{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T03:07:13Z","timestamp":1787022433373,"version":"build-2736575974"},"reference-count":29,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/501100004332","name":"Seoul National University Hospital Research Fund","doi-asserted-by":"publisher","award":["04-2020-2360"],"award-info":[{"award-number":["04-2020-2360"]}],"id":[{"id":"10.13039\/501100004332","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Seoul National University Hospital Research Fund","award":["04-2020-2360"],"award-info":[{"award-number":["04-2020-2360"]}]}],"content-domain":{"domain":["www.atsjournals.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,2,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Rationale<\/jats:title>\n                    <jats:p>Differential diagnosis of pleural effusion is challenging in clinical practice.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>We aimed to develop a machine learning model to classify the five common causes of pleural effusions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective study collected 49 features from clinical information, blood, and pleural fluid of adult patients who underwent diagnostic thoracentesis between October 2013 and December 2018. Pleural effusions were classified into the following five categories: transudative, malignant, parapneumonic, tuberculous, and other. The performance of five different classifiers, including multinomial logistic regression, support vector machine, random forest, extreme gradient boosting, and light gradient boosting machine (LGB), was evaluated in terms of accuracy and area under the receiver operating characteristic curve through fivefold cross-validation. Hybrid feature selection was applied to determine the most relevant features for classifying pleural effusion.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We analyzed 2,253 patients (training set, n\u2009=\u20091,459; validation set, n\u2009=\u2009365; extra-validation set, n\u2009=\u2009429) and found that the LGB model achieved the best performance in both validation and extra-validation sets. After feature selection, the accuracy of the LGB model with the selected 18 features was equivalent to that with all 49 features (mean\u2009\u00b1\u2009standard deviation): 0.818\u2009\u00b1\u20090.012 and 0.777\u2009\u00b1\u20090.007 in the validation and extra-validation sets, respectively. The model\u2019s mean area under the receiver operating characteristic curve was as high as 0.930\u2009\u00b1\u20090.042 and 0.916\u2009\u00b1\u20090.044 in the validation and extra-validation sets, respectively. In our model, pleural lactate dehydrogenase, protein, and adenosine deaminase levels were the most important factors for classifying pleural effusions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Our LGB model showed satisfactory performance for differential diagnosis of the common causes of pleural effusions. This model could provide clinicians with valuable information regarding the major differential diagnoses of pleural diseases.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1513\/annalsats.202305-410oc","type":"journal-article","created":{"date-parts":[[2023,10,3]],"date-time":"2023-10-03T15:18:39Z","timestamp":1696346319000},"page":"211-217","update-policy":"https:\/\/doi.org\/10.1164\/crossmarkpolicies","source":"Crossref","is-referenced-by-count":16,"title":["Differential Diagnosis of Pleural Effusion Using Machine Learning"],"prefix":"10.1093","volume":"21","author":[{"given":"Na Young","family":"Kim","sequence":"first","affiliation":[{"name":"Division of Pulmonary, Allergy, and Critical Care Medicine, Department of Internal Medicine, Hallym University Dongtan Sacred Heart Hospital, Hwaseong, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boa","family":"Jang","sequence":"additional","affiliation":[{"name":"Department of Transdisciplinary Medicine and"},{"name":"Interdisciplinary Program in Bioengineering, College of Engineering, Seoul National University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kang-Mo","family":"Gu","sequence":"additional","affiliation":[{"name":"Department of Internal Medicine, Chung-Ang University College of Medicine, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Young Sik","family":"Park","sequence":"additional","affiliation":[{"name":"Division of Pulmonary and Critical Care Medicine, Department of Internal Medicine, Seoul National University Hospital, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Young-Gon","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Transdisciplinary Medicine and"},{"name":"Department of Medicine and"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6537-8843","authenticated-orcid":false,"given":"Jaeyoung","family":"Cho","sequence":"additional","affiliation":[{"name":"Division of Pulmonary and Critical Care Medicine, Department of Internal Medicine, Seoul National University Hospital, Seoul, Republic of Korea"},{"name":"Department of Internal Medicine, Seoul National University College of Medicine, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,2,1]]},"reference":[{"key":"2026012203141025700_bib1","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1056\/NEJMra1403503","article-title":"Pleural disease","volume":"378","author":"Feller-Kopman","year":"2018","journal-title":"N Engl J Med"},{"key":"2026012203141025700_bib2","doi-asserted-by":"crossref","first-page":"ii4","DOI":"10.1136\/thx.2010.136978","article-title":"Investigation of a unilateral pleural effusion in adults: British Thoracic Society Pleural Disease Guideline 2010","volume":"65","author":"Hooper","year":"2010","journal-title":"Thorax"},{"key":"2026012203141025700_bib3","volume-title":"Pleural diseases","author":"Light","year":"2013","edition":"6th ed"},{"key":"2026012203141025700_bib4","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1136\/thx.46.2.96","article-title":"Tuberculous pleural effusions: increased culture yield with bedside inoculation of pleural fluid and poor diagnostic value of adenosine deaminase","volume":"46","author":"Maartens","year":"1991","journal-title":"Thorax"},{"key":"2026012203141025700_bib5","doi-asserted-by":"crossref","first-page":"962","DOI":"10.1111\/resp.13673","article-title":"Tuberculous pleural effusion","volume":"24","author":"Shaw","year":"2019","journal-title":"Respirology"},{"key":"2026012203141025700_bib6","doi-asserted-by":"crossref","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"},{"key":"2026012203141025700_bib7","doi-asserted-by":"crossref","first-page":"3422","DOI":"10.21037\/jtd.2020.02.02","article-title":"Can parapneumonic effusion be diagnosed only with pleural fluid analysis?","volume":"12","author":"Park","year":"2020","journal-title":"J Thorac Dis"},{"key":"2026012203141025700_bib8","doi-asserted-by":"crossref","first-page":"756","DOI":"10.4187\/respcare.02738","article-title":"A randomized trial comparing the diagnostic yield of rigid and semirigid thoracoscopy in undiagnosed pleural effusions","volume":"59","author":"Dhooria","year":"2014","journal-title":"Respir Care"},{"key":"2026012203141025700_bib9","doi-asserted-by":"crossref","first-page":"507","DOI":"10.7326\/0003-4819-77-4-507","article-title":"Pleural effusions: the diagnostic separation of transudates and exudates","volume":"77","author":"Light","year":"1972","journal-title":"Ann Intern Med"},{"key":"2026012203141025700_bib10","doi-asserted-by":"crossref","first-page":"1971","DOI":"10.1056\/NEJMcp010731","article-title":"Clinical practice: pleural effusion","volume":"346","author":"Light","year":"2002","journal-title":"N Engl J Med"},{"key":"2026012203141025700_bib11","doi-asserted-by":"crossref","first-page":"402","DOI":"10.1183\/09031936.01.00225601","article-title":"Management of malignant pleural effusions","volume":"18","author":"Antony","year":"2001","journal-title":"Eur Respir J"},{"key":"2026012203141025700_bib12","doi-asserted-by":"crossref","first-page":"485","DOI":"10.1016\/S0014-2565(09)72634-7","article-title":"Parapneumonic pleural effusions and empyema in adults: current practice [in Spanish]","volume":"209","author":"Porcel","year":"2009","journal-title":"Rev Clin Esp"},{"key":"2026012203141025700_bib13","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1016\/j.amjms.2020.10.015","article-title":"Biomarkers of distinguishing neutrophil-predominant tuberculous pleural effusion from parapneumonic pleural effusion","volume":"361","author":"Ren","year":"2021","journal-title":"Am J Med Sci"},{"key":"2026012203141025700_bib14","doi-asserted-by":"crossref","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":"2026012203141025700_bib15","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1016\/j.ins.2021.04.009","article-title":"Multiple imputation using nearest neighbor methods","volume":"570","author":"Faisal","year":"2021","journal-title":"Inf Sci"},{"key":"2026012203141025700_bib16","first-page":"21","volume-title":"Handbook of latent variable and related models","author":"Jamshidian","year":"2007"},{"key":"2026012203141025700_bib17","volume-title":"Expert systems in the micro-electronic age","author":"Quinlan","year":"1979"},{"key":"2026012203141025700_bib18","doi-asserted-by":"crossref","first-page":"682","DOI":"10.5588\/ijtld.12.0829","article-title":"Artificial neural network models to support the diagnosis of pleural tuberculosis in adult patients","volume":"17","author":"Seixas","year":"2013","journal-title":"Int J Tuberc Lung Dis"},{"key":"2026012203141025700_bib19","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1016\/j.cmpb.2017.10.022","article-title":"Developing a new intelligent system for the diagnosis of tuberculous pleural effusion","volume":"153","author":"Li","year":"2018","journal-title":"Comput Methods Programs Biomed"},{"key":"2026012203141025700_bib20","doi-asserted-by":"crossref","first-page":"e0259203","DOI":"10.1371\/journal.pone.0259203","article-title":"Diagnostic accuracy of adenosine deaminase for pleural tuberculosis in a low prevalence setting: a machine learning approach within a 7-year prospective multi-center study","volume":"16","author":"Garcia-Zamalloa","year":"2021","journal-title":"PLoS One"},{"key":"2026012203141025700_bib21","doi-asserted-by":"crossref","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":"Respir Res"},{"key":"2026012203141025700_bib22","doi-asserted-by":"crossref","first-page":"100896","DOI":"10.1016\/j.tranon.2020.100896","article-title":"Driverless artificial intelligence framework for the identification of malignant pleural effusion","volume":"14","author":"Li","year":"2021","journal-title":"Transl Oncol"},{"key":"2026012203141025700_bib23","doi-asserted-by":"crossref","first-page":"5532","DOI":"10.1038\/s41598-022-09550-w","article-title":"Classification of pleural effusions using deep learning visual models: contrastive-loss","volume":"12","author":"Lee","year":"2022","journal-title":"Sci Rep"},{"key":"2026012203141025700_bib24","doi-asserted-by":"crossref","first-page":"744","DOI":"10.1016\/j.rmed.2007.12.007","article-title":"Diagnostic accuracy of adenosine deaminase in tuberculous pleurisy: a meta-analysis","volume":"102","author":"Liang","year":"2008","journal-title":"Respir Med"},{"key":"2026012203141025700_bib25","doi-asserted-by":"crossref","first-page":"820","DOI":"10.1016\/j.rmed.2008.12.023","article-title":"Mycobacterium tuberculosis and polymorphonuclear pleural effusion: incidence and clinical pointers","volume":"103","author":"Lin","year":"2009","journal-title":"Respir Med"},{"key":"2026012203141025700_bib26","doi-asserted-by":"crossref","first-page":"822","DOI":"10.1136\/thoraxjnl-2011-201363","article-title":"Revisiting tuberculous pleurisy: pleural fluid characteristics and diagnostic yield of mycobacterial culture in an endemic area","volume":"67","author":"Ruan","year":"2012","journal-title":"Thorax"},{"key":"2026012203141025700_bib27","doi-asserted-by":"crossref","first-page":"518","DOI":"10.1111\/j.1440-1843.2008.01291.x","article-title":"Diagnostic value of carcinoembryonic antigen in malignant pleural effusion: a meta-analysis","volume":"13","author":"Shi","year":"2008","journal-title":"Respirology"},{"key":"2026012203141025700_bib28","doi-asserted-by":"crossref","first-page":"1161","DOI":"10.1186\/s12879-021-06855-5","article-title":"Decreased annual risk of tuberculosis infection in South Korean healthcare workers using interferon-gamma release assay between 1986 and 2005","volume":"21","author":"Lee","year":"2021","journal-title":"BMC Infect Dis"},{"key":"2026012203141025700_bib29","doi-asserted-by":"crossref","first-page":"376","DOI":"10.1136\/thorax-2021-218581","article-title":"Differentiation of malignant from benign pleural effusions based on artificial intelligence","volume":"78","author":"Wang","year":"2023","journal-title":"Thorax"}],"container-title":["Annals of the American Thoracic Society"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/annalsats\/article-pdf\/21\/2\/211\/66018432\/annalsats_21_2_211.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/annalsats\/article-pdf\/21\/2\/211\/66018432\/annalsats_21_2_211.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T08:15:11Z","timestamp":1769069711000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/annalsats\/article\/21\/2\/211\/8382091"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,1]]},"references-count":29,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024,2,1]]},"published-print":{"date-parts":[[2024,2,1]]}},"URL":"https:\/\/doi.org\/10.1513\/annalsats.202305-410oc","relation":{},"ISSN":["2329-6933","2325-6621"],"issn-type":[{"value":"2329-6933","type":"print"},{"value":"2325-6621","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,2]]},"published":{"date-parts":[[2024,2,1]]},"assertion":[{"value":"2023-05-05","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-10-03","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-02-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}