POS0682 IDENTIFICATION OF A DIAGNOSTIC MODEL FOR AXIAL SPONDYLOARTHRITIS IN DAILY CLINICAL PRACTICE USING A RANDOM FOREST MACHINE LEARNING APPROACH

• Published in: Annals of the rheumatic diseases Vol. 82; no. Suppl 1; pp. 623 - 624
• Main Authors: Redeker, I., Tsiami, S., Eicker, J., Kiltz, U., Kiefer, D., Andreica, I., Sewerin, P., Baraliakos, X.
• Format: Journal Article
• Language: English
• Published: Kidlington BMJ Publishing Group Ltd and European League Against Rheumatism 01.06.2023; Elsevier B.V; Elsevier Limited
• Subjects: Algorithms; Ankylosis; Arthritis; Back pain; Bone marrow; Chronic pain; Dactylitis; Datasets; Edema; Histocompatibility antigen HLA; Inflammatory bowel diseases; Inflammatory diseases; Learning algorithms; Machine learning; Magnetic resonance imaging; Mathematical models; Metaplasia; Nonsteroidal anti-inflammatory drugs; Psoriasis; Rheumatic diseases; Scientific Abstracts; Sclerosis; Spondyloarthritis; Uveitis; Spondyloarthritis
• ISSN: 0003-4967; 1468-2060; 1468-2060
• DOI: 10.1136/annrheumdis-2023-eular.3030

BackgroundIn axial spondyloarthritis (axSpA), early diagnosis plays a key role in preventing disease progression. However, a validated diagnostic algorithm does not exist, while classification criteria are frequently misused diagnostically.ObjectivesTo identify which decision model is being used for diagnosing patients with axSpA based on evaluations made in daily practice.MethodsComplete clinical data of 399 patients who presented with chronic back pain in a specialized university clinic were retrospectively evaluated. All patients received complete rheumatologic examination. The total dataset was randomly split into training and test datasets at a 7/3 ratio. A model was built to classify patients into axSpA and non-axSpA based on the random forest algorithm, an ensemble machine learning technique which allows computing the importance of each variable in the statistical modelling process. The Mean Decrease Gini measure was used for the variable importance. The overall accuracy, sensitivity, specificity, and the area under the receiver operating characteristic (ROC) curve (AUC) in the test dataset were calculated.ResultsIn total, 183 patients were diagnosed with axSpA and 216 with non-SpA (Table 1). In the test dataset, the model reached an accuracy of 0.9315, a sensitivity of 0.9634, a specificity of 0.8906, and an AUC of 0.9868 (Figure 1A). HLA-B27 positivity, erosion on SIJ MRI, and elevated CRP played the most important role in the statistical modelling process followed by awakening at second half of night due to back pain and bone marrow edema and fat metaplasia on SIJ MRI (Figure 1B).ConclusionMachine learning-based random forest classifier revealed a high performance in diagnosing patients with chronic back pain with axSpA and excluding patients with non-SpA using clinical, laboratory and imaging characteristics as evaluated in a daily practice scenario of a SpA-specialized clinic. External validation of the model is needed to investigate its clinical utility as a diagnostic decision support tool.Table 1.Patient characteristicsno axSpA, N = 2161axSpA, N = 1831Male105 (49%)111 (61%)Age35 (28, 43)36 (27, 47)Symptom duration1.5 (0.5, 5.0)2.0 (1.0, 5.0)Insidious onset of back pain94 (44%)177 (97%)Improvement with exercise of back pain119 (55%)140 (77%)Morning stiffness of back pain61 (28%)103 (56%)Awakening at second half of night due to back pain87 (40%)24 (13%)Arthritis24 (11%)52 (28%)Uveitis4 (1.9%)33 (18%)Dactylitis15 (6.9%)9 (4.9%)Psoriasis18 (8.3%)21 (11%)Inflammatory bowel disease6 (2.8%)11 (6.0%)Good NSAID response100 (46%)151 (83%)Elevated CRP36 (17%)108 (59%)HLA-B27 positivity35 (16%)125 (68%)Bone marrow edema on SIJ MRI76 (35%)140 (77%)Erosion on SIJ MRI4 (1.9%)88 (48%)Sclerosis on SIJ MRI71 (33%)110 (60%)Fat metaplasia on SIJ MRI17 (7.9%)81 (44%)Ankylosis on conventional radiograph1 (0.5%)28 (15%)Family history for axSpA18 (8.3%)59 (32%)1 n (%); Median (IQR). axSpA: axial spondyloarthritis; MRI: magnetic-resonance-imaging; NSAID: non-steroidal anti-inflammatory drug; SIJ: sacroiliac-jointsFigure 1.REFERENCES:NIL.Acknowledgements:NIL.Disclosure of InterestsNone Declared.