Skip to main content

Machine learning–based prediction of radiographic progression in patients with axial spondyloarthritis

Abstract

Introduction

Machine learning is applied to characterize the risk and predict outcomes in multi-dimensional data. The prediction of radiographic progression in axial spondyloarthritis (axSpA) remains limited. Hence, we tested the feasibility of supervised machine learning algorithms to predict radiographic progression in axSpA.

Methods

This is a retrospective and hospital-based study. Clinical and laboratory data obtained from two independent axSpA groups were used as training and testing datasets. Radiographic progression over 2 years was assessed using the modified Stoke Ankylosing Spondylitis Spine Score (mSASSS) and mSASSS worsening by ≥ two units was defined as progression. Seven machine learning models with different algorithms were fitted, and their performance for the testing dataset was assessed using receiver-operating characteristic (ROC) and precision-recall (PR) curve.

Results

The training and testing groups had equivalent characteristics, and radiographic progression was identified in 25.3% and 23.7%, respectively. The generalized linear model (GLM) and support vector machine (SVM) were the top two best-performing models with an average area-under-curve (AUC) of ROC of over 0.78. SVM had the higher AUC of PR compared with GLM (0.56 versus 0.51). Balanced accuracy was over 65% in all models. mSASSS was the most informative variable, followed by the presence of syndesmophyte(s) at the baseline and sacroiliac joint grades.

Conclusions

Clinical and radiographic data-driven predictive models showed reasonable performance in the prediction of radiographic progression in axSpA. Further modelling with larger and more detailed data could provide an excellent opportunity for the clinical translation of the predictive models to the management of high-risk patients.

Key Points
Clinical and radiographic data-driven predictive models showed reasonable performance in the prediction of radiographic progression in axSpA.
Further modelling with larger and more detailed data could provide an excellent opportunity for the clinical translation of the predictive models to the management of high-risk patients.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2

References

  1. 1.

    Sieper J, Braun J, Dougados M, Baeten D (2015) Axial spondyloarthritis. Nat Rev Dis Primers 1:15013. https://doi.org/10.1038/nrdp.2015.13

    Article  PubMed  Google Scholar 

  2. 2.

    Sieper J, Poddubnyy D (2017) Axial spondyloarthritis. Lancet 390:73–84. https://doi.org/10.1016/s0140-6736(16)31591-4

    Article  PubMed  Google Scholar 

  3. 3.

    Palla I, Trieste L, Tani C, Talarico R, Cortesi PA, Mosca M, Turchetti G (2012) A systematic literature review of the economic impact of ankylosing spondylitis. Clin Exp Rheumatol 30:S136–S141

    PubMed  Google Scholar 

  4. 4.

    Baraliakos X, Listing J, Rudwaleit M, Brandt J, Sieper J, Braun J (2005) Radiographic progression in patients with ankylosing spondylitis after 2 years of treatment with the tumour necrosis factor alpha antibody infliximab. Ann Rheum Dis 64:1462–1466. https://doi.org/10.1136/ard.2004.033472

    CAS  Article  PubMed  PubMed Central  Google Scholar 

  5. 5.

    Poddubnyy D, Haibel H, Listing J, Marker-Hermann E, Zeidler H, Braun J, Sieper J, Rudwaleit M (2012) Baseline radiographic damage, elevated acute-phase reactant levels, and cigarette smoking status predict spinal radiographic progression in early axial spondylarthritis. Arthritis Rheum 64:1388–1398. https://doi.org/10.1002/art.33465

    Article  PubMed  Google Scholar 

  6. 6.

    Poddubnyy D, Protopopov M, Haibel H, Braun J, Rudwaleit M, Sieper J (2016) High disease activity according to the Ankylosing Spondylitis Disease Activity Score is associated with accelerated radiographic spinal progression in patients with early axial spondyloarthritis: results from the GErman SPondyloarthritis Inception Cohort. Ann Rheum Dis 75:2114–2118. https://doi.org/10.1136/annrheumdis-2016-209209

    Article  PubMed  Google Scholar 

  7. 7.

    Poddubnyy D, Conrad K, Haibel H, Syrbe U, Appel H, Braun J, Rudwaleit M, Sieper J (2014) Elevated serum level of the vascular endothelial growth factor predicts radiographic spinal progression in patients with axial spondyloarthritis. Ann Rheum Dis 73:2137–2143. https://doi.org/10.1136/annrheumdis-2013-203824

    CAS  Article  PubMed  Google Scholar 

  8. 8.

    Baraliakos X, Listing J, Rudwaleit M, Haibel H, Brandt J, Sieper J, Braun J (2007) Progression of radiographic damage in patients with ankylosing spondylitis: defining the central role of syndesmophytes. Ann Rheum Dis 66:910–915. https://doi.org/10.1136/ard.2006.066415

    CAS  Article  PubMed  PubMed Central  Google Scholar 

  9. 9.

    Baraliakos X, Listing J, von der Recke A, Braun J (2009) The natural course of radiographic progression in ankylosing spondylitis--evidence for major individual variations in a large proportion of patients. J Rheumatol 36:997–1002. https://doi.org/10.3899/jrheum.080871

    Article  PubMed  Google Scholar 

  10. 10.

    van Tubergen A, Ramiro S, van der Heijde D, Dougados M, Mielants H, Landewe R (2012) Development of new syndesmophytes and bridges in ankylosing spondylitis and their predictors: a longitudinal study. Ann Rheum Dis 71:518–523. https://doi.org/10.1136/annrheumdis-2011-200411

    Article  PubMed  Google Scholar 

  11. 11.

    Rajkomar A, Dean J, Kohane I (2019) Machine learning in medicine. N Engl J Med 380:1347–1358. https://doi.org/10.1056/NEJMra1814259

    Article  PubMed  Google Scholar 

  12. 12.

    Kim KJ, Tagkopoulos I (2019) Application of machine learning in rheumatic disease research. Korean J Intern Med 34:708–722. https://doi.org/10.3904/kjim.2018.349

    Article  PubMed  PubMed Central  Google Scholar 

  13. 13.

    Lezcano-Valverde JM, Salazar F, Leon L, Toledano E, Jover JA, Fernandez-Gutierrez B, Soudah E, Gonzalez-Alvaro I, Abasolo L, Rodriguez-Rodriguez L (2017) Development and validation of a multivariate predictive model for rheumatoid arthritis mortality using a machine learning approach. Sci Rep 7:10189. https://doi.org/10.1038/s41598-017-10558-w

    CAS  Article  PubMed  PubMed Central  Google Scholar 

  14. 14.

    Ward MM, Pajevic S, Dreyfuss J, Malley JD (2006) Short-term prediction of mortality in patients with systemic lupus erythematosus: classification of outcomes using random forests. Arthritis Rheum 55:74–80. https://doi.org/10.1002/art.21695

    Article  PubMed  Google Scholar 

  15. 15.

    Rudwaleit M, van der Heijde D, Landewe R, Listing J, Akkoc N, Brandt J, Braun J, Chou CT, Collantes-Estevez E, Dougados M, Huang F, Gu J, Khan MA, Kirazli Y, Maksymowych WP, Mielants H, Sorensen IJ, Ozgocmen S, Roussou E, Valle-Onate R, Weber U, Wei J, Sieper J (2009) The development of Assessment of SpondyloArthritis international Society classification criteria for axial spondyloarthritis (part II): validation and final selection. Ann Rheum Dis 68:777–783. https://doi.org/10.1136/ard.2009.108233

    CAS  Article  PubMed  Google Scholar 

  16. 16.

    Molto A, Gossec L, Meghnathi B, Landewe RBM, van der Heijde D, Atagunduz P, Elzorkany BK, Akkoc N, Kiltz U, Gu J, Wei JCC, Dougados M (2018) An Assessment in SpondyloArthritis International Society (ASAS)-endorsed definition of clinically important worsening in axial spondyloarthritis based on ASDAS. Ann Rheum Dis 77:124–127. https://doi.org/10.1136/annrheumdis-2017-212178

    Article  PubMed  Google Scholar 

  17. 17.

    Creemers MC, Franssen MJ, van't Hof MA, Gribnau FW, van de Putte LB, van Riel PL (2005) Assessment of outcome in ankylosing spondylitis: an extended radiographic scoring system. Ann Rheum Dis 64:127–129. https://doi.org/10.1136/ard.2004.020503

    CAS  Article  PubMed  Google Scholar 

  18. 18.

    Wanders A, Landewe R, Spoorenberg A, de Vlam K, Mielants H, Dougados M, van der Linden S, van der Heijde D (2004) Scoring of radiographic progression in randomised clinical trials in ankylosing spondylitis: a preference for paired reading order. Ann Rheum Dis 63:1601–1604. https://doi.org/10.1136/ard.2004.022038

    CAS  Article  PubMed  PubMed Central  Google Scholar 

  19. 19.

    van der Linden S, Valkenburg HA, Cats A (1984) Evaluation of diagnostic criteria for ankylosing spondylitis. A proposal for modification of the New York criteria. Arthritis Rheum 27:361–368

    Article  Google Scholar 

  20. 20.

    MacKay K, Brophy S, Mack C, Doran M, Calin A (2000) The development and validation of a radiographic grading system for the hip in ankylosing spondylitis: the bath ankylosing spondylitis radiology hip index. J Rheumatol 27:2866–2872

    CAS  PubMed  Google Scholar 

  21. 21.

    James G, Witten D, Hastie T, Tibshirani R (2013) An introduction to statistical learning: with applications in R. Springer, New York

    Book  Google Scholar 

  22. 22.

    Kuhn M, Johnson K (2013) Applied predictive modeling. Springer, New York

    Book  Google Scholar 

  23. 23.

    Greenwell BM, Boehmke BC, McCarthy AJ (2018) A simple and effective model-based variable importance measure. arXiv preprint arXiv:1805.04755

  24. 24.

    Brodersen KH, Ong CS, Stephan KE, Buhmann JM The balanced accuracy and its posterior distribution. In: 2010 20th International Conference on Pattern Recognition, 23-26 Aug. 2010 2010. pp 3121-3124

  25. 25.

    Saito T, Rehmsmeier M (2015) The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLoS One 10:e0118432. https://doi.org/10.1371/journal.pone.0118432

    CAS  Article  PubMed  PubMed Central  Google Scholar 

  26. 26.

    Jeong H, Bea EK, Lee J, Koh EM, Cha HS (2015) Body mass index and estrogen predict radiographic progression in the spine in ankylosing spondylitis. Joint Bone Spine 82:473–474. https://doi.org/10.1016/j.jbspin.2014.11.009

    Article  PubMed  Google Scholar 

  27. 27.

    Ranganathan P, Pramesh CS, Aggarwal R (2017) Common pitfalls in statistical analysis: logistic regression. Perspect Clin Res 8:148–151. https://doi.org/10.4103/picr.PICR_87_17

    Article  PubMed  PubMed Central  Google Scholar 

  28. 28.

    Waljee AK, Higgins PD (2010) Machine learning in medicine: a primer for physicians. Am J Gastroenterol 105:1224–1226. https://doi.org/10.1038/ajg.2010.173

    Article  PubMed  Google Scholar 

  29. 29.

    Park JW, Kim MJ, Lee JS, Ha YJ, Park JK, Kang EH, Lee YJ, Song YW, Lee EY (2019) Impact of tumor necrosis factor inhibitor versus nonsteroidal antiinflammatory drug treatment on radiographic progression in early ankylosing spondylitis: its relationship to inflammation control during treatment. Arthritis Rheum 71:82–90. https://doi.org/10.1002/art.40661

    CAS  Article  Google Scholar 

  30. 30.

    Villaverde-Garcia V, Cobo-Ibanez T, Candelas-Rodriguez G, Seoane-Mato D, Campo-Fontecha PDD, Guerra M, Munoz-Fernandez S, Canete JD (2017) The effect of smoking on clinical and structural damage in patients with axial spondyloarthritis: a systematic literature review. Semin Arthritis Rheum 46:569–583. https://doi.org/10.1016/j.semarthrit.2016.11.004

    Article  PubMed  Google Scholar 

  31. 31.

    Choi HK, Nguyen US, Niu J, Danaei G, Zhang Y (2014) Selection bias in rheumatic disease research. Nat Rev Rheumatol 10:403–412. https://doi.org/10.1038/nrrheum.2014.36

    Article  PubMed  PubMed Central  Google Scholar 

  32. 32.

    Dahabreh IJ, Kent DM (2011) Index event bias as an explanation for the paradoxes of recurrence risk research. Jama 305:822–823. https://doi.org/10.1001/jama.2011.163

    CAS  Article  PubMed  PubMed Central  Google Scholar 

  33. 33.

    Molnar C, Scherer A, Baraliakos X, de Hooge M, Micheroli R, Exer P, Kissling RO, Tamborrini G, Wildi LM, Nissen MJ, Zufferey P, Bernhard J, Weber U, Landewe RBM, van der Heijde D, Ciurea A (2018) TNF blockers inhibit spinal radiographic progression in ankylosing spondylitis by reducing disease activity: results from the Swiss Clinical Quality Management cohort. Ann Rheum Dis 77:63–69. https://doi.org/10.1136/annrheumdis-2017-211544

    CAS  Article  PubMed  Google Scholar 

  34. 34.

    Chiowchanwisawakit P, Lambert RG, Conner-Spady B, Maksymowych WP (2011) Focal fat lesions at vertebral corners on magnetic resonance imaging predict the development of new syndesmophytes in ankylosing spondylitis. Arthritis Rheum 63:2215–2225. https://doi.org/10.1002/art.30393

    Article  PubMed  Google Scholar 

  35. 35.

    Maksymowych WP, Morency N, Conner-Spady B, Lambert RG (2013) Suppression of inflammation and effects on new bone formation in ankylosing spondylitis: evidence for a window of opportunity in disease modification. Ann Rheum Dis 72:23–28. https://doi.org/10.1136/annrheumdis-2011-200859

    Article  PubMed  Google Scholar 

  36. 36.

    Heiland GR, Appel H, Poddubnyy D, Zwerina J, Hueber A, Haibel H, Baraliakos X, Listing J, Rudwaleit M, Schett G, Sieper J (2012) High level of functional dickkopf-1 predicts protection from syndesmophyte formation in patients with ankylosing spondylitis. Ann Rheum Dis 71:572–574. https://doi.org/10.1136/annrheumdis-2011-200216

    CAS  Article  PubMed  Google Scholar 

  37. 37.

    Stolwijk C, van Tubergen A, Castillo-Ortiz JD, Boonen A (2015) Prevalence of extra-articular manifestations in patients with ankylosing spondylitis: a systematic review and meta-analysis. Ann Rheum Dis 74:65–73. https://doi.org/10.1136/annrheumdis-2013-203582

    Article  PubMed  Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Ki-Jo Kim.

Ethics declarations

The study was carried out in accordance with the Helsinki Declaration and approved by the Institutional Review Board of St. Vincent’s Hospital, the Catholic University of Korea (No. VC18RESI0248).

Disclosures

None.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic supplementary material

ESM 1

(DOCX 22 kb)

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Joo, Y.B., Baek, IW., Park, YJ. et al. Machine learning–based prediction of radiographic progression in patients with axial spondyloarthritis. Clin Rheumatol 39, 983–991 (2020). https://doi.org/10.1007/s10067-019-04803-y

Download citation

Keywords

  • Axial spondyloarthritis
  • Machine learning
  • Radiographic progression