{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:31:29Z","timestamp":1759332689851},"reference-count":32,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"6","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Comput Assist Tomogr"],"published-print":{"date-parts":[[2020,11]]},"abstract":"<jats:sec>\n            <jats:title>Purpose<\/jats:title>\n            <jats:p>To determine the predictive features of thymic carcinomas and high-risk thymomas using random forest algorithm.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Methods<\/jats:title>\n            <jats:p>A total of 137 patients with pathologically confirmed high-risk thymomas and thymic carcinomas were enrolled in this study. Three clinical features and 20 computed tomography features were reviewed. The association between computed tomography features and pathological patterns was analyzed by univariate analysis and random forest. The predictive efficiency of the random forest algorithm was evaluated by receiver operating characteristic curve analysis.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Results<\/jats:title>\n            <jats:p>There were 92 thymic carcinomas and 45 high-risk thymomas in this study. In univariate analysis, patient age, presence of myasthenia gravis, lesion shape, enhancement pattern, presence of necrosis or cystic change, mediastinal invasion, vessel invasion, lymphadenopathy, pericardial effusion, and distant organ metastasis were found to be statistically different between high-risk thymomas and thymic carcinomas (all <jats:italic toggle=\"yes\">P<\/jats:italic> &lt; 0.01). Random forest suggested that tumor shape, lymphadenopathy, and the presence of pericardial effusion were the key features in tumor differentiation. The predictive accuracy for the test data and whole data was 94.73% and 96.35%, respectively. Further receiver operating characteristic curve analysis showed the area under the curve was 0.957 (95% confidence interval, 0.986\u20130.929).<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Conclusions<\/jats:title>\n            <jats:p>The random forest model in the present study has high efficiency in predictive diagnosis of thymic carcinomas and high-risk thymomas. Tumor shape, lymphadenopathy, and pericardial effusion are the key features for tumor differentiation. Thymic tumors with irregular shape, the presence of lymphadenopathy, and pericardial effusion are highly indicative of thymic carcinomas.<\/jats:p>\n          <\/jats:sec>","DOI":"10.1097\/rct.0000000000000953","type":"journal-article","created":{"date-parts":[[2020,1,30]],"date-time":"2020-01-30T02:31:27Z","timestamp":1580351487000},"page":"857-864","source":"Crossref","is-referenced-by-count":5,"title":["Predictive Features of Thymic Carcinoma and High-Risk Thymomas Using Random Forest Analysis"],"prefix":"10.1097","volume":"44","author":[{"given":"Haiyang","family":"Dai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Medical Imaging, Shandong Tumor Hospital and Institute, Jinan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Xiao","sequence":"additional","affiliation":[{"name":"College of Mathematics and Statistics, Hanshan Normal University, Chaozhou, China."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bowen","family":"Lan","sequence":"additional","affiliation":[{"name":"Department of Medical Imaging, Huizhou Municipal Central Hospital, Huizhou"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guihua","family":"Jiang","sequence":"additional","affiliation":[{"name":"The Second School of Clinical Medicine, Southern Medical University, and Department of Medical Imaging, Guangdong Second Provincial General Hospital, Guangzhou"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junzhang","family":"Tian","sequence":"additional","affiliation":[{"name":"The Second School of Clinical Medicine, Southern Medical University, and Department of Medical Imaging, Guangdong Second Provincial General Hospital, Guangzhou"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"276","published-online":{"date-parts":[[2020,1,29]]},"reference":[{"key":"bib1-20230927","doi-asserted-by":"crossref","first-page":"766","DOI":"10.1093\/ejcts\/ezw107","article-title":"Comparison of outcomes between neuroendocrine thymic tumours and other subtypes of thymic carcinomas: a joint analysis of the European Society of Thoracic Surgeons and the International Thymic Malignancy Interest Group","volume":"50","year":"2016","journal-title":"Eur J Cardiothorac Surg"},{"key":"bib2-20230927","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1016\/j.acra.2012.08.002","article-title":"Preoperative CT findings of thymoma are correlated with postoperative Masaoka Clinical Stage","volume":"20","year":"2013","journal-title":"Academic Radiology"},{"key":"bib3-20230927","doi-asserted-by":"crossref","first-page":"46","DOI":"10.3348\/kjr.2003.4.1.46","article-title":"Thymic epithelial tumors classified according to a newly established WHO scheme: CT and MR findings","volume":"4","year":"2003","journal-title":"Korean J Radiol"},{"key":"bib4-20230927","doi-asserted-by":"crossref","first-page":"1383","DOI":"10.1097\/JTO.0000000000000654","article-title":"The 2015 World Health Organization Classification of Tumors of the Thymus: continuity and changes","volume":"10","year":"2015","journal-title":"J Thorac Oncol"},{"key":"bib5-20230927","doi-asserted-by":"crossref","first-page":"1183","DOI":"10.1016\/j.athoracsur.2003.07.042","article-title":"WHO histologic classification is a prognostic indicator in thymoma","volume":"77","year":"2004","journal-title":"Ann Thorac Surg"},{"key":"bib6-20230927","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1016\/j.humpath.2017.08.018","article-title":"Thymoma: a clinicopathological correlation of 1470 cases","volume":"73","year":"2018","journal-title":"Hum Pathol"},{"key":"bib7-20230927","doi-asserted-by":"crossref","first-page":"283","DOI":"10.2214\/ajr.183.2.1830283","article-title":"Does CT of thymic epithelial tumors enable us to differentiate histologic subtypes and predict prognosis?","volume":"183","year":"2004","journal-title":"AJR Am J Roentgenol"},{"key":"bib8-20230927","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1016\/j.lungcan.2013.11.015","article-title":"Outcome of surgically resected thymic carcinoma: a multicenter experience","volume":"83","year":"2014","journal-title":"Lung Cancer"},{"key":"bib9-20230927","first-page":"1525","article-title":"A single institutional experience of surgically resected thymic epithelial tumors over 10 years: clinical outcomes and clinicopathologic features","volume":"19","year":"2008","journal-title":"Oncol Rep"},{"key":"bib10-20230927","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1016\/j.ejrad.2006.05.003","article-title":"Thymic epithelial tumors: comparison of CT and MR imaging findings of low-risk thymomas, high-risk thymomas, and thymic carcinomas","volume":"60","year":"2006","journal-title":"Eur J Radiol"},{"key":"bib11-20230927","doi-asserted-by":"crossref","first-page":"1274","DOI":"10.1097\/JTO.0b013e31821c4203","article-title":"Computed tomography findings predicting invasiveness of thymoma","volume":"6","year":"2011","journal-title":"J Thorac Oncol"},{"key":"bib12-20230927","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1186\/s13148-019-0619-z","article-title":"Discovery and validation of DNA methylation markers for overall survival prognosis in patients with thymic epithelial tumors","volume":"11","year":"2019","journal-title":"Clin Epigenetics"},{"key":"bib13-20230927","doi-asserted-by":"crossref","first-page":"3102","DOI":"10.1002\/sim.5775","article-title":"A random forest approach for competing risks based on pseudo-values","volume":"32","year":"2013","journal-title":"Stat Med"},{"key":"bib14-20230927","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1186\/1471-2105-11-110","article-title":"The behaviour of random forest permutation-based variable importance measures under predictor correlation","volume":"11","year":"2010","journal-title":"BMC Bioinform"},{"key":"bib15-20230927","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1016\/B978-0-12-380862-2.00004-7","article-title":"Multigenic modeling of complex disease by random forests","volume":"72","year":"2010","journal-title":"Adv Genet"},{"key":"bib16-20230927","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1186\/1471-2105-8-25","article-title":"Bias in random forest variable importance measures: illustrations, sources and a solution","volume":"8","year":"2007","journal-title":"BMC Bioinform"},{"key":"bib17-20230927","first-page":"9","article-title":"Random forests for feature selection in QSPR models\u2014an application for predicting standard enthalpy of formation of hydrocarbons","volume":"5","year":"2013","journal-title":"J Chem"},{"key":"bib18-20230927","doi-asserted-by":"crossref","first-page":"250","DOI":"10.1093\/bioinformatics\/btp640","article-title":"Pathway analysis using random forests with bivariate node-split for survival outcomes","volume":"26","year":"2010","journal-title":"Bioinformatics"},{"key":"bib19-20230927","doi-asserted-by":"crossref","first-page":"6716","DOI":"10.3168\/jds.2012-6237","article-title":"Random forests approach for identifying additive and epistatic single nucleotide polymorphisms associated with residual feed intake in dairy cattle","volume":"96","year":"2013","journal-title":"J Dairy Sci"},{"key":"bib20-20230927","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1186\/1471-2105-9-307","article-title":"Conditional variable importance for random forests","volume":"9","year":"2008","journal-title":"BMC Bioinform"},{"key":"bib21-20230927","doi-asserted-by":"crossref","first-page":"3086","DOI":"10.1007\/s00330-015-4172-7","article-title":"Predictive features of CT for risk stratifications in patients with primary gastrointestinal stromal tumour","volume":"26","year":"2016","journal-title":"Eur Radiol"},{"key":"bib22-20230927","doi-asserted-by":"crossref","first-page":"S296","DOI":"10.1097\/JTO.0b013e3181f209ca","article-title":"Imaging thymoma","volume":"5","year":"2010","journal-title":"J Thorac Oncol"},{"key":"bib23-20230927","doi-asserted-by":"crossref","first-page":"452","DOI":"10.1102\/1470-7330.2012.0041","article-title":"Diffusion magnetic resonance imaging of chest tumors","volume":"12","year":"2012","journal-title":"Cancer Imaging"},{"key":"bib24-20230927","first-page":"S161","article-title":"Non-conventional imaging of lung cancer","volume":"10 spec no A","year":"2010","journal-title":"Cancer Imaging"},{"key":"bib25-20230927","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1097\/RTI.0b013e3181cc4cd7","article-title":"Thoracic magnetic resonance imaging 1985 to 2010","volume":"25","year":"2010","journal-title":"J Thorac Imaging"},{"key":"bib26-20230927","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1148\/radiol.14131643","article-title":"Diffusion-weighted MR imaging in thymic epithelial tumors: correlation with World Health Organization Classification and Clinical Staging","volume":"273","year":"2014","journal-title":"Radiology"},{"key":"bib27-20230927","doi-asserted-by":"crossref","first-page":"6984","DOI":"10.1038\/srep06984","article-title":"Predicting subtypes of thymic epithelial tumors using CT: new perspective based on a comprehensive analysis of 216 patients","volume":"4","year":"2014","journal-title":"Sci Rep"},{"key":"bib28-20230927","doi-asserted-by":"crossref","first-page":"1992","DOI":"10.1007\/s00330-016-4542-9","article-title":"Volume-based quantification using dual-energy computed tomography in the differentiation of thymic epithelial tumours: an initial experience","volume":"27","year":"2017","journal-title":"Eur Radiol"},{"key":"bib29-20230927","doi-asserted-by":"crossref","first-page":"433","DOI":"10.2214\/ajr.176.2.1760433","article-title":"Malignant thymic epithelial tumors: CT-pathologic correlation","volume":"176","year":"2001","journal-title":"AJR Am J Roentgenol"},{"key":"bib30-20230927","first-page":"105","article-title":"Diagnostic value of dual-time-point F-18 FDG PET\/CT and chest CT for the prediction of thymic epithelial neoplasms","volume":"71","year":"2017","journal-title":"Acta Med Okayama"},{"key":"bib31-20230927","doi-asserted-by":"crossref","first-page":"5581","DOI":"10.7314\/APJCP.2012.13.11.5581","article-title":"Relationship between computed tomography manifestations of thymic epithelial tumors and the WHO pathological classification","volume":"13","year":"2012","journal-title":"Asian Pac J Cancer Prev"},{"key":"bib32-20230927","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/j.lungcan.2005.05.009","article-title":"World Health Organization histologic classification: an independent prognostic factor in resected thymomas","volume":"50","year":"2005","journal-title":"Lung Cancer"}],"container-title":["Journal of Computer Assisted Tomography"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.lww.com\/10.1097\/RCT.0000000000000953","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,27]],"date-time":"2023-09-27T18:30:07Z","timestamp":1695839407000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.lww.com\/10.1097\/RCT.0000000000000953"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1,29]]},"references-count":32,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2020]]}},"URL":"https:\/\/doi.org\/10.1097\/rct.0000000000000953","relation":{},"ISSN":["1532-3145","0363-8715"],"issn-type":[{"value":"1532-3145","type":"electronic"},{"value":"0363-8715","type":"print"}],"subject":[],"published":{"date-parts":[[2020,1,29]]}}}