Literature DB >> 31667645

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

Young Bin Joo1, In-Woon Baek2, Yune-Jung Park1, Kyung-Su Park1, Ki-Jo Kim3.   

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.

Entities:  

Keywords:  Axial spondyloarthritis; Machine learning; Radiographic progression

Year:  2019        PMID: 31667645     DOI: 10.1007/s10067-019-04803-y

Source DB:  PubMed          Journal:  Clin Rheumatol        ISSN: 0770-3198            Impact factor:   2.980


  33 in total

1.  Machine learning in medicine: a primer for physicians.

Authors:  Akbar K Waljee; Peter D R Higgins
Journal:  Am J Gastroenterol       Date:  2010-06       Impact factor: 10.864

2.  Development of new syndesmophytes and bridges in ankylosing spondylitis and their predictors: a longitudinal study.

Authors:  Astrid van Tubergen; Sofia Ramiro; Désirée van der Heijde; Maxime Dougados; Herman Mielants; Robert Landewé
Journal:  Ann Rheum Dis       Date:  2011-10-11       Impact factor: 19.103

3.  Progression of radiographic damage in patients with ankylosing spondylitis: defining the central role of syndesmophytes.

Authors:  X Baraliakos; J Listing; M Rudwaleit; H Haibel; J Brandt; J Sieper; J Braun
Journal:  Ann Rheum Dis       Date:  2007-02-28       Impact factor: 19.103

Review 4.  Axial spondyloarthritis.

Authors:  Joachim Sieper; Denis Poddubnyy
Journal:  Lancet       Date:  2017-01-20       Impact factor: 79.321

5.  Scoring of radiographic progression in randomised clinical trials in ankylosing spondylitis: a preference for paired reading order.

Authors:  A Wanders; R Landewé; A Spoorenberg; K de Vlam; H Mielants; M Dougados; S van der Linden; D van der Heijde
Journal:  Ann Rheum Dis       Date:  2004-08-05       Impact factor: 19.103

Review 6.  A systematic literature review of the economic impact of ankylosing spondylitis.

Authors:  Ilaria Palla; Leopoldo Trieste; Chiara Tani; Rosaria Talarico; Paolo A Cortesi; Marta Mosca; Giuseppe Turchetti
Journal:  Clin Exp Rheumatol       Date:  2012-10-16       Impact factor: 4.473

7.  Short-term prediction of mortality in patients with systemic lupus erythematosus: classification of outcomes using random forests.

Authors:  Michael M Ward; Sinisa Pajevic; Jonathan Dreyfuss; James D Malley
Journal:  Arthritis Rheum       Date:  2006-02-15

8.  The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets.

Authors:  Takaya Saito; Marc Rehmsmeier
Journal:  PLoS One       Date:  2015-03-04       Impact factor: 3.240

9.  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.

Authors:  Jun Won Park; Min Jung Kim; Jeong Seok Lee; You-Jung Ha; Jin Kyun Park; Eun Ha Kang; Yun Jong Lee; Yeong Wook Song; Eun Young Lee
Journal:  Arthritis Rheumatol       Date:  2018-11-12       Impact factor: 10.995

Review 10.  Application of machine learning in rheumatic disease research.

Authors:  Ki-Jo Kim; Ilias Tagkopoulos
Journal:  Korean J Intern Med       Date:  2018-12-31       Impact factor: 2.884

View more
  6 in total

Review 1.  Machine Learning in Rheumatic Diseases.

Authors:  Mengdi Jiang; Yueting Li; Chendan Jiang; Lidan Zhao; Xuan Zhang; Peter E Lipsky
Journal:  Clin Rev Allergy Immunol       Date:  2021-02       Impact factor: 8.667

2.  Imaging update in spondyloarthropathy.

Authors:  Amit Shah; Neel Raja; Winston J Rennie
Journal:  J Clin Orthop Trauma       Date:  2021-08-13

Review 3.  Artificial intelligence in spine care: current applications and future utility.

Authors:  Alexander L Hornung; Christopher M Hornung; G Michael Mallow; J Nicolás Barajas; Augustus Rush; Arash J Sayari; Fabio Galbusera; Hans-Joachim Wilke; Matthew Colman; Frank M Phillips; Howard S An; Dino Samartzis
Journal:  Eur Spine J       Date:  2022-03-27       Impact factor: 2.721

Review 4.  An introduction to machine learning and analysis of its use in rheumatic diseases.

Authors:  Kathryn M Kingsmore; Christopher E Puglisi; Amrie C Grammer; Peter E Lipsky
Journal:  Nat Rev Rheumatol       Date:  2021-11-02       Impact factor: 20.543

Review 5.  Molecular Imaging of Inflammatory Disease.

Authors:  Meredith A Jones; William M MacCuaig; Alex N Frickenstein; Seda Camalan; Metin N Gurcan; Jennifer Holter-Chakrabarty; Katherine T Morris; Molly W McNally; Kristina K Booth; Steven Carter; William E Grizzle; Lacey R McNally
Journal:  Biomedicines       Date:  2021-02-04

6.  Development of a radiographic scoring system for new bone formation in gout.

Authors:  Chang-Nam Son; Ken Cai; Sarah Stewart; John Ferrier; Karen Billington; Yun-Jung Jack Tsai; Thomas Bardin; Anne Horne; Lisa K Stamp; Anthony Doyle; Nicola Dalbeth
Journal:  Arthritis Res Ther       Date:  2021-12-08       Impact factor: 5.156

  6 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.