A Wegner's Granulomatosis Risk Prediction Model Based on Machine Learning Algorithms
,
Abstract
Introduction: Prediction of Wegener's granulomatosis diagnosis and relapse is a complex process. In this study, we applied machine learning algorithms to predict Wegener's granulomatosis relapse.
Methods: In this research, 189 patients admitted to Amiralam Hospital were studied and followed for approximately 2 years. Patient features included demographics, organ involvement, symptoms, and other clinical data. Different popular machine learning algorithms were applied for predicting Wegener's granulomatosis relapse, including Support Vector Machines, Random Forest, Gradient Boosting, and XGBoost algorithms. The prediction model performance was measured for the different candidate prediction algorithms using accuracy, precision, recall, and F1-measure. The selected prediction model performance was calculated based on different relapse rates and major relapse occurrence according to Birmingham Vasculitis Activity Score (BVAS) fields.
Results: Applying different machine learning algorithms, the XGBoost algorithm performed the best. The results indicated that the prediction model's performance increased when calculating higher relapse rate possibilities. The XGBoost model had 82% accuracy while predicting more than one relapse rate and 92% accuracy in predicting more than twice the relapse rate. We also calculated the SHAP value for the prediction model. The results indicated that Cr, BVAS, lymphocyte percentage, vitamin D, nose involvement, alkaline phosphatase, diagnosis age, white blood cell count, erythrocyte sedimentation rate, and initial nose presentation are the 10 most important features according to SHAP value.
Conclusion: In this study, we have developed Wegener's granulomatosis relapse prediction model using machine learning algorithms. We achieved reasonable precision and recall for early prediction and decision- making regarding Wegener's granulomatosis relapse
2. https://www.rheumatology.org/I- Am-A/Patient-Caregiver/Diseases-Conditions/ Granulomatosis-with-Polyangitis-Wegners
3. Lutalo PM, D'Cruz DP. Diagnosis and classification of granulomatosis with polyangiitis (aka Wegener's granulomatosis). Journal of autoimmunity. 2014 Feb 1;48:94-8.
4. Boomsma MM, Stegeman CA, Van Der Leij MJ, Oost W, Hermans J, Kallenberg CG, Limburg PC, Tervaert JC. Prediction of relapses in Wegener's granulomatosis by measurement of antineutrophil cytoplasmic antibody levels: a prospective study. Arthritis & Rheumatism: Official Journal of the American College of Rheumatology. 2000 Sep;43(9):2025-33.
5. Benjamin M, McGonagle D. Histopathologic changes at “synovio–entheseal complexes” suggesting a novel mechanism for synovitis in osteoarthritis and spondylarthritis. Arthritis & Rheumatism: Official Journal of the American College of Rheumatology. 2007 Nov;56(11):3601-9.
6. Jain D, Singh V. Feature selection and classification systems for chronic disease prediction: A review. Egyptian Informatics Journal. 2018 Nov 1;19(3):179-89.
7. Chen Y, Huang S, Chen T, Liang D, Yang J, Zeng C, Li X, Xie G, Liu Z. Machine learning for prediction and risk stratification of lupus nephritis renal flare. American Journal of Nephrology. 2021;52(2):152-60.
8. 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. Annals of the rheumatic diseases. 2021 Jun 1;80(6):758-66.
9. Wang J, Xu J, Zhao C, Peng Y, Wang H. An ensemble feature selection method for high- dimensional data based on sort aggregation. Systems Science & Control Engineering. 2019 Nov 29;7(2):32-9.
10. Pierrot-Deseilligny Despujol C, Pouchot J, Pagnoux C, Coste J, Guillevin L. Predictors at diagnosis of a first Wegener’s granulomatosis relapse after obtaining complete remission. Rheumatology. 2010 Nov 1;49(11):2181-90.
11. Sanders JS, Stassen PM, Van Rossum AP, Kallenberg CG, Stegeman CA. Risk factors for relapse in anti-neutrophil cytoplasmic antibody (ANCA)-associated vasculitis: tools for treatment decisions. Clin Exp Rheumatol. 2004 Jan 1;22(6 Suppl 36):S94-101.
12. Han, W. K., Choi, H. K., Roth, R. M., McCluskey, R. T., & Niles, J. L. (2003). Serial ANCA titers: useful tool for prevention of relapses in ANCA-associated vasculitis. Kidney international, 63(3), 1079-1085.
13. G. Tomasson, P. C. Grayson, A. D. Mahr, M. LaValley, and P. A. Merkel, “Value of ANCA measurements during remission to predict a relapse of ANCA-associated vasculitis—a meta-analysis,” Rheumatology, vol. 51, no. 1, pp. 100–109, 2012.
14. Hogan PC, O’Connell RM, Scollard S, Browne E, Hackett EE, Feighery C. Biomarkers predict relapse in granulomatosis with polyangiitis. Journal of biomarkers. 2014;2014.
15. Daouk, G. H., Palsson, R., & Arnaout,M. A. (1995). Inhibition of proteinase 3 by ANCA and its correation with disease activity in Wegener’s granulomatosis. Kidney international, 47(6), 1528-1536.
16. Dabrowski, A., &Droszcz, W. (2000). Wegener’s granulomatosis-clinical analysis of 18 patients group. Medical Science Monitor, 6(1), CS151-CS157.
17. Kemna MJ, van Paassen P, Damoiseaux JG, Cohen Tervaert JW. Maintaining remission in patients with granulomatosis with polyangiitis or microscopic polyangiitis: the role of ANCA. Expert Opinion on Orphan Drugs. 2017 Mar 4;5(3):207-18.
18. Mahr A, Katsahian S, Varet H, Guillevin L, Hagen EC, Höglund P, Merkel PA, Pagnoux C, Rasmussen N, Westman K, Jayne DR. Revisiting the classification of clinical phenotypes of anti-neutrophil cytoplasmic antibody-associated vasculitis: a cluster analysis. Annals of the rheumatic diseases. 2013 Jun 1;72(6):1003-10.
19. Watts R, Lane S, Hanslik T, Hauser T, Hellmich B, Koldingsnes W, Mahr A, Segelmark M, Cohen-Tervaert JW, Scott D. Development and validation of a consensus methodology for the classification of the ANCA-associated vasculitides and polyarteritis nodosa for epidemiological studies. Annals of the rheumatic diseases. 2007 Feb 1;66(2):222-7
20. Kemna MJ, Damoiseaux J, Austen J, Winkens B, Peters J, van Paassen P, Tervaert JW. ANCA as a predictor of relapse: useful in patients with renal involvement but not in patients with nonrenal disease. Journal of the American Society of Nephrology. 2015 Mar 1;26(3):537-42.
21. Hilhorst M, van Paassen P, Tervaert JW. Proteinase 3-ANCA vasculitis versus myeloperoxidase-ANCA vasculitis. Journal of the American Society of Nephrology. 2015 Oct 1;26(10):2314-27.
22. Vabalas A, Gowen E, Poliakoff E, Casson AJ. Machine learning algorithm validation with a limited sample size. PloS one. 2019 Nov 7;14(11):e0224365.
23. Yata K, Aoshima M. Effective PCA for high-dimension, low-sample-size data with noise reduction via geometric representations. Journal of multivariate analysis. 2012 Feb 1;105(1):193-215.
24. Samson M, Devilliers H, Thietart S, Charles P, Pagnoux C, Cohen P, Karras A, Mouthon L, Terrier B, Puéchal X, Guillevin L. Score to assess the probability of relapse in granulomatosis with polyangiitis and microscopic polyangiitis. RMD open. 2023 Mar 1;9(1):e002953.
25. Chen Z, Tian X, Qu J, Chen J, Yang Y, Li J. Development and internal validation of a model to predict long-term survival of ANCA associated vasculitis. Rheumatology and Immunology Research. 2023 Apr 18;4(1):30-9.
26. Burkhardt O, Köhnlein T, Wrenger E, Lux A, Neumann KH, Welte T. Predicting outcome and survival in patients with Wegener's granulomatosis treated on the intensive care unit. Scandinavian journal of rheumatology. 2007 Jan 1;36(2):119-24.
27. Casal Moura M, Specks U, Tehranian S, Sethi S, Zubidat D, Nardelli L, Dos Santos FG, Sousa C, León-Róman J, Bobart SA, Greene E. Maintenance of Remission and Risk of Relapse in Myeloperoxidase-Positive ANCA-Associated Vasculitis with Kidney Involvement. The Clinical Journal of the American Society of Nephrology. 2023 Jan 1;18(1):47-59.
28. Radhachandran A, Garikipati A, Iqbal Z, Siefkas A, Barnes G, Hoffman J, Mao Q, Das R. A machine learning approach to predicting risk of myelodysplastic syndrome. Leuk Res. 2021 Oct;109:106639. doi: 10.1016/j. leukres.2021.106639. Epub 2021 Jun 8. PMID: 34171604.
| Files | ||
| Issue | Vol 9 No 2 (2023) | |
| Section | Original Article(s) | |
| DOI | https://doi.org/10.18502/jbe.v9i2.14619 | |
| Keywords | ||
| Wegener's granulomatosis relapse; Relapse prediction; Machine learning; Clinical decision-making; Xgboost algorithm; Birmingham vasculitis activity score; Predictive modeling; Healthcare analytics; Autoimmune diseases; Precision medicine | ||
| Rights and permissions | |
|
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
