{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T16:06:41Z","timestamp":1789142801660,"version":"build-2803163510"},"reference-count":51,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T00:00:00Z","timestamp":1786492800000},"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. Pharmacol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Tuberculous meningitis (TBM) is a severe central nervous system infection with high disability and mortality rates. However, during TBM treatment, anti-tuberculosis drug-induced liver injury (ATB-DILI) often precipitates treatment interruption and contributes to poor clinical outcomes. This study aims to develop an automatic machine learning (AutoML) model for predicting the risk of ATB-DILI in TBM patients.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A retrospective cohort study was conducted in adult TBM patients. After feature selection via least absolute shrinkage and selection operator (LASSO) regression, AutoML was employed to construct predictive models. The bootstrap resampling method was used for internal validation. Furthermore, feature importance, partial dependence plots, and SHapley Additive exPlanations (SHAP) analysis were utilized for model interpretation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>A total of 253 TBM patients were included in this study, of whom 54 (21.34%) developed ATB-DILI. LASSO regression analysis identified four characteristic factors, including cerebrospinal fluid (CSF) chloride, blood platelet, hypertension, and total bilirubin. Among the candidate models generated by AutoML, the optimal gradient boosting machine (GBM) model demonstrated superior performance. It achieved an optimism-corrected area under the receiver operating characteristic curve (AUC) of 0.828 (95% CI: 0.794\u20130.861) and an optimism-corrected area under the precision-recall curve (PR-AUC) of 0.711 (95% CI: 0.628\u20130.782). In addition, interpretability analysis revealed that CSF chloride was the most important variable for the optimal GBM model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The ATB-DILI prediction model, developed using AutoML technology, demonstrated high predictive ability and interpretability. It can assist clinicians in identifying TBM patients at risk of ATB-DILI, thereby optimizing patient management and facilitating the formulation of personalized medication regimens.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fphar.2026.1816387","type":"journal-article","created":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T04:41:49Z","timestamp":1786509709000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Automated machine learning model to predict anti-tuberculosis drug-induced liver injury in patients with tuberculous meningitis"],"prefix":"10.3389","volume":"17","author":[{"given":"Pengyu","family":"Li","sequence":"first","affiliation":[{"name":"Department of Pharmacy, The Affiliated Changsha Central Hospital, Hengyang Medical School, University of South China","place":["Changsha, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Pharmacy, Changsha Medical University","place":["Changsha, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lanyan","family":"Xi","sequence":"additional","affiliation":[{"name":"Department of Pharmacy, The Affiliated Changsha Central Hospital, Hengyang Medical School, University of South China","place":["Changsha, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ling","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Pharmacy, The Affiliated Changsha Central Hospital, Hengyang Medical School, University of South China","place":["Changsha, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Zeng","sequence":"additional","affiliation":[{"name":"Department of Pharmacy, The Affiliated Changsha Central Hospital, Hengyang Medical School, University of South China","place":["Changsha, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanmei","family":"Mao","sequence":"additional","affiliation":[{"name":"Department of Pharmacy, The Affiliated Changsha Central Hospital, Hengyang Medical School, University of South China","place":["Changsha, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pan","family":"Yan","sequence":"additional","affiliation":[{"name":"Department of Pharmacy, The Affiliated Changsha Central Hospital, Hengyang Medical School, University of South China","place":["Changsha, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,12]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"101623","DOI":"10.1016\/j.nmni.2025.101623","article-title":"Anti-TB treatment outcomes in TB meningitis: a systematic review and meta-analysis","volume":"67","author":"Afazel","year":"2025","journal-title":"New Microbes New Infect."},{"key":"B2","doi-asserted-by":"publisher","first-page":"100792","DOI":"10.1016\/j.mlwa.2025.100792","article-title":"Machine learning approaches to traffic accident severity prediction: addressing class imbalance","volume":"22","author":"Amiri","year":"2025","journal-title":"Mach. Learn. Appl."},{"key":"B3","first-page":"1","volume-title":"Deep Learning with H2O","author":"Candel","year":"2016"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1069","DOI":"10.3760\/cma.j.cn112147-20240614-00338","article-title":"Guidelines for diagnosis and management of drug-induced liver injury caused by anti-tuberculosis drugs (2024 version)","volume":"47","year":"2024","journal-title":"Chin. J. Tuberc. Respir. Dis."},{"key":"B5","doi-asserted-by":"publisher","first-page":"164","DOI":"10.12688\/wellcomeopenres.15506.2","article-title":"Recent developments in tuberculous meningitis pathogenesis and diagnostics","volume":"4","author":"Cresswell","year":"2021","journal-title":"Wellcome Open Research"},{"key":"B6","doi-asserted-by":"publisher","first-page":"e96","DOI":"10.1016\/s1473-3099(25)00364-0","article-title":"A clinical practice guideline for tuberculous meningitis","volume":"26","author":"Donovan","year":"2025","journal-title":"Lancet Infect. Dis."},{"key":"B7","doi-asserted-by":"publisher","first-page":"790343","DOI":"10.3389\/fonc.2022.790343","article-title":"A risk scoring system utilizing machine learning methods for hepatotoxicity prediction one year after the initiation of tyrosine kinase inhibitors","volume":"12","author":"Han","year":"2022","journal-title":"Front. Oncol."},{"key":"B8","doi-asserted-by":"publisher","first-page":"450","DOI":"10.1016\/s1474-4422(21)00435-x","article-title":"Tuberculous meningitis: progress and remaining questions","volume":"21","author":"Huynh","year":"2022","journal-title":"Lancet Neurol."},{"key":"B9","doi-asserted-by":"publisher","first-page":"e23458","DOI":"10.2196\/23458","article-title":"Using automated machine learning to predict the mortality of patients with COVID-19: prediction model development study","volume":"23","author":"Ikemura","year":"2021","journal-title":"J. Med. Internet Res."},{"key":"B10","doi-asserted-by":"publisher","first-page":"1153815","DOI":"10.3389\/fphar.2023.1153815","article-title":"A nomogram model to predict the risk of drug-induced liver injury in patients receiving anti-tuberculosis treatment","volume":"14","author":"Ji","year":"2023","journal-title":"Front. Pharmacol."},{"key":"B11","doi-asserted-by":"publisher","first-page":"1565","DOI":"10.1111\/liv.14896","article-title":"Incidence and risk factors of anti-tuberculosis drug induced liver injury (DILI): large cohort study involving 4652 Chinese adult tuberculosis patients","volume":"41","author":"Jiang","year":"2021","journal-title":"Liver Int."},{"key":"B12","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1007\/s12031-019-01304-0","article-title":"Role of oxidative stress in tuberculous meningitis: a clinico-radiological correlation","volume":"68","author":"Kalita","year":"2019","journal-title":"J. Mol. Neurosci."},{"key":"B13","doi-asserted-by":"publisher","first-page":"3300","DOI":"10.3390\/molecules26113300","article-title":"Machine learning approaches to predict hepatotoxicity risk in patients receiving nilotinib","volume":"26","author":"Kim","year":"2021","journal-title":"Molecules"},{"key":"B14","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1093\/trstmh\/try006","article-title":"Is drug-induced hepatitis related to the severity of tuberculous meningitis?","volume":"111","author":"Kumar","year":"2017","journal-title":"Trans. R. Soc. Trop. Med. Hyg."},{"key":"B15","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1182\/asheducation-2016.1.251","article-title":"Platelets in liver and renal disease","volume":"2016","author":"Lambert","year":"2016","journal-title":"Hematol. Am. Soc. Hematol. Educ. Program"},{"key":"B16","article-title":"H2o automl: scalable automatic machine learning","volume-title":"Proceedings of the AutoML Workshop at ICML","author":"Ledell","year":"2020"},{"key":"B17","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1111\/1751-2980.13205","article-title":"Mapping the incidence of drug-induced liver injury: a systematic review and meta-analysis","volume":"24","author":"Li","year":"2023","journal-title":"J. Dig. Dis."},{"key":"B18","doi-asserted-by":"publisher","first-page":"2920","DOI":"10.3390\/rs15112920","article-title":"Uncertainty of partial dependence relationship between climate and vegetation growth calculated by machine learning models","volume":"15","author":"Liang","year":"2023","journal-title":"Remote Sens."},{"key":"B19","doi-asserted-by":"publisher","first-page":"ofad422","DOI":"10.1093\/ofid\/ofad422","article-title":"Metabolic disorders are associated with drug-induced liver injury during antituberculosis treatment: a multicenter prospective observational cohort study in Korea","volume":"10","author":"Lim","year":"2023","journal-title":"Open Forum Infect. Dis."},{"key":"B20","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1055\/s-0037-1604091","article-title":"Platelets as modulators of liver diseases","volume":"44","author":"Lisman","year":"2018","journal-title":"Semin. Thromb. Hemost."},{"key":"B21","doi-asserted-by":"publisher","first-page":"1190987","DOI":"10.3389\/fonc.2023.1190987","article-title":"Automated machine learning to predict the difficulty for endoscopic resection of gastric gastrointestinal stromal tumor","volume":"13","author":"Liu","year":"2023","journal-title":"Front. Oncol."},{"key":"B22","doi-asserted-by":"publisher","first-page":"1406454","DOI":"10.3389\/fphar.2024.1406454","article-title":"Clinical risk factors for moderate and severe antituberculosis drug-induced liver injury","volume":"15","author":"Liu","year":"2024","journal-title":"Front. Pharmacol."},{"key":"B23","doi-asserted-by":"publisher","first-page":"1101","DOI":"10.1093\/infdis\/jiaf181","article-title":"Tuberculous meningitis across the lifespan","volume":"231","author":"Lourens","year":"2025","journal-title":"J. Infect. Dis."},{"key":"B24","doi-asserted-by":"publisher","first-page":"3049","DOI":"10.1007\/s00204-024-03803-5","article-title":"Development and validation of an automatic machine learning model to predict abnormal increase of transaminase in valproic acid-treated epilepsy","volume":"98","author":"Ma","year":"2024","journal-title":"Arch. Toxicol."},{"key":"B25","doi-asserted-by":"publisher","first-page":"116825","DOI":"10.1016\/j.jns.2020.116825","article-title":"Oxidative stress and ER stress may contribute to drug-induced hepatitis in tuberculous meningitis","volume":"414","author":"Misra","year":"2020","journal-title":"J. Neurol. Sci."},{"key":"B26","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1093\/trstmh\/traa144","article-title":"Standard versus sequential anti-tubercular treatment in patients with tuberculous meningitis: a randomized controlled trial","volume":"115","author":"Misra","year":"2021","journal-title":"Trans. R. Soc. Trop. Med. Hyg."},{"key":"B27","doi-asserted-by":"publisher","first-page":"1400","DOI":"10.1186\/s12879-025-11796-4","article-title":"Incidence and associated risk factors of anti-tuberculosis drug induced liver injury among TB patients","volume":"25","author":"Nyangwara","year":"2025","journal-title":"BMC Infect. Dis."},{"key":"B28","doi-asserted-by":"publisher","first-page":"642","DOI":"10.21037\/atm-20-5144","article-title":"Prevalence and clinical characteristics of antibiotics associated drug induced liver injury","volume":"9","author":"Park","year":"2021","journal-title":"Ann. Transl. Med."},{"key":"B29","doi-asserted-by":"publisher","first-page":"1321923","DOI":"10.3389\/fneur.2024.1321923","article-title":"Deep learning and machine learning predictive models for neurological function after interventional embolization of intracranial aneurysms","volume":"15","author":"Peng","year":"2024","journal-title":"Front. Neurology"},{"key":"B30","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1136\/archdischild-2020-321426","article-title":"Pharmacokinetics and safety\/tolerability of isoniazid, rifampicin and pyrazinamide in children and adolescents treated for tuberculous meningitis","volume":"107","author":"Ruslami","year":"2022","journal-title":"Arch. Dis. Child."},{"key":"B31","doi-asserted-by":"publisher","first-page":"35645","DOI":"10.1109\/access.2025.3539746","article-title":"Optimized breast cancer classification using PCA-LASSO feature selection and ensemble learning strategies with optuna optimization","volume":"13","author":"Sahu","year":"2025","journal-title":"Ieee Access"},{"key":"B32","doi-asserted-by":"publisher","first-page":"101875","DOI":"10.5409\/wjcp.v14.i2.101875","article-title":"Understanding antituberculosis drug-induced hepatotoxicity: risk factors and effective management strategies in the pediatric population","volume":"14","author":"Semwal","year":"2025","journal-title":"World J. Clin. Pediatr."},{"key":"B33","doi-asserted-by":"publisher","first-page":"1290746","DOI":"10.3389\/fmicb.2023.1290746","article-title":"The diagnosis of tuberculous meningitis: advancements in new technologies and machine learning algorithms","volume":"14","author":"Shi","year":"2023","journal-title":"Front. Microbiol."},{"key":"B34","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1186\/s12911-025-02955-3","article-title":"Comparing conventional and Bayesian workflows for clinical outcome prediction modelling with an exemplar cohort study of severe COVID-19 infection incorporating clinical biomarker test results","volume":"25","author":"Sullivan","year":"2025","journal-title":"BMC Med. Inf. Decis. Mak."},{"key":"B35","doi-asserted-by":"publisher","first-page":"100080","DOI":"10.1016\/j.prmedi.2026.100080","article-title":"Challenges in utilizing the FAERS database for adverse drug reaction data mining: a critical analysis","volume":"3","author":"Sun","year":"2026","journal-title":"Precis. Medicat."},{"key":"B36","doi-asserted-by":"publisher","first-page":"390","DOI":"10.3390\/antiox10030390","article-title":"Oxidative stress in drug-induced liver injury (DILI): from mechanisms to biomarkers for use in clinical practice","volume":"10","author":"Villanueva-Paz","year":"2021","journal-title":"Antioxidants (Basel)"},{"key":"B37","doi-asserted-by":"publisher","first-page":"1044808","DOI":"10.3389\/fphar.2022.1044808","article-title":"Plasma metabolomic and lipidomic alterations associated with anti-tuberculosis drug-induced liver injury","volume":"13","author":"Wang","year":"2022","journal-title":"Front. Pharmacol."},{"key":"B38","doi-asserted-by":"publisher","first-page":"1384931","DOI":"10.3389\/fonc.2024.1384931","article-title":"Construction of a predictive model for postoperative hospitalization time in colorectal cancer patients based on interpretable machine learning algorithm: a prospective preliminary study","volume":"14","author":"Wen","year":"2024","journal-title":"Front. Oncol."},{"key":"B39","volume-title":"Defeating Meningitis by 2030: A Global Road Map","year":"2021"},{"key":"B40","doi-asserted-by":"publisher","first-page":"1910","DOI":"10.1186\/s12903-025-07245-y","article-title":"Predicting plaque-gingivitis risk in schoolchildren using an interpretable machine learning model: a cross-sectional study","volume":"25","author":"Wu","year":"2025","journal-title":"BMC Oral Health"},{"key":"B41","doi-asserted-by":"publisher","first-page":"648","DOI":"10.1016\/j.apsb.2018.12.003","article-title":"Guidance for the clinical evaluation of traditional Chinese medicine-induced liver injuryIssued by China food and drug administration","volume":"9","author":"Xiao","year":"2019","journal-title":"Acta Pharm. Sin. B"},{"key":"B42","doi-asserted-by":"publisher","first-page":"3052","DOI":"10.6039\/j.issn.1001-0408.2024.24.15","article-title":"Meta-analysis of the incidence and risk factors of anti-tuberculosis drug-induced liver injury","volume":"35","author":"Xie","year":"2024","journal-title":"China Pharm."},{"key":"B43","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1136\/ejhpharm-2020-002433","article-title":"Incidence and associated risk factors of antituberculosis drug-induced hepatotoxicity among hospitalised patients in wuhan, China","volume":"29","author":"Xu","year":"2022","journal-title":"Eur. J. Hosp. Pharm."},{"key":"B44","doi-asserted-by":"publisher","first-page":"106002","DOI":"10.1016\/j.rineng.2025.106002","article-title":"Predicting adverse drug reactions in oncology: a critical review of machine learning approaches and future directions","volume":"27","author":"Yahya","year":"2025","journal-title":"Results Eng."},{"key":"B45","doi-asserted-by":"publisher","first-page":"100011","DOI":"10.1016\/j.aichem.2023.100011","article-title":"Application of artificial intelligence and machine learning in early detection of adverse drug reactions (ADRs) and drug-induced toxicity","volume":"1","author":"Yang","year":"2023","journal-title":"Artif. Intell. Chem."},{"key":"B46","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1111\/tmi.13849","article-title":"Adenosine deaminase from the cerebrospinal fluid for the diagnosis of tuberculous meningitis: a meta-analysis","volume":"28","author":"Ye","year":"2023","journal-title":"Trop. Med. Int. Health"},{"key":"B47","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1186\/s12911-024-02734-6","article-title":"Predictive modeling of preoperative acute heart failure in older adults with hypertension: a dual perspective of SHAP values and interaction analysis","volume":"24","author":"Yu","year":"2024","journal-title":"BMC Med. Inf. Decis. Mak."},{"key":"B48","doi-asserted-by":"publisher","first-page":"239","DOI":"10.2147\/dddt.s495555","article-title":"Risk prediction of liver injury in pediatric tuberculosis treatment: development of an automated machine learning model","volume":"19","author":"Zeng","year":"2025","journal-title":"Drug Des. Devel Ther."},{"key":"B49","doi-asserted-by":"publisher","first-page":"1114","DOI":"10.21037\/atm-22-4551","article-title":"Combined electronic medical records and gene polymorphism characteristics to establish an anti-tuberculosis drug-induced hepatic injury (ATDH) prediction model and evaluate the prediction value","volume":"10","author":"Zhang","year":"2022","journal-title":"Ann. Transl. Med."},{"key":"B50","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1186\/s12911-024-02414-5","article-title":"Automated machine learning for early prediction of acute kidney injury in acute pancreatitis","volume":"24","author":"Zhang","year":"2024","journal-title":"BMC Med. Inf. Decis. Mak."},{"key":"B51","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1002\/dc.23284","article-title":"Prediction of cerebrospinal fluid parameters for tuberculous meningitis","volume":"43","author":"Zou","year":"2015","journal-title":"Diagn Cytopathol."}],"container-title":["Frontiers in Pharmacology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphar.2026.1816387\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T04:42:00Z","timestamp":1786509720000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphar.2026.1816387\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,12]]},"references-count":51,"alternative-id":["10.3389\/fphar.2026.1816387"],"URL":"https:\/\/doi.org\/10.3389\/fphar.2026.1816387","relation":{},"ISSN":["1663-9812"],"issn-type":[{"value":"1663-9812","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,12]]},"article-number":"1816387"}}