{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T05:36:47Z","timestamp":1776836207545,"version":"3.51.2"},"reference-count":20,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T00:00:00Z","timestamp":1776816000000},"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>Background<\/jats:title>\n                    <jats:p>Tuberculosis (TB) remains a global health challenge, with heterogeneous treatment outcomes despite standardized protocols. Traditional statistical models struggle with high-dimensional clinical data, necessitating advanced machine learning (ML) approaches.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To analyze clinical data from 467 pulmonary TB patients and construct a predictive model using multiple ML algorithms.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      A prospective cohort of 467 patients (218 intervention, 249 control) was enrolled from Xi'an Chest Hospital. Medical ratio features (ALT\/AST, CD4\/CD8) and polynomial interaction terms (e.g., RBC \u00d7 ALT) were constructed. Recursive feature elimination (RFE) selected 60 predictive factors from an expanded 80-dimensional feature space. Fourteen ML algorithms were systematically compared, with hyperparameters optimized via grid search. Performance was assessed using five-fold cross-validation\n                      <jats:italic>R<\/jats:italic>\n                      <jats:sup>2<\/jats:sup>\n                      , RMSE, and MAE.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      LightGBM achieved the highest initial predictive performance (\n                      <jats:italic>R<\/jats:italic>\n                      <jats:sup>2<\/jats:sup>\n                      = 0.1829, RMSE = 139.23). Following hyperparameter optimization, Random Forest attained a marginally improved\n                      <jats:italic>R<\/jats:italic>\n                      <jats:sup>2<\/jats:sup>\n                      of 0.1867 with comparable error metrics and enhanced clinical interpretability, serving as the final reference model. Feature engineering expanded the feature space from 33 to 80, with 60 optimal features retained.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>\n                      The optimized Random Forest model (\n                      <jats:italic>R<\/jats:italic>\n                      <jats:sup>2<\/jats:sup>\n                      = 0.1867) demonstrates moderate accuracy and clinical interpretability, supporting its potential as a decision-support tool for TB treatment optimization. Pharmacist-led therapeutic drug monitoring (TDM) further enhances individualized therapy. Future work requires multi-center validation and radiomics integration to improve predictive performance in severe cases.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Clinical trial registration<\/jats:title>\n                    <jats:p>\n                      Registration Platform: Chinese Clinical Trial Registry [\n                      <jats:ext-link>https:\/\/www.chictr.org.cn\/<\/jats:ext-link>\n                      ], identifier [ChiCTR2300074328].\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1785419","type":"journal-article","created":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T04:37:38Z","timestamp":1776832658000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Clinical data analysis research on tuberculosis based on machine learning"],"prefix":"10.3389","volume":"13","author":[{"given":"Rongrong","family":"Kang","sequence":"first","affiliation":[{"name":"Department of Pharmacy, Xi'an Chest Hospital","place":["Xi'an, Shaanxi, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huanqing","family":"Liu","sequence":"additional","affiliation":[{"name":"Information Management Office, Northwestern Polytechnical University","place":["Xi'an, Shaanxi, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qian","family":"Lei","sequence":"additional","affiliation":[{"name":"Department of Pharmacy, Xi'an Chest Hospital","place":["Xi'an, Shaanxi, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tingting","family":"Li","sequence":"additional","affiliation":[{"name":"Drug Clinical Trial Institution Office, Xi'an Chest Hospital","place":["Xi'an, Shaanxi, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,4,22]]},"reference":[{"key":"B1","volume-title":"Global Tuberculosis Report 2023","year":"2023"},{"key":"B2","doi-asserted-by":"publisher","first-page":"2057","DOI":"10.1016\/S0140-6736(13)62639-2","article-title":"Tuberculosis prevalence in China, 1990\u20132010; a longitudinal analysis of national survey data","volume":"383","author":"Wang","year":"2014","journal-title":"Lancet"},{"key":"B3","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1097\/MCP.0000000000000866","article-title":"Drug-resistant tuberculosis: advances in diagnosis and management","volume":"28","author":"G\u00fcnther","year":"2022","journal-title":"Curr Opin Pulm Med"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1216","DOI":"10.1056\/NEJMp1606181","article-title":"Predicting the future\u2014big data, machine learning, and clinical medicine","volume":"375","author":"Obermeyer","year":"2016","journal-title":"N Engl J Med"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1920","DOI":"10.1161\/CIRCULATIONAHA.115.001593","article-title":"Machine learning in medicine","volume":"132","author":"Deo","year":"2015","journal-title":"Circulation"},{"key":"B6","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1186\/s13148-020-00842-4","article-title":"Machine learning and clinical epigenetics: a review of challenges for diagnosis and classification","volume":"12","author":"Rauschert","year":"2020","journal-title":"Clin Epigenetics"},{"key":"B7","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1038\/s41591-021-01614-0","article-title":"AI in health and medicine","volume":"28","author":"Rajpurkar","year":"2022","journal-title":"Nat Med"},{"key":"B8","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1038\/s41591-019-0727-5","article-title":"Axes of a revolution: challenges and promises of big data in healthcare","volume":"26","author":"Shilo","year":"2020","journal-title":"Nat Med"},{"key":"B9","doi-asserted-by":"publisher","first-page":"28907","DOI":"10.1007\/s11071-025-11620-3","article-title":"AI-driven analysis of buoyancy-convective flow of ternary-hybrid nanofluid in a porous medium over stretching cylinder","volume":"113","author":"Qureshi","year":"2025","journal-title":"Nonlinear Dyn"},{"key":"B10","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1007\/s41939-025-01110-9","article-title":"Artificial neural network simulation modeling of heat transfer effects on a magnetohydrodynamic Casson liquid film flow over a stretching surface","volume":"9","author":"Qureshi","year":"2026","journal-title":"Multiscale Multidiscip Model Exp Des"},{"key":"B11","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 Infect"},{"key":"B12","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1186\/s12916-019-1426-2","article-title":"Key challenges for delivering clinical impact with artificial intelligence","volume":"17","author":"Kelly","year":"2019","journal-title":"BMC Med"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1171985","DOI":"10.3389\/fphar.2023.1171985","article-title":"A randomized controlled trial to evaluate the impact of pharmacist-led clinical interventions on the health-related quality of life among TB patients","volume":"14","author":"Khan","year":"2023","journal-title":"Front Pharmacol"},{"key":"B14","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1007\/s12072-021-10144-3","article-title":"Drug-induced liver injury: Asia Pacific Association of Study of Liver consensus guidelines","volume":"15","author":"Devarbhavi","year":"2021","journal-title":"Hepatol Int"},{"key":"B15","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1186\/s12916-018-1033-7","article-title":"Liver toxicity associated with tuberculosis chemotherapy in the REMoxTB study","volume":"16","author":"Tweed","year":"2018","journal-title":"BMC Med"},{"key":"B16","doi-asserted-by":"publisher","first-page":"e1997","DOI":"10.1002\/hsr2.1997","article-title":"Active tuberculosis incidence among treatment failure experienced patients in North Wollow zone: a multicenter historical cohort","volume":"7","author":"Bizuneh","year":"2024","journal-title":"Health Sci Rep"},{"key":"B17","doi-asserted-by":"publisher","first-page":"171","DOI":"10.3389\/fmed.2017.00171","article-title":"Host-directed therapeutic strategies for tuberculosis","volume":"4","author":"Kolloli","year":"2017","journal-title":"Front Med (Lausanne)"},{"key":"B18","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1186\/s12199-020-00931-z","article-title":"Anemia as a risk factor for tuberculosis: a systematic review and meta-analysis","volume":"26","author":"Gelaw","year":"2021","journal-title":"Environ Health Prev Med"},{"key":"B19","doi-asserted-by":"publisher","first-page":"102453","DOI":"10.1016\/j.jiac.2024.06.016","article-title":"Effectiveness and safety of the simulation-based first-dose design of voriconazole","volume":"31","author":"Umemura","year":"2025","journal-title":"J Infect Chemother"},{"key":"B20","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1007\/s11096-024-01822-x","article-title":"Model-informed precision dosing of vancomycin in clinical practice: an intervention development study","volume":"47","author":"Swartling","year":"2025","journal-title":"Int J Clin Pharm"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1785419\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T04:37:38Z","timestamp":1776832658000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1785419\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,22]]},"references-count":20,"alternative-id":["10.3389\/fmed.2026.1785419"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1785419","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,22]]},"article-number":"1785419"}}