{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T12:25:50Z","timestamp":1777551950182,"version":"3.51.4"},"reference-count":29,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["DIGITAL HEALTH"],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Flares of axial spondyloarthritis (axSpA) are common yet unpredictable. We aimed to develop and internally validate a machine learning (ML) model to forecast flares 3, 6, 9 and 12 months ahead using routinely collected electronic health record (EHR) data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We performed a retrospective cohort study of 282 axSpA patients (January 2018 to May 2024) in our centre. Flares were defined as a\u2009\u2265\u20092.1 unit rise in Bath Ankylosing Spondylitis Disease Activity Index (BASDAI), \u2265 0.9 unit rise in axSpA Disease Activity Score and clinician confirmed flare. Ninety-eight candidate predictors spanning demographics, patient-reported outcomes, laboratory indices and comorbidities were aggregated into time-series windows. We applied Light Gradient-Boosting Machine (LGBM) and eXtreme Gradient Boosting to forecast the risk of flare. Model interpretability was assessed with SHapley Additive exPlanations (SHAP).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Of 282 patients, 100 (35.5%) experienced at least one flare. Our LGBM model demonstrated key 3-month metrics of: accuracy 0.846 (95% CI 0.545\u20130.980), sensitivity 0.833 (95% CI 0.358\u20130.995), specificity 0.857 (95% CI 0.421\u20130.996) and area under the receiver operating characteristic curve (AUROC) 0.845 (95% CI 0.615\u20131.000). Performance decreased modestly at 12 months, AUROC 0.773 (95% CI 0.562\u20130.984). Top SHAP contributors included comorbidity burden, BASDAI, CRP deviation, lymphocyte count, age and deprivation index. Individual-level SHAP plots enabled personalised risk profiles.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This proof-of-concept study demonstrates the feasibility of explainable ML models to predict axSpA flares up to 1 year in advance using real-world EHR data. Embedding the algorithm in electronic records could triage high-risk patients to earlier review and therapy adjustment. This approach offers a novel strategy to inform treat-to-target care pathways and support future integration into digital rheumatology systems.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/20552076261433513","type":"journal-article","created":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T13:10:46Z","timestamp":1777122646000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Explainable machine learning for predicting disease flares in axial spondyloarthritis: A real-world electronic health record-based pilot study"],"prefix":"10.1177","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2323-8161","authenticated-orcid":false,"given":"Antoni","family":"Chan","sequence":"first","affiliation":[{"name":"University of Reading"},{"name":"University Department of Rheumatology, Royal Berkshire NHS Foundation Trust, Reading, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pradip","family":"Moon","sequence":"additional","affiliation":[{"name":"University of Reading"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weizi","family":"Li","sequence":"additional","affiliation":[{"name":"University of Reading"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eghosa","family":"Bazuaye","sequence":"additional","affiliation":[{"name":"Royal Berkshire NHS Foundation Trust"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2026,4,25]]},"reference":[{"key":"e_1_3_2_2_2","volume-title":"Axial Spondyloarthritis: A Review","author":"Bittar M","year":"2024","unstructured":"Bittar M, Deodhar A. Axial Spondyloarthritis: A Review. Chicago, IL: JAMA, 2024."},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1097\/BOR.0000000000000883"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1002\/acr.23768"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2023.1280266"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13075-023-03050-6"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1136\/ard.2009.108233"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbspin.2014.12.008"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10067-019-04803-y"},{"key":"e_1_3_2_10_2","first-page":"727","article-title":"Machine-learning derived algorithms for prediction of radiographic progression in early axial spondyloarthritis","volume":"41","author":"Garofoli R","year":"2023","unstructured":"Garofoli R, Resche-Rigon M, Roux C, et al. Machine-learning derived algorithms for prediction of radiographic progression in early axial spondyloarthritis. Clin Exp Rheumatol 2023; 41: 727\u2013734.","journal-title":"Clin Exp Rheumatol"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1093\/rheumatology\/keaa768"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.berh.2023.101857"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.3899\/jrheum.090899"},{"key":"e_1_3_2_14_2","first-page":"954","article-title":"Definition of disease flare in ankylosing spondylitis: the patients\u2019 perspective","volume":"29","author":"Brophy S","year":"2002","unstructured":"Brophy S, Calin A. Definition of disease flare in ankylosing spondylitis: the patients\u2019 perspective. J Rheumatol 2002; 29: 954\u2013958.","journal-title":"J Rheumatol"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.3899\/jrheum.160838"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1002\/acr.24515"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbspin.2022.105422"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1093\/rheumatology\/kew303"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13075-018-1644-6"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1136\/annrheumdis-2017-212629"},{"key":"e_1_3_2_21_2","first-page":"472","article-title":"C-reactive protein thresholds for discriminating active disease in axial spondyloarthritis: should we lower them?","volume":"43","author":"Alonso-Castro S","year":"2025","unstructured":"Alonso-Castro S, Del Pozo PG, Alvarez P, et al. C-reactive protein thresholds for discriminating active disease in axial spondyloarthritis: should we lower them? Clin Exp Rheumatol 2025; 43: 472\u2013476.","journal-title":"Clin Exp Rheumatol"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1136\/ard.2009.120139"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/6642486"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10067-023-06703-8"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2023-078378"},{"key":"e_1_3_2_26_2","first-page":"223","article-title":"Protocol for development of a risk of bias assessment tool for diagnostic and prognositc prediction studies based on artificial intelligence: PROBAST-AI","volume":"388","author":"Navarro CLA","year":"2024","unstructured":"Navarro CLA, Damen JA, Hooft L, et al. Protocol for development of a risk of bias assessment tool for diagnostic and prognositc prediction studies based on artificial intelligence: PROBAST-AI. Quality Of Mach Learning Prediction Models Healthcare 2024; 388: 223\u2013-238.","journal-title":"Quality Of Mach Learning Prediction Models Healthcare"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1177\/20552076241272657"},{"key":"e_1_3_2_28_2","article-title":"Explainable machine learning-based prediction of psoriatic arthritis flares using heterogenous real-world data for personalised patient care","author":"Moon P","year":"2025","unstructured":"Moon P, Li W, Chan A, et al. Explainable machine learning-based prediction of psoriatic arthritis flares using heterogenous real-world data for personalised patient care. Methods 2025; 246.","journal-title":"Methods"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000422"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.3390\/jcm13216559"}],"container-title":["DIGITAL HEALTH"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/20552076261433513","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/20552076261433513","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/20552076261433513","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T17:56:25Z","timestamp":1777398985000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/20552076261433513"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":29,"alternative-id":["10.1177\/20552076261433513"],"URL":"https:\/\/doi.org\/10.1177\/20552076261433513","relation":{},"ISSN":["2055-2076","2055-2076"],"issn-type":[{"value":"2055-2076","type":"print"},{"value":"2055-2076","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]},"article-number":"20552076261433513"}}