{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T21:20:50Z","timestamp":1792790450250,"version":"4.5.0"},"reference-count":55,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T00:00:00Z","timestamp":1747699200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0"}],"funder":[{"name":"Scientific Research Fund of Zhejiang Provincial Education Department, China","award":["Y202045308"],"award-info":[{"award-number":["Y202045308"]}]},{"name":"Zhejiang Province Medical and Health Science and Technology Project, China","award":["2022KY877"],"award-info":[{"award-number":["2022KY877"]}]},{"name":"Jiashan Bureau of Science and Technology, China","award":["2023A60"],"award-info":[{"award-number":["2023A60"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Tuberculous pleural effusion (TPE) is a prevalent tuberculosis complication, with diagnosis presenting considerable challenges. Timely and precise identification of TPE is vital for effective patient management and prognosis, yet existing diagnostic methods tend to be invasive, lengthy, and often lack sufficient accuracy. This study seeks to design and validate an interpretable machine learning model based on routine laboratory data to enable noninvasive and rapid TPE diagnosis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      A multicenter prospective study was conducted across China between January 2021 and September 2024, enrolling 963 patients. The derivation cohort, comprising 763 patients, was employed for model training and internal validation, while 200 patients formed the external validation cohort. The model was built upon 18 routine laboratory parameters, including pleural fluid and serum biomarkers, with multiple machine learning (ML) algorithms evaluated. Light gradient boosting machine (LGBM) emerged as the top-performing model. Shapley Additive exPlanations (SHAP) analysis assessed feature importance and interpretability. Model performance was evaluated\n                      <jats:italic>via<\/jats:italic>\n                      area under the curve (AUC) and accuracy metrics.\n                      <jats:bold\/>\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Of the 10 ML models compared, LGBM demonstrated superior performance. Feature importance analysis identified 11 key variables, leading to constructing a highly interpretable LGBM model. The model achieved an AUC of 0.9454 in internal validation and 0.9262 in external validation, showcasing strong robustness and generalizability. SHAP analysis enhanced interpretability by highlighting each feature\u2019s contribution to prediction outcomes. This model has since been integrated into clinical practice for noninvasive, rapid TPE diagnosis. During external validation, the model achieved a sensitivity of 0.8600, specificity of 0.9056, positive predictive value of 0.8698, and negative predictive value of 0.8686, underscoring its accuracy across diverse patient cohorts.\n                      <jats:bold\/>\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Interpretation<\/jats:title>\n                    <jats:p>\n                      This interpretable machine learning model offers a noninvasive, accurate solution for early TPE diagnosis, significantly reducing reliance on invasive procedures. The integration of SHAP ensures the model\u2019s clinical interpretability, mitigating concerns surrounding the \u201cblack-box\u201d nature of many machine learning approaches.\n                      <jats:bold\/>\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This interpretable LGBM-based model provides a reliable, noninvasive tool for TPE diagnosis. It supports clinical decision-making with real-time risk assessment and promises broader applicability through future integration into clinical information systems.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.7717\/peerj.19411","type":"journal-article","created":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T04:49:02Z","timestamp":1747716542000},"page":"e19411","source":"Crossref","is-referenced-by-count":4,"title":["Interpretable noninvasive diagnosis of tuberculous pleural effusion using LGBM and SHAP: development and clinical application of a machine learning model"],"prefix":"10.7717","volume":"13","author":[{"given":"Bihua","family":"Yao","sequence":"first","affiliation":[{"name":"Laboratory Medicine Center, Department of Clinical Laboratory, The First People\u2019s Hospital of Jiashan Affiliated to Jiaxing University, Jiaxing, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5382-973X","authenticated-orcid":true,"given":"Xingyu","family":"Yu","sequence":"additional","affiliation":[{"name":"Zhejiang Sci-Tech University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liannv","family":"Qiu","sequence":"additional","affiliation":[{"name":"Department of Laboratory Medicine, Zhejiang Provincial People\u2019s Hospital, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Er-min","family":"Gu","sequence":"additional","affiliation":[{"name":"Department of Science and Education, The First People\u2019s Hospital of Jiashan affiliated to Jiaxing University, Jiaxing, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siyu","family":"Mao","sequence":"additional","affiliation":[{"name":"Laboratory Medicine Center, Department of Clinical Laboratory, The First People\u2019s Hospital of Jiashan Affiliated to Jiaxing University, Jiaxing, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Laboratory Medicine, Zhejiang Provincial People\u2019s Hospital, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jijun","family":"Tong","sequence":"additional","affiliation":[{"name":"Zhejiang Sci-Tech University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianguo","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Laboratory Medicine, Hangzhou TCM Hospital Affiliated to Zhejiang Chinese Medical University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"4443","published-online":{"date-parts":[[2025,5,20]]},"reference":[{"issue":"9","key":"10.7717\/peerj.19411\/ref-1","doi-asserted-by":"publisher","first-page":"1773","DOI":"10.1038\/s41591-022-01981-2","article-title":"Multimodal biomedical AI","volume":"28","author":"Acosta","year":"2022","journal-title":"Nature Medicine"},{"issue":"3","key":"10.7717\/peerj.19411\/ref-2","doi-asserted-by":"publisher","first-page":"e0213728","DOI":"10.1371\/journal.pone.0213728","article-title":"Adenosine deaminase for diagnosis of tuberculous pleural effusion: a systematic review and meta-analysis","volume":"14","author":"Aggarwal","year":"2019","journal-title":"PLOS ONE"},{"key":"10.7717\/peerj.19411\/ref-3","doi-asserted-by":"publisher","first-page":"132095\u2013132105","DOI":"10.1109\/ACCESS.2020.3010099","article-title":"A k-nearest neighbours based ensemble via optimal model selection for regression","volume":"8","author":"Ali","year":"2020","journal-title":"IEEE Access"},{"issue":"1","key":"10.7717\/peerj.19411\/ref-4","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1007\/s10238-024-01377-1","article-title":"The diagnostic value of multimodal imaging based on MR combined with ultrasound in benign and malignant breast diseases","volume":"24","author":"Bai","year":"2024","journal-title":"Clinical and Experimental Medicine"},{"key":"10.7717\/peerj.19411\/ref-5","doi-asserted-by":"crossref","first-page":"149","DOI":"10.4049\/jimmunol.145.1.149","article-title":"Local production of tumor necrosis factor and IFN-gamma in tuberculous pleuritis","volume":"145","author":"Barnes","year":"1990","journal-title":"The Journal of Immunology"},{"key":"10.7717\/peerj.19411\/ref-6","doi-asserted-by":"publisher","first-page":"3319","DOI":"10.1109\/CVPR.2017.354","article-title":"Network dissection: quantifying interpretability of deep visual representations","author":"Bau","year":"2017"},{"issue":"4","key":"10.7717\/peerj.19411\/ref-7","doi-asserted-by":"publisher","first-page":"900","DOI":"10.1158\/2159-8290.Cd-21-0090","article-title":"Artificial intelligence in cancer research and precision medicine","volume":"11","author":"Bhinder","year":"2021","journal-title":"Cancer Discovery"},{"key":"10.7717\/peerj.19411\/ref-8","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Machine Learning"},{"issue":"6","key":"10.7717\/peerj.19411\/ref-9","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1001\/jama.2017.7797","article-title":"Unintended consequences of machine learning in medicine","volume":"318","author":"Cabitza","year":"2017","journal-title":"The Journal of the American Medical Association"},{"key":"10.7717\/peerj.19411\/ref-10","doi-asserted-by":"publisher","first-page":"183","DOI":"10.2147\/IJGM","article-title":"Novel biomarker analysis of pleural effusion enhances differentiation of tuberculous from malignant pleural effusion","volume":"9","author":"Chen","year":"2016","journal-title":"International Journal of General Medicine"},{"key":"10.7717\/peerj.19411\/ref-11","first-page":"59","article-title":"Applications of machine learning in cancer prediction and prognosis","volume":"2","author":"Cruz","year":"2007","journal-title":"Cancer Informatics"},{"key":"10.7717\/peerj.19411\/ref-12","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1183\/09031936.00115110","article-title":"Interferon-\u03b3 release assays for the diagnosis of latent Mycobacterium tuberculosis infection: a systematic review and meta-analysis","volume":"37","author":"Diel","year":"2011","journal-title":"European Respiratory Journal"},{"key":"10.7717\/peerj.19411\/ref-13","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2409.14839","article-title":"Explainable and human-grounded AI for decision support systems: the theory of epistemic quasi-partnerships","author":"Dorsch","year":"2024"},{"key":"10.7717\/peerj.19411\/ref-14","doi-asserted-by":"publisher","first-page":"e16405","DOI":"10.7717\/peerj.16405","article-title":"Predictive value of machine learning for the risk of acute kidney injury (AKI) in hospital intensive care units (ICU) patients: a systematic review and meta-analysis","volume":"11","author":"Du","year":"2023","journal-title":"PeerJ"},{"issue":"3","key":"10.7717\/peerj.19411\/ref-15","doi-asserted-by":"publisher","first-page":"880","DOI":"10.1378\/chest.06-2063","article-title":"Diagnosis and treatment of tuberculous pleural effusion in 2006","volume":"131","author":"Gopi","year":"2007","journal-title":"Chest"},{"issue":"37","key":"10.7717\/peerj.19411\/ref-16","doi-asserted-by":"publisher","first-page":"eaay7120","DOI":"10.1126\/scirobotics.aay7120","article-title":"XAI\u2014explainable artificial intelligence","volume":"4","author":"Gunning","year":"2019","journal-title":"Science Robotics"},{"issue":"6","key":"10.7717\/peerj.19411\/ref-17","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1177\/1753465808099522","article-title":"Managing TB in the 21st century: existing and novel drug therapies","volume":"2","author":"Guy","year":"2008","journal-title":"Therapeutic Advances in Respiratory Disease"},{"key":"10.7717\/peerj.19411\/ref-18","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-84858-7","volume-title":"The elements of statistical learning: data mining, inference, and prediction","author":"Hastie","year":"2009"},{"key":"10.7717\/peerj.19411\/ref-19","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1712.09923","article-title":"What do we need to build explainable AI systems for the medical domain?","author":"Holzinger","year":"2017"},{"key":"10.7717\/peerj.19411\/ref-20","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4614-7138-7","volume-title":"An introduction to statistical learning","author":"James","year":"2013"},{"key":"10.7717\/peerj.19411\/ref-21","doi-asserted-by":"publisher","first-page":"20150202","DOI":"10.1098\/rsta.2015.0202","article-title":"Principal component analysis: a review and recent developments","volume":"374","author":"Jolliffe","year":"2016","journal-title":"Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences"},{"key":"10.7717\/peerj.19411\/ref-22","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1007\/978-3-030-32622-7_21","article-title":"Decision trees and applications","volume":"1194","author":"Karalis","year":"2020","journal-title":"Advances in Experimental Medicine and Biology"},{"key":"10.7717\/peerj.19411\/ref-23","first-page":"3149","article-title":"LightGBM: a highly efficient gradient boosting decision tree","author":"Ke","year":"2017"},{"issue":"9785","key":"10.7717\/peerj.19411\/ref-24","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/s0140-6736(10)62173-3","article-title":"Tuberculosis","volume":"378","author":"Lawn","year":"2011","journal-title":"Lancet"},{"key":"10.7717\/peerj.19411\/ref-25","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1186\/s12911-022-01951-1","article-title":"Machine learning algorithms\u2019 accuracy in predicting kidney disease progression: a systematic review and meta-analysis","volume":"22","author":"Lei","year":"2022","journal-title":"BMC Medical Informatics and Decision Making"},{"key":"10.7717\/peerj.19411\/ref-26","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1111\/j.1440-1843.2010.01723.x","article-title":"Update on tuberculous pleural effusion","volume":"15","author":"Light","year":"2010","journal-title":"Respirology"},{"key":"10.7717\/peerj.19411\/ref-27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2406.18546","article-title":"Application of multimodal fusion deep learning model in disease recognition","author":"Liu","year":"2024"},{"key":"10.7717\/peerj.19411\/ref-28","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nature Machine Intelligence"},{"key":"10.7717\/peerj.19411\/ref-29","first-page":"4768","article-title":"Advances in neural information processing systems 30","volume":"30","author":"Lundberg","year":"2017"},{"issue":"4","key":"10.7717\/peerj.19411\/ref-30","doi-asserted-by":"publisher","first-page":"230143","DOI":"10.1183\/20734735.0143-2023","article-title":"The tuberculous pleural effusion","volume":"19","author":"McNally","year":"2023","journal-title":"Breathe"},{"issue":"suppl_2","key":"10.7717\/peerj.19411\/ref-31","doi-asserted-by":"publisher","first-page":"S147-58","DOI":"10.1093\/infdis\/jir860","article-title":"Tuberculosis diagnostics and biomarkers: needs, challenges, recent advances, and opportunities","volume":"205","author":"McNerney","year":"2012","journal-title":"The Journal of Infectious Diseases"},{"key":"10.7717\/peerj.19411\/ref-32","doi-asserted-by":"publisher","first-page":"101968","DOI":"10.1016\/j.cose.2020.101968","article-title":"A novel approach for detecting vulnerable IoT devices connected behind a home NAT","volume":"97","author":"Meidan","year":"2020","journal-title":"Computers & Security"},{"issue":"2","key":"10.7717\/peerj.19411\/ref-33","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1080\/13645706.2019.1575882","article-title":"Introduction to artificial intelligence in medicine","volume":"28","author":"Mintz","year":"2019","journal-title":"Minimally Invasive Therapy & Allied Technologies"},{"key":"10.7717\/peerj.19411\/ref-34","volume-title":"Interpretable machine learning","author":"Molnar","year":"2020"},{"key":"10.7717\/peerj.19411\/ref-35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2410.01649","article-title":"shapiq: shapley interactions for machine learning","author":"Muschalik","year":"2024"},{"key":"10.7717\/peerj.19411\/ref-36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2410.12692","article-title":"Machine learning approach to brain tumor detection and classification","author":"Oh","year":"2024"},{"key":"10.7717\/peerj.19411\/ref-37","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1007\/s00408-009-9165-3","article-title":"Tuberculous pleural effusion","volume":"187","author":"Porcel","year":"2009","journal-title":"Lung"},{"issue":"15","key":"10.7717\/peerj.19411\/ref-38","doi-asserted-by":"publisher","first-page":"282","DOI":"10.21037\/atm.2016.07.23","article-title":"Advances in the diagnosis of tuberculous pleuritis","volume":"4","author":"Porcel","year":"2016","journal-title":"Annals of Translational Medicine"},{"key":"10.7717\/peerj.19411\/ref-39","doi-asserted-by":"publisher","first-page":"1753466618808660","DOI":"10.1177\/1753466618808660","article-title":"Biomarkers in the diagnosis of pleural diseases: a 2018 update","volume":"12","author":"Porcel","year":"2018","journal-title":"Therapeutic Advances in Respiratory Disease"},{"issue":"9829","key":"10.7717\/peerj.19411\/ref-40","doi-asserted-by":"publisher","first-page":"1902","DOI":"10.1016\/s0140-6736(12)60727-2","article-title":"Scaling up interventions to achieve global tuberculosis control: progress and new developments","volume":"379","author":"Raviglione","year":"2012","journal-title":"Lancet"},{"key":"10.7717\/peerj.19411\/ref-41","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1186\/s12931-019-1197-5","article-title":"Identifying tuberculous pleural effusion using artificial intelligence machine learning algorithms","volume":"20","author":"Ren","year":"2019","journal-title":"Respiratory Research"},{"key":"10.7717\/peerj.19411\/ref-42","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1007\/s41133-020-00032-0","article-title":"A Comparative analysis of logistic regression, random forest and KNN models for the text classification","volume":"5","author":"Shah","year":"2020","journal-title":"Augmented Human Research"},{"issue":"2","key":"10.7717\/peerj.19411\/ref-43","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1016\/j.jbi.2007.09.003","article-title":"Grand challenges in clinical decision support","volume":"41","author":"Sittig","year":"2008","journal-title":"Journal of Biomedical Informatics"},{"key":"10.7717\/peerj.19411\/ref-44","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1038\/s41746-020-0221-y","article-title":"An overview of clinical decision support systems: benefits, risks, and strategies for success","volume":"3","author":"Sutton","year":"2020","journal-title":"NPJ Digital Medicine"},{"key":"10.7717\/peerj.19411\/ref-45","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1186\/s40537-024-00905-w","article-title":"Feature selection strategies: a comparative analysis of SHAP-value and importance-based methods","volume":"11","author":"Wang","year":"2024","journal-title":"Journal of Big Data"},{"key":"10.7717\/peerj.19411\/ref-46","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1007\/s13253-021-00479-7","article-title":"Techniques to improve ecological interpretability of black-box machine learning models","volume":"27","author":"Welchowski","year":"2021","journal-title":"Journal of Agricultural, Biological and Environmental Statistics"},{"key":"10.7717\/peerj.19411\/ref-47","volume-title":"Multidrug and extensively drug-resistant TB (M\/XDR-TB): 2010 global report on surveillance and response","author":"World Health Organization","year":"2010"},{"issue":"10","key":"10.7717\/peerj.19411\/ref-48","doi-asserted-by":"publisher","first-page":"2357","DOI":"10.1109\/tnnls.2014.2382123","article-title":"Linear regression-based efficient SVM learning for large-scale classification","volume":"26","author":"Wu","year":"2015","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.7717\/peerj.19411\/ref-49","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1007\/s10994-011-5268-1","article-title":"Robustness and generalization","volume":"86","author":"Xu","year":"2012","journal-title":"Machine Learning"},{"key":"10.7717\/peerj.19411\/ref-50","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2406.13300","article-title":"LightGBM robust optimization algorithm based on topological data analysis","author":"Yang","year":"2024"},{"issue":"3","key":"10.7717\/peerj.19411\/ref-51","doi-asserted-by":"publisher","first-page":"e18391","DOI":"10.7717\/peerj.18391","article-title":"Common laboratory results-based artificial intelligence analysis achieves accurate classification of plasma cell dyscrasias","volume":"12","author":"Yao","year":"2024","journal-title":"PeerJ"},{"key":"10.7717\/peerj.19411\/ref-52","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2410.03705","article-title":"Gradient boosting decision trees on medical diagnosis over tabular data","author":"Y\u0131ld\u0131z","year":"2024"},{"issue":"7","key":"10.7717\/peerj.19411\/ref-53","doi-asserted-by":"publisher","first-page":"E486\u201394","DOI":"10.21037\/jtd.2016.05.87","article-title":"Tuberculous pleural effusion","volume":"8","author":"Zhai","year":"2016","journal-title":"Journal of Thoracic Disease"},{"issue":"suppl_2","key":"10.7717\/peerj.19411\/ref-54","doi-asserted-by":"publisher","first-page":"S228\u2013S240","DOI":"10.1093\/infdis\/jir858","article-title":"Drug-resistant tuberculosis\u2014current dilemmas, unanswered questions, challenges, and priority needs","volume":"205","author":"Zumla","year":"2012","journal-title":"Journal of Infectious Disease"},{"issue":"8","key":"10.7717\/peerj.19411\/ref-55","doi-asserted-by":"publisher","first-page":"745","DOI":"10.1056\/NEJMra1200894","article-title":"Tuberculosis","volume":"368","author":"Zumla","year":"2013","journal-title":"New England Journal of Medicine"}],"container-title":["PeerJ"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/19411.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/19411.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/19411.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/19411.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T04:49:13Z","timestamp":1747716553000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/19411"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,20]]},"references-count":55,"alternative-id":["10.7717\/peerj.19411"],"URL":"https:\/\/doi.org\/10.7717\/peerj.19411","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2167-8359"],"issn-type":[{"value":"2167-8359","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,20]]},"article-number":"e19411"}}