{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T00:40:31Z","timestamp":1792629631205,"version":"4.5.0"},"reference-count":25,"publisher":"BMJ","issue":"2","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"unspecified","delay-in-days":92,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["Lupus Sci Med"],"accepted":{"date-parts":[[2025,9,6]]},"published-print":{"date-parts":[[2025,7]]},"abstract":"<jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>To evaluate the diagnostic and prognostic performance of the neutrophil to lymphocyte ratio (NLR) and platelet to lymphocyte ratio (PLR) in SLE and to integrate these biomarkers into an interpretable artificial intelligence (AI) model for clinical decision support.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Design<\/jats:title>\n                    <jats:p>We conducted a two-phase mixed-methods study: (1) a meta-analysis of 50 studies (n=12\u2009850\u2009patients with SLE), compliant with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses, and (2) the development and validation of an XGBoost machine learning model, guided by the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis-AI, with SHapley Additive exPlanations (SHAP) explainability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Setting<\/jats:title>\n                    <jats:p>Our analysis used multicentre data from global SLE registries, including cohorts from Asia, Europe, North America and Africa.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Participants<\/jats:title>\n                    <jats:p>The study included adults (\u226518 years) who met the 2019 European League Against Rheumatism\/American College of Rheumatology classification criteria for SLE, with NLR and PLR measured via standardised complete blood count. Comparator groups consisted of healthy controls and patients with non-SLE autoimmune diseases.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Interventions<\/jats:title>\n                    <jats:p>NLR and PLR were assessed as biomarkers for SLE activity and complications. Our AI model integrated these ratios with standard clinical biomarkers and multi-omics data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Primary and secondary outcome measures<\/jats:title>\n                    <jats:p>The primary outcome was diagnostic accuracy (measured by area under the curve (AUC), sensitivity and specificity) for active SLE (defined as Systemic Lupus Erythematosus Disease Activity Index \u22656). Secondary outcomes included prognostic value (HRs for lupus nephritis, cardiovascular events and mortality) and treatment response monitoring.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Our analysis demonstrated that NLR has superior diagnostic accuracy for active SLE compared with PLR, with a pooled AUC of 0.85 vs 0.78 (p=0.02). NLR showed pooled sensitivity and specificity of 78% and 82%, respectively, while PLR showed 70% and 75%. Elevated NLR (&gt;3.5) and PLR (&gt;185) predicted higher risks of lupus nephritis (HR=2.1\u2009and 1.8, respectively), cardiovascular events (HR=2.3\u2009and 1.9) and mortality (HR=3.1\u2009and 2.1; all p&lt;0.01). We identified significant ethnic variations, with optimal NLR cut-offs of &gt;3.1 for Asian populations, &gt;2.8 for Caucasian populations and &gt;3.4 for African populations. The AI model achieved an AUC of 0.87 in training and 0.82 in validation, with NLR emerging as the top predictive feature (SHAP score=0.25).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>NLR outperforms PLR in SLE diagnosis and risk stratification, with validated cut-offs that vary significantly by ethnicity. The integration of these biomarkers into AI models enhances predictive accuracy, supporting the use of NLR and PLR as cost-effective tools for SLE management.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/lupus-2025-001696","type":"journal-article","created":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T06:15:23Z","timestamp":1759299323000},"page":"e001696","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":8,"title":["NLR outperforms PLR in SLE diagnosis and prognosis: an AI-enhanced meta-analysis of 12 850 patients with ethnicity-specific cut-offs"],"prefix":"10.1136","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2266-1569","authenticated-orcid":false,"given":"Naif Taleb","family":"Ali","sequence":"first","affiliation":[{"name":"Department of Laboratory Sciences, University of Lahej, Saber, Yemen"},{"name":"Department of Health Sciences, University of Science and Technology, Aden, Yemen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gamila Saleh","family":"Ali","sequence":"additional","affiliation":[{"name":"Medicine, University of Aden Faculty of Medicine and Health Science, Aden, Yemen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6144-4769","authenticated-orcid":false,"given":"Hana","family":"Mohsen Ali","sequence":"additional","affiliation":[{"name":"Medicine, University of Aden Faculty of Medicine and Health Science, Aden, Yemen"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2025,9,30]]},"reference":[{"key":"2026010700553665000_12.2.e001696.1","doi-asserted-by":"publisher","DOI":"10.1136\/annrheumdis-2020-218272"},{"key":"2026010700553665000_12.2.e001696.2","doi-asserted-by":"publisher","DOI":"10.1002\/art.40930"},{"key":"2026010700553665000_12.2.e001696.3","doi-asserted-by":"publisher","DOI":"10.1016\/j.intimp.2016.04.006"},{"key":"2026010700553665000_12.2.e001696.4","first-page":"456","article-title":"Neutrophil heterogeneity in SLE: Emerging roles of LDGs and NETosis","volume":"75","author":"Liu","year":"2023","journal-title":"Arthritis Rheumatol"},{"key":"2026010700553665000_12.2.e001696.5","doi-asserted-by":"publisher","DOI":"10.1038\/nm.4027"},{"key":"2026010700553665000_12.2.e001696.6","doi-asserted-by":"crossref","DOI":"10.3389\/fimmu.2012.00380","article-title":"Proteins derived from neutrophil extracellular traps may serve as self-antigens and mediate organ damage in autoimmune diseases","volume":"3","author":"Knight","year":"2012","journal-title":"Front Immunol"},{"key":"2026010700553665000_12.2.e001696.7","first-page":"332","article-title":"Diagnostic accuracy of neutrophil-to-lymphocyte ratio for active systemic lupus erythematosus: a meta-analysis","volume":"31","author":"Huang","year":"2022","journal-title":"Lupus"},{"key":"2026010700553665000_12.2.e001696.8","doi-asserted-by":"crossref","unstructured":"Zhang X , Wang Q , Zhang Y , et al . Platelet-to-lymphocyte ratio as a novel biomarker for systemic lupus erythematosus activity: evidence from meta-analysis. Autoimmun Rev 2021;20. doi:10.1016\/j.autrev.2021.102976","DOI":"10.1016\/j.autrev.2021.102976"},{"key":"2026010700553665000_12.2.e001696.9","first-page":"189","article-title":"Ethnic variation in neutrophil-to-lymphocyte ratio (NLR) thresholds for systemic lupus erythematosus: a multinational study","volume":"50","author":"Vega","year":"2023","journal-title":"J Rheumatol"},{"key":"2026010700553665000_12.2.e001696.10","first-page":"95","article-title":"Baseline characteristics of a multiethnic lupus cohort: PROFILE","volume":"11","author":"Alarc\u00f3n","year":"2002","journal-title":"Lupus (Los Angel)"},{"key":"2026010700553665000_12.2.e001696.11","first-page":"20","article-title":"Artificial intelligence in rheumatology: advances and opportunities","volume":"19","author":"Yang","year":"2023","journal-title":"Nat Rev Rheumatol"},{"key":"2026010700553665000_12.2.e001696.12","first-page":"1589","article-title":"Machine learning identifies distinct biomarker patterns for lupus nephritis and disease activity","volume":"81","author":"Narain","year":"2022","journal-title":"Ann Rheum Dis"},{"key":"2026010700553665000_12.2.e001696.13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2005.02.022"},{"key":"2026010700553665000_12.2.e001696.14","doi-asserted-by":"crossref","DOI":"10.1136\/bmj.k4597","article-title":"A guide to systematic review and meta-analysis of prognostic factor studies","volume":"364","author":"Riley","year":"2019","journal-title":"BMJ"},{"key":"2026010700553665000_12.2.e001696.15","doi-asserted-by":"crossref","DOI":"10.1136\/bmjopen-2020-048008","article-title":"Protocol for development of a reporting guideline (TRIPOD-AI) and risk of bias tool (PROBAST-AI) for diagnostic and prognostic prediction model studies based on artificial intelligence","volume":"11","author":"Collins","year":"2021","journal-title":"BMJ Open"},{"key":"2026010700553665000_12.2.e001696.16","doi-asserted-by":"crossref","DOI":"10.3390\/jcm10020243","article-title":"The Main Challenges in Systemic Lupus Erythematosus: Where Do We Stand?","volume":"10","author":"Piga","year":"2021","journal-title":"J Clin Med"},{"key":"2026010700553665000_12.2.e001696.17","doi-asserted-by":"crossref","first-page":"891","DOI":"10.1002\/acr.22583","article-title":"Distinctions Between Diagnostic and Classification Criteria?","volume":"67","author":"Aggarwal","year":"2015","journal-title":"Arthritis Care & Research"},{"key":"2026010700553665000_12.2.e001696.18","first-page":"2799","article-title":"Racial disparities in lupus nephritis: a cohort analysis","volume":"44","author":"Alarc\u00f3n","year":"2001","journal-title":"Arthritis Rheum"},{"key":"2026010700553665000_12.2.e001696.19","first-page":"103000","article-title":"Autoantibody clusters in SLE: A multi-omics reappraisal","volume":"135","author":"Giannouli","year":"2023","journal-title":"J Autoimmun"},{"key":"2026010700553665000_12.2.e001696.20","first-page":"e401","article-title":"Machine learning to predict anti-drug antibodies in patients with autoimmune diseases","volume":"4","author":"Guan","year":"2022","journal-title":"Lancet Rheumatol"},{"key":"2026010700553665000_12.2.e001696.21","first-page":"658","article-title":"Practice-based costs of SLE care in the United States: the Lupus Pacific Registry","volume":"73","author":"Yazdany","year":"2021","journal-title":"Arthritis Care Res"},{"key":"2026010700553665000_12.2.e001696.22","doi-asserted-by":"publisher","DOI":"10.1136\/ard.2006.068676"},{"key":"2026010700553665000_12.2.e001696.23","doi-asserted-by":"publisher","DOI":"10.1002\/art.34426"},{"key":"2026010700553665000_12.2.e001696.24","doi-asserted-by":"crossref","unstructured":"Dizon BLP , Redmond C , Gotschlich EC , et al . 2023 Clinical outcomes and safety of anakinra in the treatment of multisystem inflammatory syndrome in children: a single center observational study. Pediatr Rheumatol 21. doi:10.1186\/s12969-023-00858-z","DOI":"10.1186\/s12969-023-00858-z"},{"key":"2026010700553665000_12.2.e001696.25","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2016.05.057"}],"container-title":["Lupus Science &amp; Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/lupus-2025-001696","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T08:56:11Z","timestamp":1767776171000},"score":1,"resource":{"primary":{"URL":"https:\/\/lupus.bmj.com\/lookup\/doi\/10.1136\/lupus-2025-001696"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":25,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,9,30]]},"published-print":{"date-parts":[[2025,7]]}},"alternative-id":["10.1136\/lupus-2025-001696"],"URL":"https:\/\/doi.org\/10.1136\/lupus-2025-001696","relation":{},"ISSN":["2053-8790"],"issn-type":[{"value":"2053-8790","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}