED, Erden A, Seyhoğlu E, Kilic L, Büyükasık Y, Karadag O, Bilginer Y, Bilgen SA, Akdogan A, Kiraz S, et al. Assessment of the HScore for reactive haemophagocytic syndrome in patients with rheumatic diseases. Scand J Rheumatol. 2017;46(1):44–8.
doi: 10.3109/03009742.2016.1167951
pubmed: 27359073
Handelman GS, Kok HK, Chandra RV, Razavi AH, Lee MJ, Asadi H. eDoctor: machine learning and the future of medicine. J Intern Med. 2018;284(6):603–19.
doi: 10.1111/joim.12822
pubmed: 30102808
Sarangi R, Pathak M, Padhi S, Mahapatra S. Ferritin in hemophagocytic lymphohistiocytosis (HLH): current concepts and controversies. Clin Chim Acta. 2020;510:408–15.
doi: 10.1016/j.cca.2020.07.053
pubmed: 32745577
Naymagon L, Tremblay D, Mascarenhas J. Reevaluating the role of ferritin in the diagnosis of adult secondary hemophagocytic lymphohistiocytosis. Eur J Haematol. 2020;104(4):344–51.
doi: 10.1111/ejh.13391
pubmed: 31991015
Lehmberg K, McClain KL, Janka GE, Allen CE. Determination of an appropriate cut-off value for ferritin in the diagnosis of hemophagocytic lymphohistiocytosis. Pediatr Blood Cancer. 2014;61(11):2101–3.
doi: 10.1002/pbc.25058
pubmed: 24753034
Cheng W, Wang L, Gao X, Duan L, Shu Y, Qiu H. Prognostic value of lipid profile in adult hemophagocytic lymphohistiocytosis. Front Oncol. 2023;13:1083088.
doi: 10.3389/fonc.2023.1083088
pmcid: 9988898
pubmed: 36895490
Zhou YH, Han XR, Xia FQ, Poonit ND, Liu L. Clinical features and prognostic factors of early outcome in Pediatric Hemophagocytic lymphohistiocytosis: a retrospective analysis of 227 cases. J Pediatr Hematol Oncol. 2022;44(1):e217–22.
doi: 10.1097/MPH.0000000000002283
pubmed: 34986134
Lehmberg K, Pink I, Eulenburg C, Beutel K, Maul-Pavicic A, Janka G. Differentiating macrophage activation syndrome in systemic juvenile idiopathic arthritis from other forms of hemophagocytic lymphohistiocytosis. J Pediatr. 2013;162(6):1245–51.
doi: 10.1016/j.jpeds.2012.11.081
pubmed: 23333131
Ahn SS, Yoo BW, Jung SM, Lee SW, Park YB, Song JJ. In-hospital mortality in febrile lupus patients based on 2016 EULAR/ACR/PRINTO classification criteria for macrophage activation syndrome. Semin Arthritis Rheum. 2017;47(2):216–21.
doi: 10.1016/j.semarthrit.2017.02.002
pubmed: 28268026
Assari R, Ziaee V, Mirmohammadsadeghi A, Moradinejad MH. Dynamic Changes, Cut-Off Points, Sensitivity, and Specificity of Laboratory Data to Differentiate Macrophage Activation Syndrome from Active Disease. Dis Markers 2015, 2015:424381.
Kostik MM, Dubko MF, Masalova VV, Snegireva LS, Kornishina TL, Chikova IA, Likhacheva TS, Isupova EA, Glebova NI, Kuchinskaya EM, et al. Identification of the best cutoff points and clinical signs specific for early recognition of macrophage activation syndrome in active systemic juvenile idiopathic arthritis. Semin Arthritis Rheum. 2015;44(4):417–22.
doi: 10.1016/j.semarthrit.2014.09.004
pubmed: 25300700
Yamazawa K, Kodo K, Maeda J, Omori S, Hida M, Mori T, Awazu M. Hyponatremia, hypophosphatemia, and hypouricemia in a girl with macrophage activation syndrome. Pediatrics. 2006;118(6):2557–60.
doi: 10.1542/peds.2006-1127
pubmed: 17142545
Crayne CB, Albeituni S, Nichols KE, Cron RQ. The immunology of macrophage activation syndrome. Front Immunol. 2019;10:119.
doi: 10.3389/fimmu.2019.00119
pmcid: 6367262
pubmed: 30774631
Mizuta M, Shimizu M, Irabu H, Usami M, Inoue N, Nakagishi Y, Wada T, Yachie A. Comparison of serum cytokine profiles in macrophage activation syndrome complicating different background rheumatic diseases in children. Rheumatology (Oxford). 2021;60(1):231–8.
doi: 10.1093/rheumatology/keaa299
pubmed: 32681176
He L, Yao S, Zhang R, Liu M, Hua Z, Zou H, Wang Z, Wang Y. Macrophage activation syndrome in adults: characteristics, outcomes, and therapeutic effectiveness of etoposide-based regimen. Front Immunol. 2022;13:955523.
doi: 10.3389/fimmu.2022.955523
pmcid: 9520258
pubmed: 36189240