{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T06:15:06Z","timestamp":1790748906917,"version":"4.1.0"},"reference-count":36,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T00:00:00Z","timestamp":1765843200000},"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. Med."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>As a globally significant infectious disease, the tuberculosis bacterium can not only cause pulmonary tuberculosis through respiratory tract infection but also spread from pulmonary lesions to organs throughout the body via the blood or lymphatic system, resulting in extrapulmonary tuberculosis (EPTB). However, achieving early and accurate diagnosis of EPTB remains a major clinical challenge.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this study, 1,580 patients were identified as samples for analysis. Through the process of decollinearity and characterization, seven routine blood markers: Basophil (BASO), Hemoglobin (HB), Mean erythrocyte hemoglobin concentration (MCHC), mean corpuscular volume (MCV), mean platelet volume (MPV), Red Blood Cell (RBC), Lymph and red blood cell distribution width coefficient of variation (RDW-CV), one cytokine: interleukin-6 (IL-6), and three lymphocyte-related indices: CD4+ T cell, CD4+\/CD8+ T cells, CD8+ T cells were included in the subsequent model construction. Then nine machine learning (ML) algorithms were used to construct predictive models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The most outstanding one is the K-Nearest Neighbors (KNN) model, which has an AUC value as high as 0.846, with sensitivity and specificity of 0.769 and 0.786, respectively, shows strong prediction effectiveness. Among them, CD4+ T cells, HB, and MPV ranked the top three in terms of importance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>In conclusion, we have developed an interpretable ML model to identify EPTB based on data from routine laboratory tests, which provides some assistance in early diagnosis.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2025.1712073","type":"journal-article","created":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T13:27:38Z","timestamp":1765891658000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Machine learning of immune-related laboratory indicators enables discrimination between pulmonary and extrapulmonary tuberculosis"],"prefix":"10.3389","volume":"12","author":[{"given":"Shuanglin","family":"Gu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yichen","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tengyue","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiuchang","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenxian","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zihao","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Apeng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changhua","family":"Yi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,12,16]]},"reference":[{"key":"ref1","volume-title":"Global tuberculosis report 2024","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"S629","DOI":"10.1093\/infdis\/jix362","article-title":"What we know about tuberculosis transmission: An overview","volume":"216","author":"Churchyard","year":"2017","journal-title":"J Infect Dis"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1038\/nrmicro749","article-title":"Tuberculosis: a problem with persistence","volume":"1","author":"Stewart","year":"2003","journal-title":"Nat Rev Microbiol"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"1292","DOI":"10.1164\/ajrccm\/148.5.1292","article-title":"Relationship of the manifestations of tuberculosis to CD4 cell counts in patients with human immunodeficiency virus infection","volume":"148","author":"Jones","year":"1993","journal-title":"Am Rev Respir Dis"},{"key":"ref5","first-page":"658","article-title":"Tuberculosis immunology in children: diagnostic and therapeutic challenges and opportunities","volume":"8","author":"Lewinsohn","year":"2004","journal-title":"Int J Tuberc Lung Dis"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"e30405","DOI":"10.1097\/md.0000000000030405","article-title":"Diagnosis and treatment of tuberculosis in adults with HIV","volume":"101","author":"Yang","year":"2022","journal-title":"Medicine"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1146\/annurev-immunol-042617-053420","article-title":"The immune response to Mycobacterium tuberculosis in HIV-1-coinfected persons","volume":"36","author":"Esmail","year":"2018","journal-title":"Annu Rev Immunol"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1186\/s13244-022-01172-0","article-title":"Extrapulmonary tuberculos\u0131s: an old but resurgent problem","volume":"13","author":"Baykan","year":"2022","journal-title":"Insights Imaging"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"1019","DOI":"10.1055\/s-0031-1273429","article-title":"Extrapulmonary tuberculosis: radiological imaging of an almost forgotten transformation artist","volume":"183","author":"Heye","year":"2011","journal-title":"Rofo"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"705","DOI":"10.1136\/thx.2006.075754","article-title":"A systematic review of commercial serological antibody detection tests for the diagnosis of extrapulmonary tuberculosis","volume":"83","author":"Steingart","year":"2007","journal-title":"Thorax"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1128\/microbiolspec.TBTB2-0019-2016","article-title":"Tuberculosis diagnostics: state of the art and future directions","volume":"4","author":"Pai","year":"2016","journal-title":"Microbiol Spectr"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"703","DOI":"10.1038\/s41571-019-0252-y","article-title":"Artificial intelligence in digital pathology - new tools for diagnosis and precision oncology","volume":"16","author":"Bera","year":"2019","journal-title":"Nat Rev Clin Oncol"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1126\/science.aaa8415","article-title":"Machine learning: trends, perspectives, and prospects","volume":"349","author":"Jordan","year":"2015","journal-title":"Science"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"965","DOI":"10.1186\/s12879-022-07954-7","article-title":"Development of diagnostic algorithm using machine learning for distinguishing between active tuberculosis and latent tuberculosis infection","volume":"22","author":"Luo","year":"2022","journal-title":"BMC Infect Dis"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"100648","DOI":"10.1016\/j.xinn.2024.100648","article-title":"A multimodal integration pipeline for accurate diagnosis, pathogen identification, and prognosis prediction of pulmonary infections","volume":"5","author":"Shao","year":"2024","journal-title":"Innovation"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"106931","DOI":"10.1016\/j.ress.2020.106931","article-title":"Accident prediction accuracy assessment for highway-rail grade crossings using random forest algorithm compared with decision tree","volume":"200","author":"Zhou","year":"2020","journal-title":"Reliab Eng Syst Saf"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"5713","DOI":"10.1109\/tnnls.2018.2812279","article-title":"Adaptive learning-based -nearest neighbor classifiers with resilience to class imbalance","volume":"29","author":"Mullick","year":"2018","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1016\/j.jiph.2019.07.001","article-title":"Pulmonary vs. extra-pulmonary tuberculosis hospitalizations in the US [1998\u20132014]","volume":"13","author":"Banta","year":"2020","journal-title":"J Infect Public Health"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1477493","DOI":"10.1080\/16549716.2018.1477493","article-title":"Catastrophic costs of tuberculosis care: a mixed methods study from Puducherry, India","volume":"11","author":"Prasanna","year":"2018","journal-title":"Glob Health Action"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1080\/14737159.2023.2223980","article-title":"Diagnosis of extrapulmonary tuberculosis by GeneXpert MTB\/RIF ultra assay","volume":"23","author":"Dahiya","year":"2023","journal-title":"Expert Rev Mol Diagn"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/j.ijid.2022.12.005","article-title":"Extrapulmonary tuberculosis in China: a national survey","volume":"128","author":"Li","year":"2023","journal-title":"Int J Infect Dis"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1016\/j.tube.2014.01.005","article-title":"Programmed death-1 receptor suppresses \u03b3-IFN producing NKT cells in human tuberculosis","volume":"94","author":"Singh","year":"2014","journal-title":"Tuberculosis (Edinb)"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"1252","DOI":"10.3389\/fimmu.2017.01252","article-title":"IL-17 production from T helper 17, mucosal-associated invariant T, and \u03b3\u03b4 cells in tuberculosis infection and disease","volume":"8","author":"Coulter","year":"2017","journal-title":"Front Immunol"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"e136222","DOI":"10.1172\/JCI136222","article-title":"The knowns and unknowns of latent Mycobacterium tuberculosis infection","volume":"131","author":"Boom","year":"2021","journal-title":"J Clin Invest"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"3087","DOI":"10.1128\/iai.67.6.3087-3095.1999","article-title":"Increased antimycobacterial immunity in interleukin-10-deficient mice","volume":"67","author":"Murray","year":"1999","journal-title":"Infect Immun"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1038\/s41385-019-0217-6","article-title":"Limited recognition of Mycobacterium tuberculosis\u2212infected macrophages by polyclonal CD4 and CD8 T cells from the lungs of infected mice","volume":"13","author":"Patankar","year":"2020","journal-title":"Mucosal Immunol"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"6287545","DOI":"10.1155\/2020\/6287545","article-title":"Machine learning-based differentiation of nontuberculous mycobacteria lung disease and pulmonary tuberculosis using CT images","volume":"2020","author":"Xing","year":"2020","journal-title":"Biomed Res Int"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"e523","DOI":"10.1002\/ctm2.523","article-title":"Machine learning algorithms utilizing blood parameters enable early detection of immunethrombotic dysregulation in COVID-19","volume":"11","author":"Zhou","year":"2021","journal-title":"Clin Transl Med"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"1905","DOI":"10.1093\/cid\/ciz1070","article-title":"Differential expression of activation markers by Mycobacterium tuberculosis-specific CD4+ T cell distinguishes extrapulmonary from pulmonary tuberculosis and latent infection","volume":"71","author":"Silveira-Mattos","year":"2020","journal-title":"Clin Infect Dis"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1111\/imr.12274","article-title":"T cells and adaptive immunity to Mycobacterium tuberculosis in humans","volume":"264","author":"Jasenosky","year":"2015","journal-title":"Immunol Rev"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1101\/2024.08.22.609198","article-title":"CD4 (+) T cells recruit, then engage macrophages in cognate interactions to clear Mycobacterium tuberculosis from the lungs","author":"Becker","year":"2024","journal-title":"bioRxiv"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"e1002063","DOI":"10.1371\/journal.ppat.1002063","article-title":"Suboptimal activation of antigen-specific CD4+ effector cells enables persistence of M. tuberculosis in vivo","volume":"7","author":"Bold","year":"2011","journal-title":"PLoS Pathog"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"871","DOI":"10.1016\/j.cell.2010.02.029","article-title":"Nonresolving inflammation","volume":"140","author":"Nathan","year":"2010","journal-title":"Cell"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1038\/nrmicro1930","article-title":"Viral infection and iron metabolism","volume":"6","author":"Drakesmith","year":"2008","journal-title":"Nat Rev Microbiol"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1186\/2049-6958-9-11","article-title":"Mean platelet volume as an inflammation marker in active pulmonary tuberculosis","volume":"9","author":"Gunluoglu","year":"2014","journal-title":"Multidiscip Respir Med"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1016\/j.pbj.2017.05.005","article-title":"Role of platelets in immune system and inflammation","volume":"2","author":"Sonmez","year":"2017","journal-title":"Porto Biomed J"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1712073\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T13:27:39Z","timestamp":1765891659000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1712073\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,16]]},"references-count":36,"alternative-id":["10.3389\/fmed.2025.1712073"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2025.1712073","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,16]]},"article-number":"1712073"}}