{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T21:12:49Z","timestamp":1790111569657,"version":"4.0.1"},"reference-count":47,"publisher":"BMJ","issue":"1","license":[{"start":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T00:00:00Z","timestamp":1777248000000},"content-version":"unspecified","delay-in-days":116,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Luzhou Municipal People\u2019s Government-Southwest Medical University Science and Technology Strategic Cooperation Project Fund","award":["2023LZXNYDJ021"],"award-info":[{"award-number":["2023LZXNYDJ021"]}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["Lupus Sci Med"],"accepted":{"date-parts":[[2026,4,13]]},"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>The diagnosis of systemic lupus erythematosus (SLE) is clinically complex, and early identification is essential for timely intervention and reducing disease burden. Machine learning offers a promising approach to distinguish early-stage SLE patients from healthy individuals.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A total of 2672 SLE patients and 154\u2009798 healthy controls from the Luzhou (discovery) cohort, along with 2532 SLE patients and 38\u2009597 healthy controls from the Enshi (validation) cohort, were enrolled in this study. A complete machine learning pipeline\u2014including data preprocessing, feature selection, model training and postanalysis, was developed in the Luzhou cohort and subsequently validated in the Enshi cohort. Optimal features and the best-performing model were identified in the Luzhou cohort, then scaled and validated in the Enshi cohort. Model performance was evaluated using 13 binary classification metrics. The optimal feature set and model were integrated to construct an Artificial Intelligence Prediction tool for SLE (AI-PSLE).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Fifty candidate features were initially selected in the Luzhou cohort, among which the light gradient boosting (LGB) model demonstrated the best performance following data preprocessing. After scaling in the Enshi cohort, 35 reproducible features were retained. The LGB model based on these 35 features maintained superior performance in the Luzhou cohort and was further successfully validated in both the Enshi and combined Luzhou+Enshi cohorts.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>We developed an open-access, clinically user-friendly tool-AI-PSLE-based on 35 routine features, aimed at facilitating the early identification of SLE patients from healthy populations.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/lupus-2026-002007","type":"journal-article","created":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T12:40:25Z","timestamp":1777293625000},"page":"e002007","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":1,"title":["Validity and applicability of machine learning models for systemic lupus erythematosus diagnosis"],"prefix":"10.1136","volume":"13","author":[{"given":"Rui-Cen","family":"Li","sequence":"first","affiliation":[{"name":"Health Management Center, West China Hospital, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3860-8383","authenticated-orcid":false,"given":"An-Fang","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Rheumatology and Immunology, The Affiliated Hospital, Luzhou, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin-Chong","family":"Su","sequence":"additional","affiliation":[{"name":"Hubei Provincial Key Laboratory of Occurrence and Intervention of Rheumatic Diseases, Affiliated Minda Hospital of Hubei Minzu University, Enshi, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Da-Cheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Evidence-Based Medicine, Southwest Medical University, Luzhou, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8276-1249","authenticated-orcid":false,"given":"Wang-Dong","family":"Xu","sequence":"additional","affiliation":[{"name":"Southwest Medical University, Luzhou, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2026,4,27]]},"reference":[{"key":"2026072811151716000_13.1.e002007.1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2024.2315"},{"key":"2026072811151716000_13.1.e002007.2","doi-asserted-by":"crossref","first-page":"1613441","DOI":"10.3389\/fimmu.2025.1613441","article-title":"Air pollution, emerging chemical exposures, and systemic lupus erythematosus: a meta-epidemiology study","volume":"16","author":"Xu","year":"2025","journal-title":"Front Immunol"},{"key":"2026072811151716000_13.1.e002007.3","doi-asserted-by":"crossref","DOI":"10.1136\/lupus-2024-001385","article-title":"Higher PM2.5 exposure increases the risk of incident systemic lupus erythematosus: a prospective cohort study in Taiwan","volume":"12","author":"Lai","year":"2025","journal-title":"Lupus Sci Med"},{"key":"2026072811151716000_13.1.e002007.4","doi-asserted-by":"crossref","DOI":"10.1186\/s12931-026-03532-6","article-title":"Triggering mechanisms of acute thunderstorm asthma: epithelial barrier disruption and immune dysregulation","volume":"27","author":"Xiao","year":"2026","journal-title":"Respir Res"},{"key":"2026072811151716000_13.1.e002007.5","doi-asserted-by":"crossref","DOI":"10.3390\/antiox15010089","article-title":"Seasonal Variation in PM2.5 Composition Modulates Oxidative Stress and Neutrophilic Inflammation with Involvement of TLR4 Signaling","volume":"15","author":"Wang","year":"2026","journal-title":"Antioxidants (Basel)"},{"key":"2026072811151716000_13.1.e002007.6","doi-asserted-by":"publisher","DOI":"10.1007\/s00296-011-1971-2"},{"key":"2026072811151716000_13.1.e002007.7","first-page":"212","article-title":"The Importance of an Early Diagnosis in Systemic Lupus Erythematosus","volume":"18","author":"Sebastiani","year":"2016","journal-title":"Isr Med Assoc J"},{"key":"2026072811151716000_13.1.e002007.8","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1016\/j.ard.2025.09.007","article-title":"EULAR recommendations for the management of systemic lupus erythematosus with kidney involvement: 2025 update","volume":"85","author":"Fanouriakis","year":"2026","journal-title":"Ann Rheum Dis"},{"key":"2026072811151716000_13.1.e002007.9","doi-asserted-by":"publisher","DOI":"10.1136\/annrheumdis-2020-218272"},{"key":"2026072811151716000_13.1.e002007.10","doi-asserted-by":"crossref","first-page":"1400","DOI":"10.1002\/art.40930","article-title":"2019 European League Against Rheumatism\/American College of Rheumatology Classification Criteria for Systemic Lupus Erythematosus","volume":"71","author":"Aringer","year":"2019","journal-title":"Arthritis Rheumatol"},{"key":"2026072811151716000_13.1.e002007.11","doi-asserted-by":"publisher","DOI":"10.1002\/art.34473"},{"key":"2026072811151716000_13.1.e002007.12","first-page":"773","article-title":"Health care utilization and costs of systemic lupus erythematosus in the United States: A systematic review","volume":"31","author":"Lin","year":"2022","journal-title":"Lupus (Los Angel)"},{"key":"2026072811151716000_13.1.e002007.13","doi-asserted-by":"crossref","unstructured":"Zhang D , Liang F , Li Q , et al . Air pollution, meteorological factors, and cardiac remodelling in children: a multi-omics cohort study. Eur Heart J 2026. doi:10.1093\/eurheartj\/ehaf1086","DOI":"10.1093\/eurheartj\/ehaf1086"},{"key":"2026072811151716000_13.1.e002007.14","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1016\/j.fmre.2025.08.009","article-title":"Harnessing multi-omics and machine learning for predicting immune checkpoint blockade responses: Advances, challenges, and future directions","volume":"6","author":"Cao","year":"2026","journal-title":"Fundam Res"},{"key":"2026072811151716000_13.1.e002007.15","doi-asserted-by":"publisher","DOI":"10.1007\/s00011-023-01755-7"},{"key":"2026072811151716000_13.1.e002007.16","doi-asserted-by":"publisher","DOI":"10.1007\/s00011-023-01793-1"},{"key":"2026072811151716000_13.1.e002007.17","doi-asserted-by":"crossref","DOI":"10.1186\/s13075-024-03330-9","article-title":"Early identification of macrophage activation syndrome secondary to systemic lupus erythematosus with machine learning","volume":"26","author":"Lin","year":"2024","journal-title":"Arthritis Res Ther"},{"key":"2026072811151716000_13.1.e002007.18","doi-asserted-by":"crossref","DOI":"10.1186\/s12933-025-02654-3","article-title":"Relationship between atherogenic index of plasma and length of stay in critically ill patients with atherosclerotic cardiovascular disease: a retrospective cohort study and predictive modeling based on machine learning","volume":"24","author":"Guo","year":"2025","journal-title":"Cardiovasc Diabetol"},{"key":"2026072811151716000_13.1.e002007.19","doi-asserted-by":"crossref","unstructured":"Wang L , Zhu L , Jiang J , et al . Decision tree analysis for evaluating disease activity in patients with rheumatoid arthritis. J Int Med Res 2021;49. doi:10.1177\/03000605211053232","DOI":"10.1177\/03000605211053232"},{"key":"2026072811151716000_13.1.e002007.20","doi-asserted-by":"crossref","DOI":"10.1136\/lupus-2022-000769","article-title":"Adverse pregnancy outcomes in women with systemic lupus erythematosus: can we improve predictions with machine learning?","volume":"9","author":"Fazzari","year":"2022","journal-title":"Lupus Sci Med"},{"key":"2026072811151716000_13.1.e002007.21","doi-asserted-by":"crossref","first-page":"2268","DOI":"10.1111\/jdv.20031","article-title":"Human-multimodal deep learning collaboration in \u201cprecise\u201d diagnosis of lupus erythematosus subtypes and similar skin diseases","volume":"38","author":"Li","year":"2024","journal-title":"J Eur Acad Dermatol Venereol"},{"key":"2026072811151716000_13.1.e002007.22","doi-asserted-by":"publisher","DOI":"10.1093\/rheumatology\/kead221"},{"key":"2026072811151716000_13.1.e002007.23","doi-asserted-by":"publisher","DOI":"10.18295\/squmj.12.2022.069"},{"key":"2026072811151716000_13.1.e002007.24","doi-asserted-by":"publisher","DOI":"10.1016\/j.kint.2021.11.014"},{"key":"2026072811151716000_13.1.e002007.25","doi-asserted-by":"crossref","DOI":"10.1016\/j.ebiom.2025.105785","article-title":"Advances in precision medicine for lupus nephritis: biomarker- and AI-driven diagnosis and treatment response prediction and targeted therapies","volume":"117","author":"Shang","year":"2025","journal-title":"EBioMedicine"},{"key":"2026072811151716000_13.1.e002007.26","doi-asserted-by":"crossref","DOI":"10.1186\/s13054-015-0741-z","article-title":"Glycocalyx and sepsis-induced alterations in vascular permeability","volume":"19","author":"Chelazzi","year":"2015","journal-title":"Crit Care"},{"key":"2026072811151716000_13.1.e002007.27","doi-asserted-by":"publisher","DOI":"10.3899\/jrheum.151523"},{"key":"2026072811151716000_13.1.e002007.28","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1016\/j.jcrc.2019.02.004","article-title":"Serum albumin as a risk factor for death in patients with prolonged sepsis: An observational study","volume":"51","author":"Takegawa","year":"2019","journal-title":"J Crit Care"},{"key":"2026072811151716000_13.1.e002007.29","doi-asserted-by":"crossref","first-page":"801","DOI":"10.7754\/Clin.Lab.2015.141246","article-title":"Hematocrit Level could Reflect Inflammatory Response and Disease Activity in Patients with Systemic Lupus Erythematosus","volume":"61","author":"Yang","year":"2015","journal-title":"Clin Lab"},{"key":"2026072811151716000_13.1.e002007.30","doi-asserted-by":"crossref","DOI":"10.3390\/ijms252010905","article-title":"Lymphocytes Change Their Phenotype and Function in Systemic Lupus Erythematosus and Lupus Nephritis","volume":"25","author":"Moysidou","year":"2024","journal-title":"Int J Mol Sci"},{"key":"2026072811151716000_13.1.e002007.31","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1289\/ehp.1002123","article-title":"Associations between ambient fine particulate levels and disease activity in patients with systemic lupus erythematosus (SLE)","volume":"119","author":"Bernatsky","year":"2011","journal-title":"Environ Health Perspect"},{"key":"2026072811151716000_13.1.e002007.32","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2019.03.018"},{"key":"2026072811151716000_13.1.e002007.33","doi-asserted-by":"publisher","DOI":"10.1289\/ehp.11092"},{"key":"2026072811151716000_13.1.e002007.34","doi-asserted-by":"crossref","first-page":"3317","DOI":"10.1007\/s10653-022-01409-3","article-title":"Associations between particulate matter air pollutants and hospitalization risk for systemic lupus erythematosus: a time-series study from Xi\u2019an, China","volume":"45","author":"Pan","year":"2023","journal-title":"Environ Geochem Health"},{"key":"2026072811151716000_13.1.e002007.35","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-023-36901-y","article-title":"Environmental risk factors of systemic lupus erythematosus: a case-control study","volume":"13","author":"Refai","year":"2023","journal-title":"Sci Rep"},{"key":"2026072811151716000_13.1.e002007.36","doi-asserted-by":"publisher","DOI":"10.1118\/1.3267037"},{"key":"2026072811151716000_13.1.e002007.37","doi-asserted-by":"crossref","DOI":"10.1186\/s13040-018-0168-6","article-title":"Collective feature selection to identify crucial epistatic variants","volume":"11","author":"Verma","year":"2018","journal-title":"BioData Min"},{"key":"2026072811151716000_13.1.e002007.38","doi-asserted-by":"crossref","first-page":"103721","DOI":"10.1016\/j.autrev.2024.103721","article-title":"Risk factors associated with thrombocytopenia in systemic lupus erythematosus: A systematic review and meta-analysis","volume":"24","author":"Yang","year":"2025","journal-title":"Autoimmun Rev"},{"key":"2026072811151716000_13.1.e002007.39","doi-asserted-by":"crossref","DOI":"10.1155\/2022\/9391136","article-title":"Survival Prediction of Children Undergoing Hematopoietic Stem Cell Transplantation Using Different Machine Learning Classifiers by Performing Chi-Square Test and Hyperparameter Optimization: A Retrospective Analysis","volume":"2022","author":"Ratul","year":"2022","journal-title":"Comput Math Methods Med"},{"key":"2026072811151716000_13.1.e002007.40","doi-asserted-by":"publisher","DOI":"10.1016\/j.autrev.2023.103294"},{"key":"2026072811151716000_13.1.e002007.41","doi-asserted-by":"crossref","unstructured":"David WH , Stanley LS , Rodney XS . Introduction to the Logistic Regression Model. Hoboken (NJ): Wiley-Blackwell, 2013:35\u201347.","DOI":"10.1002\/9781118548387.ch2"},{"key":"2026072811151716000_13.1.e002007.42","doi-asserted-by":"crossref","DOI":"10.3390\/diagnostics11091714","article-title":"Diagnosis of Diabetes Mellitus Using Gradient Boosting Machine (LightGBM)","volume":"11","author":"Rufo","year":"2021","journal-title":"Diagnostics (Basel)"},{"key":"2026072811151716000_13.1.e002007.43","doi-asserted-by":"crossref","DOI":"10.1212\/WNL.0000000000209531","article-title":"Prediction of Future Parkinson Disease Using Plasma Proteins Combined With Clinical-Demographic Measures","volume":"103","author":"You","year":"2024","journal-title":"Neurology (ECronicon)"},{"key":"2026072811151716000_13.1.e002007.44","doi-asserted-by":"crossref","first-page":"15561","DOI":"10.1038\/s41598-024-66658-x","article-title":"AI models predicting breast cancer distant metastasis using LightGBM with clinical blood markers and ultrasound maximum diameter","volume":"14","author":"Tan","year":"2024","journal-title":"Sci Rep"},{"key":"2026072811151716000_13.1.e002007.45","doi-asserted-by":"crossref","DOI":"10.2196\/51354","article-title":"Machine Learning for Predicting Risk and Prognosis of Acute Kidney Disease in Critically Ill Elderly Patients During Hospitalization: Internet-Based and Interpretable Model Study","volume":"26","author":"Li","year":"2024","journal-title":"J Med Internet Res"},{"key":"2026072811151716000_13.1.e002007.46","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2022.839197"},{"key":"2026072811151716000_13.1.e002007.47","doi-asserted-by":"crossref","DOI":"10.1002\/cti2.1093","article-title":"Machine learning applied to whole-blood RNA-sequencing data uncovers distinct subsets of patients with systemic lupus erythematosus","volume":"8","author":"Figgett","year":"2019","journal-title":"Clin Transl Immunology"}],"container-title":["Lupus Science &amp; Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/lupus-2026-002007","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T18:15:28Z","timestamp":1785262528000},"score":1,"resource":{"primary":{"URL":"https:\/\/lupus.bmj.com\/lookup\/doi\/10.1136\/lupus-2026-002007"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":47,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,4,27]]},"published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1136\/lupus-2026-002007"],"URL":"https:\/\/doi.org\/10.1136\/lupus-2026-002007","relation":{},"ISSN":["2053-8790"],"issn-type":[{"value":"2053-8790","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}