{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T20:28:41Z","timestamp":1793132921460,"version":"4.5.0"},"reference-count":25,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T00:00:00Z","timestamp":1767916800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Immunol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Rheumatoid arthritis (RA) exhibits substantial diagnostic overlap with other autoimmune diseases that share similar pathological features, leading to redundant testing and limited diagnostic specificity. Therefore, there is an urgent need to identify critical clinical indicators with high diagnostic and predictive value to improve both diagnostic efficiency and accuracy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>To address this challenge, we propose a multidimensional embedded feature selection framework based on ensemble learning. This framework integrates Gradient Boosted Decision Trees (GBDT) and Logistic Regression (LR) models to extract potential diagnostic features from multi-source clinical datasets. GBDT captures complex nonlinear interactions among features, enhancing adaptability to heterogeneous data, while LR leverages its sparsity-promoting characteristics to perform dimensionality reduction and highlight discriminative variables. To further improve interpretability, the SHapley Additive exPlanations (SHAP) algorithm was employed to quantify the contribution of each feature to the model\u2019s predictions and to identify novel diagnostic markers beyond traditional indicators.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Validated on real-world clinical data, the proposed framework achieved excellent diagnostic performance across multiple evaluation metrics, significantly enhancing the specificity and accuracy of RA diagnosis. Compared with conventional diagnostic methods, our model demonstrated marked improvements in test accuracy and area under the receiver operating characteristic curve (AUC). SHAP not only reaffirmed the importance of RF and anti-CCP but revealed that systemic metabolic indicators\u2014such as low HDL, elevated bile acids, and altered creatinine\u2014carry independent diagnostic weight. This supports a paradigm shift toward viewing RA as a multi-system inflammatory disorder, enabling earlier clinical suspicion even before classic articular manifestations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The proposed multidimensional embedded feature selection framework showed strong diagnostic performance and interpretability in identifying key biomarkers for RA, effectively addressing the issue of indicator redundancy and enhancing diagnostic precision. This pragmatic application of an established GBDT+LR framework, integrated with SHAP for interpretability and built on routine clinical data, offers potential clinical utility in RA diagnosis.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fimmu.2025.1679223","type":"journal-article","created":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T06:35:54Z","timestamp":1767940554000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Research on key indicators for diagnosis and prediction of rheumatoid arthritis based on GBDT+LR embedded feature selection model"],"prefix":"10.3389","volume":"16","author":[{"given":"Jiaqi","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenqiang","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunsheng","family":"Qu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,1,9]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1007\/s10067-024-07083-3","article-title":"Trends and future projections of incidence rate and mortality of rheumatoid arthritis in China: a systematic analysis based on GBD 2021 data","volume":"43","author":"Gu","year":"2024","journal-title":"Clin Rheumatol"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1002\/art.27584","article-title":"2010 Rheumatoid arthritis classification criteria","volume":"62","author":"Aletaha","year":"2010","journal-title":"Arthritis Rheum"},{"key":"B3","doi-asserted-by":"publisher","first-page":"797","DOI":"10.7326\/0003-4819-146-11-200706050-00008","article-title":"Meta-analysis: diagnostic accuracy of anti-cyclic citrullinated peptide antibody and rheumatoid factor for rheumatoid arthritis","volume":"146","author":"Kunihiro Nishimura","year":"2007","journal-title":"Ann Internal Med"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(17)31472-1","article-title":"Pathogenetic insights from the treatment of rheumatoid arthritis","volume":"389","author":"McInnes","year":"2017","journal-title":"Lancet"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jstrokecerebrovasdis.2022.106320","article-title":"Global metabolomic profiling reveals disrupted lipid metabolism in rheumatoid arthritis","volume":"40","author":"Sidorov","year":"2022","journal-title":"Clin Exp Rheumatol"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1093\/rheumatology\/kes378","article-title":"An evaluation of molecular and clinical remission in rheumatoid arthritis by radiographic progression","volume":"74","author":"van der Helm-van Mil","year":"2022","journal-title":"Arthritis Rheumatol"},{"key":"B7","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1155\/2022\/1926661","article-title":"From segmentation to classification: A deep learning scheme for sintered surface images processing","volume":"12","author":"Yang","year":"2024","journal-title":"Processes"},{"key":"B8","doi-asserted-by":"crossref","DOI":"10.1145\/2939672.2939785","volume-title":"XGBoost: A scalable tree boosting system","author":"Chen","year":"2016"},{"key":"B9","doi-asserted-by":"publisher","first-page":"1926661","DOI":"10.1155\/2022\/1926661","article-title":"Identification of diagnostic biomarkers, immune infiltration characteristics, and potential compounds in rheumatoid arthritis","volume":"2022","author":"Chen","year":"2022","journal-title":"BioMed Res Int"},{"key":"B10","doi-asserted-by":"publisher","first-page":"37","DOI":"10.3389\/fimmu.2024.1409555","article-title":"Machine learning for rheumatoid arthritis identification","volume":"45","author":"Shi","year":"2021","journal-title":"J Med Syst"},{"key":"B11","volume-title":"A unified approach to interpreting model predictions","author":"Lundberg","year":"2017"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2023.1204652","article-title":"Platelets-related signature based diagnostic model in rheumatoid arthritis using WGCNA and machine learning","volume":"14","author":"Liu","year":"2023","journal-title":"Front Immunol"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2023.1126647","article-title":"Identification of immune-related genes in diagnosing atherosclerosis with rheumatoid arthritis through bioinformatics analysis and machine learning","volume":"14","author":"Liu","year":"2023","journal-title":"Front Immunol"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.2174\/1386207326666230306114626","article-title":"Application of machine learning in rheumatoid arthritis diseases research: review and future directions","volume":"26","author":"Patil Kose","year":"2023","journal-title":"Comb Chem High Throughput Screen"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2023.1291727","article-title":"Machine learning to characterize bone biomarkers profile in rheumatoid arthritis","volume":"14","author":"Adami","year":"2023","journal-title":"Front Immunol"},{"key":"B16","doi-asserted-by":"publisher","first-page":"5600190","DOI":"10.1155\/2022\/5600190","article-title":"Identification of biomarkers associated with diagnosis of osteoarthritis patients based on bioinformatics and machine learning","volume":"2022","author":"Liang","year":"2022","journal-title":"J Immunol Res"},{"key":"B17","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1186\/s13075-023-03222-4","article-title":"Machine learning and molecular subtype analyses provide insights into PANoptosis-associated genes in rheumatoid arthritis","volume":"25","author":"Li","year":"2023","journal-title":"Arthritis Res Ther"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2023.1116489","article-title":"Rheumatoid arthritis and the risk of end-stage renal disease: A nationwide, population-based study","volume":"10","author":"Suh","year":"2023","journal-title":"Front Med"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1007\/s12223-023-01036-0","article-title":"Immune dysregulation and pathogenic pathways mediated by common infections in rheumatoid arthritis","volume":"68","author":"Salehi","year":"2023","journal-title":"Folia Microbiologica"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1016\/j.immuni.2022.11.009","article-title":"The pathogenesis of rheumatoid arthritis","volume":"55","author":"Alivernini","year":"2022","journal-title":"Immunity"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2022.1051082","article-title":"Systemic complications of rheumatoid arthritis: focus on pathogenesis and treatment","volume":"13","author":"Wu","year":"2022","journal-title":"Front Immunol"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2022.1007165","article-title":"Gut microbiota and rheumatoid arthritis: From pathogenesis to novel therapeutic opportunities","volume":"13","author":"Zhao","year":"2022","journal-title":"Front Immunol"},{"key":"B23","doi-asserted-by":"crossref","first-page":"129","DOI":"10.3389\/fimmu.2012.00129","article-title":"TH17 cells in autoimmunity and immunodeficiency: protective or pathogenic","volume":"3","author":"Marwaha","year":"2012","journal-title":"Front Immun"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2025.3545552","article-title":"Reliability-guaranteed fault observer design for systems with stochastic parametric uncertainty","author":"Chen","year":"2025","journal-title":"IEEE Control Syst Lett"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1016\/j.medengphy.2010.04.009","article-title":"Application of higher order statistics\/spectra in biomedical signals\u2014A review","volume":"32","author":"Chua","year":"2010","journal-title":"Med Eng Phys"}],"container-title":["Frontiers in Immunology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fimmu.2025.1679223\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T06:35:55Z","timestamp":1767940555000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fimmu.2025.1679223\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,9]]},"references-count":25,"alternative-id":["10.3389\/fimmu.2025.1679223"],"URL":"https:\/\/doi.org\/10.3389\/fimmu.2025.1679223","relation":{},"ISSN":["1664-3224"],"issn-type":[{"value":"1664-3224","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,9]]},"article-number":"1679223"}}