{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T16:29:38Z","timestamp":1787243378685,"version":"build-2736575974"},"reference-count":54,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T00:00:00Z","timestamp":1766016000000},"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. Cell. Infect. Microbiol."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>\n                      Diagnosis of active\n                      <jats:italic>Mycobacterium tuberculosis<\/jats:italic>\n                      (Mtb) infection relies on clinical symptoms, imaging, and molecular testing, but these methods are often costly and slow. Consequently, there is an urgent need for a rapid and accessible diagnostic approach that can support early detection and reduce ongoing\n                      <jats:italic>tuberculosis<\/jats:italic>\n                      transmission.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A discovery cohort of 3,829 individuals and an external validation cohort of 405 individuals were included. Six supervised machine learning models were trained using routine laboratory data, and 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>Among the six models, XGBoost demonstrated the best diagnostic performance in the internal cohort (accuracy 97.49%; sensitivity 97.56%; specificity 97.42%) and maintained strong performance in the external cohort (accuracy 93.67%; sensitivity 91.56%; specificity 91.13%). SHAP analysis indicated that key predictors reflected characteristic host-response patterns, including inflammation-related hypoalbuminemia, lipid metabolism suppression (HDL-C and LDL-C), altered platelet activity (MPV), and lymphocyte reduction (LYM).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The study presents a high-performing and interpretable machine learning model capable of accurately identifying active Mtb infection using routine blood tests. This low-cost and non-invasive approach has strong potential for application in resource-limited and high-burden settings.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fcimb.2025.1718614","type":"journal-article","created":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T06:43:34Z","timestamp":1766040214000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Validation and interpretation of machine-learning models for rapid identification of active tuberculosis infection using routine laboratory indicators"],"prefix":"10.3389","volume":"15","author":[{"given":"Zhan-Zhong","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quan","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Dong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xue-Di","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jia-Wei","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kang-Peng","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui-Jin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,12,18]]},"reference":[{"key":"B1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.5897\/AJB2013.13073","article-title":"Tuberculosis treatment raises total cholesterol level and restores high density lipoprotein cholesterol (HDLC) in patients with pulmonary tuberculosis","volume":"12","author":"Akpovi","year":"2013","journal-title":"Afr. J. Biotechnol."},{"key":"B2","doi-asserted-by":"publisher","first-page":"104335","DOI":"10.1016\/j.compbiomed.2021.104335","article-title":"Explaining machine learning based diagnosis of COVID-19 from routine blood tests with decision trees and criteria graphs","volume":"132","author":"Alves","year":"2021","journal-title":"Comput. Biol. Med."},{"key":"B3","doi-asserted-by":"publisher","first-page":"3318","DOI":"10.3390\/nu14163318","article-title":"Anemia is a strong predictor of wasting, disease severity, and progression, in clinical tuberculosis (TB)","volume":"14","author":"Ashenafi","year":"2022","journal-title":"Nutrients"},{"key":"B4","doi-asserted-by":"publisher","first-page":"41","DOI":"10.2174\/1874285801812010041","article-title":"Mycobacteriosis and tuberculosis: laboratory diagnosis","volume":"12","author":"Azadi","year":"2018","journal-title":"Open Microbiol. J."},{"key":"B5","doi-asserted-by":"publisher","first-page":"184","DOI":"10.4236\/jtr.2015.34025","article-title":"The strengths, weaknesses, opportunities and threats (SWOT) analysis of Mycobacterium tuberculosis: a systematic review","volume":"3","author":"Babalola","year":"2015","journal-title":"J. Tuberculosis Res."},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1016\/S2666-5247(22)00359-7","article-title":"WHO\u2019s global tuberculosis report 2022","volume":"4","author":"Bagcchi","year":"2023","journal-title":"Lancet Microbe"},{"key":"B7","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1186\/s12944-024-02063-7","article-title":"Association between biomarkers of inflammation and dyslipidemia in drug resistant tuberculosis in Uganda","volume":"23","author":"Baluku","year":"2024","journal-title":"Lipids Health Dis."},{"key":"B8","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.jctube.2016.05.005","article-title":"Diagnosis of active tuberculosis disease: From microscopy to molecular techniques","volume":"4","author":"Caulfield","year":"2016","journal-title":"J. Clin. Tuberculosis Other Mycobacterial Dis."},{"key":"B9","doi-asserted-by":"publisher","first-page":"S7","DOI":"10.1016\/j.ijid.2021.02.107","article-title":"Global Tuberculosis Report 2020\u2013Reflections on the Global TB burden, treatment and prevention efforts","volume":"113","author":"Chakaya","year":"2021","journal-title":"Int. J. Infect. Dis."},{"key":"B10","doi-asserted-by":"publisher","first-page":"226","DOI":"10.4103\/ijabmr.ijabmr_76_21","article-title":"Anemia and nutritional status in tuberculosis patients","volume":"11","author":"Chhabra","year":"2021","journal-title":"Int. J. Appl. Basic Med. Res."},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.3389\/fcvm.2021.696517","article-title":"Higher serum cholesterol levels are associated with reduced systemic inflammation and mortality during tuberculosis treatment independent of body mass index","volume":"8","author":"Chidambaram","year":"2021","journal-title":"Front. Cardiovasc. Med."},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.2196\/23390","article-title":"Establishing classifiers with clinical laboratory indicators to distinguish COVID-19 from community-acquired pneumonia: retrospective cohort study","volume":"23","author":"Dai","year":"2021","journal-title":"J. Med. Internet Res."},{"key":"B13","first-page":"442","article-title":"Sputum smear microscopy in tuberculosis: is it still relevant","volume":"137","author":"Desikan","year":"2013","journal-title":"Indian J. Med. Res."},{"key":"B14","first-page":"1","article-title":"A systematic review of rapid diagnostic tests for the detection of tuberculosis infection","volume":"11","author":"Dinnes","year":"2007","journal-title":"Health Technol. Assess. (Winchester England)"},{"key":"B15","doi-asserted-by":"publisher","first-page":"109067","DOI":"10.1016\/j.asoc.2022.109067","article-title":"A neural network boosting regression model based on XGBoost","volume":"125","author":"Dong","year":"2022","journal-title":"Appl. Soft Computing"},{"key":"B16","doi-asserted-by":"publisher","first-page":"199","DOI":"10.15406\/icpjl.2018.06.00188","article-title":"The utility and validity of immunological, inflammatory, and nutritional-based scores and indices in active Pulmonary Tuberculosis","volume":"6","author":"Fayed","year":"2018","journal-title":"Int. Clin. Pathol. J."},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.1003899","article-title":"Integrating tuberculosis and noncommunicable diseases care in low-and middle-income countries (LMICs): a systematic review","volume":"19","author":"Foo","year":"2022","journal-title":"PLoS Med."},{"key":"B18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1128\/cmr.00038-17","article-title":"Practical guidance for clinical microbiology laboratories: mycobacteria","volume":"31","author":"Forbes","year":"2018","journal-title":"Clin. Microbiol. Rev."},{"key":"B19","first-page":"1","article-title":"Beyond anemia: Red cell distribution width as a universal biomarker in contemporary medicine","volume":"2025","author":"Garg","year":"2025","journal-title":"J. Hematol. Allied Sci."},{"key":"B20","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1016\/j.clinbiochem.2014.08.022","article-title":"Red blood cell distribution width and neutrophil\/lymphocyte ratio are positively correlated with disease activity in primary Sj\u00f6gren\u2019s syndrome","volume":"47","author":"Hu","year":"2014","journal-title":"Clin. Biochem."},{"key":"B21","first-page":"13","article-title":"Haematological parameters altered in tuberculosis","volume":"11","author":"Iqbal","year":"2015","journal-title":"Pakistan J. Physiol."},{"key":"B22","article-title":"Xpert MTB\/RIF and Xpert MTB\/RIF Ultra assays for active tuberculosis and rifampicin resistance in children","author":"Kay","year":"2020","journal-title":"Cochrane Database Systematic Rev."},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0067956","article-title":"Blood neutrophil counts in HIV-infected patients with pulmonary tuberculosis: association with sputum mycobacterial load","volume":"8","author":"Kerkhoff","year":"2013","journal-title":"PLoS One"},{"key":"B24","first-page":"15","article-title":"Foundations of machine learning-based clinical prediction modeling: Part II\u2014Generalization and overfitting","volume-title":"Machine Learning in Clinical Neuroscience: Foundations and Applications","author":"Kernbach","year":"2021"},{"key":"B25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.heliyon.2022.e11185","article-title":"Predictive models for COVID-19 detection using routine blood tests and machine learning","volume":"8","author":"Kistenev","year":"2022","journal-title":"Heliyon"},{"key":"B26","doi-asserted-by":"publisher","first-page":"9213074","DOI":"10.1155\/2019\/9213074","article-title":"Mean platelet volume (MPV): new perspectives for an old marker in the course and prognosis of inflammatory conditions","volume":"2019","author":"Korniluk","year":"2019","journal-title":"Mediators Inflammation"},{"key":"B27","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1128\/CMR.00042-10","article-title":"HIV and tuberculosis: a deadly human syndemic","volume":"24","author":"Kwan","year":"2011","journal-title":"Clin. Microbiol. Rev."},{"key":"B28","doi-asserted-by":"publisher","first-page":"101845","DOI":"10.1016\/j.compenvurbsys.2022.101845","article-title":"Extracting spatial effects from machine learning model using local interpretation method: An example of SHAP and XGBoost","volume":"96","author":"Li","year":"2022","journal-title":"Computers Environ. Urban Syst."},{"key":"B29","doi-asserted-by":"publisher","first-page":"11485","DOI":"10.1038\/s41598-024-62521-1","article-title":"Using blood routine indicators to establish a machine learning model for predicting liver fibrosis in patients with Schistosoma japonicum","volume":"14","author":"Liu","year":"2024","journal-title":"Sci. Rep."},{"key":"B30","doi-asserted-by":"publisher","first-page":"648","DOI":"10.1016\/j.jinf.2021.12.046","article-title":"Machine learning based on routine laboratory indicators promoting the discrimination between active tuberculosis and latent tuberculosis infection","volume":"84","author":"Luo","year":"2022","journal-title":"J. Infection"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2021.658843","article-title":"Lymphocyte-related immunological indicators for stratifying mycobacterium tuberculosis infection","volume":"12","author":"Luo","year":"2021","journal-title":"Front. Immunol."},{"key":"B32","doi-asserted-by":"publisher","first-page":"113","DOI":"10.3390\/technologies12070113","article-title":"Probabilistic confusion matrix: A novel method for machine learning algorithm generalized performance analysis","volume":"12","author":"Markoulidakis","year":"2024","journal-title":"Technologies"},{"key":"B33","doi-asserted-by":"publisher","first-page":"1106","DOI":"10.1175\/825.1","article-title":"The ROC curve and the area under it as performance measures","volume":"19","author":"Marzban","year":"2004","journal-title":"Weather Forecasting"},{"key":"B34","first-page":"18","article-title":"Tuberculosis is a fatal disease among some developing countries of the world","volume":"3","author":"Mohajan","year":"2014","journal-title":"Am. J. Infect. Dis. Microbiol."},{"key":"B35","volume-title":"Global strategy for tuberculosis research and innovation","author":"Organization","year":"2020"},{"key":"B36","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1128\/CMR.00059-10","article-title":"Laboratory diagnosis of tuberculosis in resource-poor countries: challenges and opportunities","volume":"24","author":"Parsons","year":"2011","journal-title":"Clin. Microbiol. Rev."},{"key":"B37","doi-asserted-by":"publisher","first-page":"576","DOI":"10.1080\/09537104.2016.1246716","article-title":"Platelet index levels and cardiovascular mortality in incident peritoneal dialysis patients: a cohort study","volume":"28","author":"Peng","year":"2017","journal-title":"Platelets"},{"key":"B38","doi-asserted-by":"publisher","first-page":"16865","DOI":"10.1038\/s41598-023-44155-x","article-title":"The importance of interpreting machine learning models for blood glucose prediction in diabetes: an analysis using SHAP","volume":"13","author":"Prendin","year":"2023","journal-title":"Sci. Rep."},{"key":"B39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.clinbiochem.2022.02.011","article-title":"Applications of machine learning in routine laboratory medicine: Current state and future directions","volume":"103","author":"Rabbani","year":"2022","journal-title":"Clin. Biochem."},{"key":"B40","doi-asserted-by":"publisher","first-page":"64","DOI":"10.4046\/trd.2015.78.2.64","article-title":"Diagnosis of pulmonary tuberculosis: recent advances and diagnostic algorithms","volume":"78","author":"Ryu","year":"2015","journal-title":"Tuberculosis Respir. Dis."},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.3389\/fmede.2024.1369265","article-title":"Artificial intelligence in routine blood tests","volume":"2","author":"Santos-Silva","year":"2024","journal-title":"Front. Med. Eng."},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1101\/2024.09.27.24314525","article-title":"Burden of Latent Tuberculosis Infection among Healthcare Workers of Primary Health Centres and its Association with Clinical Laboratory Parameters","author":"Selvavinayagam","year":"2024","journal-title":"medRxiv"},{"key":"B43","first-page":"P1","article-title":"Application of machine learning for hematological diagnosis","author":"Silva","year":"2024","journal-title":"PhD Dissertation. Universidade do Minho"},{"key":"B44","doi-asserted-by":"crossref","first-page":"137382","DOI":"10.1016\/j.jhazmat.2025.137382","article-title":"Beyond XGBoost and SHAP: Unveiling true feature importance","volume":"2025","author":"Takefuji","year":"2025","journal-title":"J. Hazardous Materials"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.3389\/fcimb.2020.586054","article-title":"Prediction of sepsis in COVID-19 using laboratory indicators","volume":"10","author":"Tang","year":"2021","journal-title":"Front. Cell. infection Microbiol."},{"key":"B46","doi-asserted-by":"publisher","first-page":"328","DOI":"10.12688\/f1000research.161124.1","article-title":"Platelet-based biomarkers: A new frontier in inflammation monitoring for respiratory infections","volume":"14","author":"Verma","year":"2025","journal-title":"F1000Research"},{"key":"B47","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40001-025-02442-5","article-title":"Predicting diabetic retinopathy based on routine laboratory tests by machine learning algorithms","volume":"30","author":"Wan","year":"2025","journal-title":"Eur. J. Med. Res."},{"key":"B48","doi-asserted-by":"publisher","first-page":"947","DOI":"10.1093\/cid\/ciz581","article-title":"5-year follow-up of active tuberculosis development from latent infection in rural China","volume":"70","author":"Xin","year":"2020","journal-title":"Clin. Infect. Dis."},{"key":"B49","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1007\/s12094-024-03564-8","article-title":"Enhancing the diagnostic accuracy of colorectal cancer through the integration of serum tumor markers and hematological indicators with machine learning algorithms","volume":"27","author":"Xu","year":"2025","journal-title":"Clin. Trans. Oncol."},{"key":"B50","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1007\/s41664-018-0068-2","article-title":"On splitting training and validation set: a comparative study of cross-validation, bootstrap and systematic sampling for estimating the generalization performance of supervised learning","volume":"2","author":"Xu","year":"2018","journal-title":"J. Anal. testing"},{"key":"B51","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2020.eval4nlp-1.9","article-title":"Probabilistic extension of precision, recall, and f1 score for more thorough evaluation of classification models","author":"Yacouby","year":"2020"},{"key":"B52","doi-asserted-by":"crossref","DOI":"10.1109\/IACC.2016.25","article-title":"Analysis of k-fold cross-validation over hold-out validation on colossal datasets for quality classification","volume-title":"Proceedings of the 2016 IEEE 6th International conference on advanced computing (IACC)","author":"Yadav","year":"2016"},{"key":"B53","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1186\/s12935-024-03439-6","article-title":"Machine learning models for predicting of PD-1 treatment efficacy in Pan-cancer patients based on routine hematologic and biochemical parameters","volume":"24","author":"Yang","year":"2024","journal-title":"Cancer Cell Int."},{"key":"B54","doi-asserted-by":"publisher","first-page":"805","DOI":"10.3390\/life13030805","article-title":"Infectious microorganisms seen as etiologic agents in Parkinson\u2019s disease","volume":"13","author":"Zorina","year":"2023","journal-title":"Life"}],"container-title":["Frontiers in Cellular and Infection Microbiology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcimb.2025.1718614\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T06:43:38Z","timestamp":1766040218000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcimb.2025.1718614\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,18]]},"references-count":54,"alternative-id":["10.3389\/fcimb.2025.1718614"],"URL":"https:\/\/doi.org\/10.3389\/fcimb.2025.1718614","relation":{},"ISSN":["2235-2988"],"issn-type":[{"value":"2235-2988","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,18]]},"article-number":"1718614"}}