{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T05:24:40Z","timestamp":1786944280261,"version":"build-2736575974"},"reference-count":29,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T00:00:00Z","timestamp":1786924800000},"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. Oncol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Clinicians face challenges in diagnosing malignant pleural effusion (MPE) and distinguishing it from benign causes. This study aimed to develop and validate machine learning (ML) models for this purpose.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The retrospective study included 1,530 untreated patients with pleural effusion (PE) between January 2016 and December 2025. Clinical variables, including age, sex, smoking status, and laboratory indices were collected for analysis. The patients were randomly divided into the training and test sets at a ratio of 7:3. Six ML algorithms were developed and compared to determine the best diagnostic model for MPE using seven metrics, calibration curve, and decision curve. The SHapley Additive exPlanations (SHAP) values were used to interpret the model. An independent cohort of 244 PE patients was used for external validation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Based on the feature importance analysis, the XGBoost (extreme gradient boosting) model achieved the best diagnostic performance in the training set, with an AUC of 0.988 (95% CI: 0.982-0.993), the lowest brier score 0.037 (95% CI: 0.029-0.045), and high values for accuracy of 0.951, sensitivity of 0.891, specificity of 0.984, and F1 score of 0.928. Six features were included: fluid carcinoembryonic antigen (CEA), serum CEA, serum cytokeratin 19 fragment (CYFRA 21-1), fluid carbohydrate antigen 724 (CA724), fluid carbohydrate antigen CA199 (CA199), and fluid adenosine deaminase (ADA). SHAP analysis showed that fluid CEA, fluid ADA, and serum CYFRA21\u20131 were the three most important variables.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>We developed and validated an accurate and interpretable XGBoost model for distinguishing MPE from BPE using routine laboratory data, which might be applied in clinical practice and decision-making.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2026.1880122","type":"journal-article","created":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T04:35:03Z","timestamp":1786941303000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Development and external validation of machine-learning models for diagnosing malignant pleural effusion"],"prefix":"10.3389","volume":"16","author":[{"given":"Aihua","family":"Wu","sequence":"first","affiliation":[{"name":"Department of Laboratory Medicine, The First Affiliated Hospital of Ningbo University","place":["Ningbo, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanshan","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Laboratory Medicine, The First Affiliated Hospital of Ningbo University","place":["Ningbo, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongying","family":"Ma","sequence":"additional","affiliation":[{"name":"Department of Respiratory and Critical Care Medicine, The First Affiliated Hospital of Ningbo University","place":["Ningbo, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Songbo","family":"Yuan","sequence":"additional","affiliation":[{"name":"Department of Laboratory Medicine, The Affiliated People\u2019s Hospital of Ningbo University","place":["Ningbo, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanqing","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Laboratory Medicine, The First Affiliated Hospital of Ningbo University","place":["Ningbo, Zhejiang, China"]},{"name":"School of Medicine, Ningbo University","place":["Ningbo, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,17]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1080\/17476348.2020.1684266","article-title":"Advances in pleural effusion diagnostics","volume":"14","author":"Ferreiro","year":"2020","journal-title":"Expert Rev Respir Med"},{"key":"B2","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1186\/s12931-024-02684-7","article-title":"Malignant pleural effusion: current understanding and therapeutic approach","volume":"25","author":"Gonnelli","year":"2024","journal-title":"Respir Res"},{"key":"B3","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.arbres.2022.09.017","article-title":"Diagnosis and treatment of pleural effusion. Recommendations of the Spanish Society of Pulmonology and Thoracic Surgery. Update 2022","volume":"59","author":"Botana Rial","year":"2023","journal-title":"Arch Bronconeumol"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/j.mcna.2018.12.007","article-title":"Update in the management of pleural effusions","volume":"103","author":"Aboudara","year":"2019","journal-title":"Med Clin North Am"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2021.20306","article-title":"Prevalence, causes, and health care burden of pleural effusions among hospitalized adults in China","volume":"4","author":"Tian","year":"2021","journal-title":"JAMA Netw Open"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1801254","DOI":"10.1183\/13993003.01254-2018","article-title":"Investigating unilateral pleural effusions: the role of cytology","volume":"52","author":"Arnold","year":"2018","journal-title":"Eur Respir J"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1016\/j.rmed.2022.106802","article-title":"Update on the diagnosis and management of Malignant pleural effusions","volume":"196","author":"Bashour","year":"2022","journal-title":"Respir Med"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1016\/j.amjmed.2022.04.017","article-title":"Malignant pleural effusion: presentation, diagnosis, and management","volume":"135","author":"Gayen","year":"2022","journal-title":"Am J Med"},{"key":"B9","doi-asserted-by":"publisher","first-page":"987","DOI":"10.1080\/17476348.2020.1788940","article-title":"Medical thoracoscopy in the diagnosis of pleural disease: a guide for the clinician","volume":"14","author":"Shaikh","year":"2020","journal-title":"Expert Rev Respir Med"},{"key":"B10","doi-asserted-by":"publisher","first-page":"bbab128","DOI":"10.1093\/bib\/bbab128","article-title":"Machine learning approach to gene essentiality prediction: a review","volume":"22","author":"Aromolaran","year":"2021","journal-title":"Brief Bioinform"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1111\/joim.12822","article-title":"eDoctor: machine learning and the future of medicine","volume":"284","author":"Handelman","year":"2018","journal-title":"J Intern Med"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1161\/circulationaha.115.001593","article-title":"Machine learning in medicine","volume":"132","author":"Deo","year":"2015","journal-title":"Circulation"},{"key":"B13","doi-asserted-by":"publisher","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":"B14","doi-asserted-by":"publisher","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":"B15","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":"Respir Res"},{"key":"B16","doi-asserted-by":"publisher","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":"B17","doi-asserted-by":"publisher","DOI":"10.1177\/03936155231158125","article-title":"Diagnosis of Malignant pleural effusion with combinations of multiple tumor markers: a comparison study of five machine learning models","volume":"38","author":"Zhang","year":"2023","journal-title":"Int J Biol Markers"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1016\/s1532-0464(03)00034-0","article-title":"Logistic regression and artificial neural network classification models: a methodology review","volume":"35","author":"Dreiseitl","year":"2002","journal-title":"J BioMed Inform"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1021\/acs.molpharmaceut.7b00578","article-title":"Comparison of deep learning with multiple machine learning methods and metrics using diverse drug discovery data sets","volume":"14","author":"Korotcov","year":"2017","journal-title":"Mol Pharm"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106970","article-title":"Improved fractional-order gradient descent method based on multilayer perceptron","volume":"183","author":"Zhou","year":"2025","journal-title":"Neural Netw"},{"key":"B21","doi-asserted-by":"publisher","first-page":"499","DOI":"10.3390\/polym17040499","article-title":"Boosting-based machine learning applications in polymer science: a review","volume":"17","author":"Malashin","year":"2025","journal-title":"Polymers (Basel)"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2022.e11383","article-title":"Differentiating Malignant pleural mesothelioma and metastatic pleural disease based on a machine learning model with primary CT signs: a multicentre study","volume":"8","author":"Li","year":"2022","journal-title":"Heliyon"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1177\/17534666231208632","article-title":"Development and validation of a machine learning model for differential diagnosis of Malignant pleural effusion using routine laboratory data","volume":"17","author":"Wei","year":"2023","journal-title":"Ther Adv Respir Dis"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1513\/AnnalsATS.202305-410OC","article-title":"Differential diagnosis of pleural effusion using machine learning","volume":"21","author":"Kim","year":"2024","journal-title":"Ann Am Thorac Soc"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1002\/ctm2.842","article-title":"EASY-APP: an artificial intelligence model and application for early and easy prediction of severity in acute pancreatitis","volume":"12","author":"Kui","year":"2022","journal-title":"Clin Transl Med"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1016\/j.clinbiochem.2016.08.006","article-title":"Evaluation of predictive value of pleural CEA in patients with pleural effusions and histological findings: a prospective study and literature review","volume":"49","author":"Tozzoli","year":"2016","journal-title":"Clin Biochem"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.21037\/tlcr-20-1111","article-title":"Pleural biomarkers in diagnostics of Malignant pleural effusion: a narrative review","volume":"10","author":"Zhang","year":"2021","journal-title":"Transl Lung Cancer Res"},{"key":"B28","doi-asserted-by":"publisher","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":"B29","doi-asserted-by":"publisher","first-page":"498","DOI":"10.3390\/ijerph23040498","article-title":"Association of serum ADA levels in pulmonary tuberculosis: a systematic review and meta-analysis","volume":"23","author":"Songsri","year":"2026","journal-title":"Int J Environ Res Public Health"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1880122\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T04:35:05Z","timestamp":1786941305000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1880122\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,17]]},"references-count":29,"alternative-id":["10.3389\/fonc.2026.1880122"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1880122","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,17]]},"article-number":"1880122"}}