{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T23:33:00Z","timestamp":1785540780252,"version":"3.56.0"},"reference-count":41,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T00:00:00Z","timestamp":1770076800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Surgical Standardized Diagnosis and Treatment Research Project","award":["WKZX2023WK0112"],"award-info":[{"award-number":["WKZX2023WK0112"]}]},{"name":"Jilin Province\u2019s Special Project for Medical and Health Care Talents","award":["JLSWSRCZX2023-35, JLSWSRCZX2023-96"],"award-info":[{"award-number":["JLSWSRCZX2023-35, JLSWSRCZX2023-96"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aims to evaluate whether Positron Emission Tomography\u2013Computed Tomography (PET-CT) imaging features of primary tumors and lymph nodes, combined with clinical and pathological data, can accurately predict mediastinal lymph node metastasis (MLNM) in resectable non-small cell lung cancer (NSCLC) using machine learning models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A retrospective study was conducted on 390 NSCLC patients who underwent tumor resection and lymph node dissection between January 2017 and December 2023. All patients received 18F-fluorodeoxyglucose (18F-FDG) PET-CT scans within two weeks before surgery. Data from 390 primary tumors and 1,026 lymph node stations were analyzed. Clinical and PET-CT imaging features were extracted, and feature selection was performed using a random forest algorithm. Eight machine learning models were evaluated, including Logistic Regression, classification and regression tree (CART), support vector machine (SVM), gradient boosting decision tree (GBDT), Random Forest, multi-layer perceptron (MLP), extreme gradient boosting tree (XGBoost) and k-nearest neighbor algorithm (KNN).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Three models were developed<\/jats:title>\n                    <jats:p>Tumor-Pathology-Clinical (TPC), Lymph-Pathology-Clinical (LPC), and Tumor-Lymph-Pathology-Clinical (TLPC). Model performance was assessed using Receiver Operating Characteristic (ROC) curves, Decision Curve Analysis (DCA), and confusion matrices.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The TLPC model, based on the XGBoost algorithm, showed the best performance, with an Area Under the Curve (AUC) of 0.90 (95% CI [0.883\u20130.957]), specificity of 0.84, and sensitivity of 0.96 (\n                      <jats:italic>P<\/jats:italic>\n                      = 0.0069; significant at\n                      <jats:italic>P<\/jats:italic>\n                      &lt; 0.05). In comparison, the TPC model achieved an AUC of 0.67 (95% CI [0.647\u20130.703]), specificity of 0.46, and sensitivity of 0.56 (\n                      <jats:italic>P<\/jats:italic>\n                      = 0.7037; not significant). The LPC model showed intermediate performance, with an AUC of 0.78 (95% CI [0.713\u20130.751]), specificity of 0.73, and sensitivity of 0.84 (\n                      <jats:italic>P<\/jats:italic>\n                      = 0.0269; significant at\n                      <jats:italic>P<\/jats:italic>\n                      &lt; 0.05). All\n                      <jats:italic>P<\/jats:italic>\n                      -values were derived from DeLong\u2019s test comparing AUCs between models, with statistical significance defined as\n                      <jats:italic>P<\/jats:italic>\n                      &lt; 0.05. Of the 1,026 lymph node stations analyzed, 204 showed metastasis, while 822 did not. XGBoost consistently outperformed other models in predicting MLNM.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Combining PET-CT imaging features of primary tumors and lymph nodes with clinical and pathological data shows promise for accurately predicting MLNM in NSCLC. The TLPC model offers a non-invasive method for identifying lymph node metastasis, supporting personalized treatment strategies. However, since PET-CT was performed selectively rather than routinely acquired, external validation across diverse clinical settings is warranted to confirm model generalizability.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.7717\/peerj.20788","type":"journal-article","created":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T08:58:01Z","timestamp":1770109081000},"page":"e20788","source":"Crossref","is-referenced-by-count":2,"title":["Machine learning-driven PET-CT and clinical pathology model for predicting mediastinal lymph node metastasis in non-small cell lung cancer: a retrospective cohort study"],"prefix":"10.7717","volume":"14","author":[{"given":"Taiyu","family":"Bi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Qiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaotian","family":"Duan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yipeng","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhe","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinjun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianzun","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bowei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingbo","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9658-5186","authenticated-orcid":true,"given":"Wei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"4443","published-online":{"date-parts":[[2026,2,3]]},"reference":[{"issue":"3","key":"10.7717\/peerj.20788\/ref-1","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1016\/j.lungcan.2008.01.005","article-title":"Endobronchial ultrasound and value of PET for prediction of pathological results of mediastinal hot spots in lung cancer patients","volume":"61","author":"Bauwens","year":"2008","journal-title":"Lung Cancer"},{"issue":"6","key":"10.7717\/peerj.20788\/ref-2","doi-asserted-by":"publisher","first-page":"1432","DOI":"10.3390\/cancers12061432","article-title":"Association of a CT-based clinical and radiomics score of non-small cell lung cancer (NSCLC) with lymph node status and overall survival","volume":"12","author":"Botta","year":"2020","journal-title":"Cancers"},{"issue":"3","key":"10.7717\/peerj.20788\/ref-3","doi-asserted-by":"publisher","first-page":"230191","DOI":"10.1183\/20734735.0191-2023","article-title":"Mediastinal staging of nonsmall cell lung cancer: what\u2019s new?","volume":"21","author":"Bradley","year":"2025","journal-title":"Breathe"},{"issue":"2","key":"10.7717\/peerj.20788\/ref-4","doi-asserted-by":"publisher","first-page":"280","DOI":"10.21037\/tlcr.2020.03.13","article-title":"DNA methylation markers that correlate with occult lymph node metastases of non-small cell lung cancer and a preliminary prediction model","volume":"9","author":"Chen","year":"2020","journal-title":"Translational Lung Cancer Research"},{"key":"10.7717\/peerj.20788\/ref-5","first-page":"599","article-title":"Nomogram based on prognostic nutrition index and Chest CT imaging signs predicts lymph node metastasis in NSCLC patients","volume":"30","author":"Chen","year":"2022","journal-title":"Journal of X-Ray Science and Technology"},{"issue":"7","key":"10.7717\/peerj.20788\/ref-6","doi-asserted-by":"publisher","first-page":"4033","DOI":"10.21037\/jtd-21-98","article-title":"Clinicopathological models for predicting lymph node metastasis in patients with early-stage lung adenocarcinoma: the application of machine learning algorithms","volume":"13","author":"Chong","year":"2021","journal-title":"Journal of Thoracic Disease"},{"issue":"2","key":"10.7717\/peerj.20788\/ref-7","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1016\/j.lungcan.2019.11.003","article-title":"Development of a predictive radiomics model for lymph node metastases in pre-surgical CT-based stage IA non-small cell lung cancer","volume":"139","author":"Cong","year":"2020","journal-title":"Lung Cancer"},{"issue":"2","key":"10.7717\/peerj.20788\/ref-8","doi-asserted-by":"publisher","first-page":"77","DOI":"10.3322\/caac.21598","article-title":"Introducing the \u201cVirtual Tumor Board\u201d series in CA: A Cancer Journal for Clinicians","volume":"70","author":"Delman","year":"2020","journal-title":"CA: A Cancer Journal for Clinicians"},{"issue":"4","key":"10.7717\/peerj.20788\/ref-9","doi-asserted-by":"publisher","first-page":"1044","DOI":"10.1378\/chest.12-0350","article-title":"Complications, consequences, and practice patterns of endobronchial ultrasound-guided transbronchial needle aspiration: Results of the AQuIRE registry","volume":"143","author":"Eapen","year":"2013","journal-title":"Chest"},{"key":"10.7717\/peerj.20788\/ref-10","doi-asserted-by":"publisher","first-page":"340","DOI":"10.6004\/jnccn.2023.0020","article-title":"NCCN guidelines(R) insights: non-small cell lung cancer, version 2.2023","volume":"21","author":"Ettinger","year":"2023","journal-title":"Journal of the National Comprehensive Cancer Network"},{"issue":"6","key":"10.7717\/peerj.20788\/ref-11","doi-asserted-by":"publisher","first-page":"2151","DOI":"10.1111\/crj.12786","article-title":"The role of plasma D-dimer levels for predicting lymph node and mediastinal lymph node involvement in non-small cell lung cancer","volume":"12","author":"Gao","year":"2018","journal-title":"The Clinical Respiratory Journal"},{"issue":"11","key":"10.7717\/peerj.20788\/ref-12","doi-asserted-by":"publisher","first-page":"4384","DOI":"10.21037\/jtd-22-1511","article-title":"Artificial intelligence neural network analysis and application of CT imaging features to predict lymph node metastasis in non-small cell lung cancer","volume":"14","author":"Geng","year":"2022","journal-title":"Journal of Thoracic Disease"},{"issue":"1","key":"10.7717\/peerj.20788\/ref-13","doi-asserted-by":"publisher","first-page":"ARTN","DOI":"10.1186\/s12911-023-02171-x","article-title":"Construction of the XGBoost model for early lung cancer prediction based on metabolic indices","volume":"23","author":"Guan","year":"2023","journal-title":"BMC Medical Informatics and Decision Making"},{"issue":"3","key":"10.7717\/peerj.20788\/ref-14","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1016\/j.remn.2015.08.004","article-title":"Ratio between maximum standardized uptake value of N1 lymph nodes and tumor predicts N2 disease in patients with non-small cell lung cancer in 18F-FDG PET-CT scan","volume":"35","author":"Honguero Martinez","year":"2016","journal-title":"Revista Espa\u00f1ola de Medicina Nuclear e Imagen Molecular"},{"issue":"1","key":"10.7717\/peerj.20788\/ref-15","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1016\/j.crad.2022.08.140","article-title":"Preoperative prediction of mediastinal lymph node metastasis in non-small cell lung cancer based on (18)F-FDG PET\/CT radiomics","volume":"78","author":"Huang","year":"2023","journal-title":"Clinical Radiology"},{"issue":"2","key":"10.7717\/peerj.20788\/ref-16","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1097\/eus.0000000000000051","article-title":"A risk-scoring model based on endobronchial ultrasound multimodal imaging for predicting metastatic lymph nodes in lung cancer patients","volume":"13","author":"Huang","year":"2024","journal-title":"Endoscopic Ultrasound"},{"key":"10.7717\/peerj.20788\/ref-17","doi-asserted-by":"publisher","first-page":"e77880","DOI":"10.7759\/cureus.77880","article-title":"Diagnostic accuracy of FDG PET-CT in lymph nodal staging of lung cancer","volume":"17","author":"Khan","year":"2025","journal-title":"Cureus"},{"key":"10.7717\/peerj.20788\/ref-18","doi-asserted-by":"publisher","first-page":"1618494","DOI":"10.3389\/fonc.2025.1618494","article-title":"Prediction of lymph node metastasis in lung adenocarcinoma using a PET\/CT radiomics-based ensemble learning model and its pathological basis","volume":"15","author":"Li","year":"2025","journal-title":"Frontiers in Oncology"},{"issue":"1","key":"10.7717\/peerj.20788\/ref-19","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1186\/s12967-022-03369-9","article-title":"XGBoost-based and tumor-immune characterized gene signature for the prediction of metastatic status in breast cancer","volume":"20","author":"Li","year":"2022","journal-title":"Journal of Translational Medicine"},{"issue":"1","key":"10.7717\/peerj.20788\/ref-20","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1186\/s12880-023-01004-7","article-title":"The value on SUV-derived parameters assessed on 18F-FDG PET\/CT for predicting mediastinal lymph node metastasis in non-small cell lung cancer","volume":"23","author":"Liao","year":"2023","journal-title":"BMC Medical Imaging"},{"issue":"1","key":"10.7717\/peerj.20788\/ref-21","doi-asserted-by":"publisher","first-page":"430","DOI":"10.21037\/tlcr-20-1026","article-title":"A nomogram for predicting the risk of lymph node metastasis in T1-2 non-small-cell lung cancer based on PET\/CT and clinical characteristics","volume":"10","author":"Lv","year":"2021","journal-title":"Translational Lung Cancer Research"},{"issue":"5","key":"10.7717\/peerj.20788\/ref-22","doi-asserted-by":"publisher","first-page":"599","DOI":"10.6004\/jnccn.2012.0062","article-title":"The management of patients with stage IIIA non-small cell lung cancer with N2 mediastinal node involvement","volume":"10","author":"Martins","year":"2012","journal-title":"Journal of the National Comprehensive Cancer Network"},{"issue":"15","key":"10.7717\/peerj.20788\/ref-23","doi-asserted-by":"publisher","first-page":"1924","DOI":"10.3390\/healthcare13151924","article-title":"Balancing accuracy, safety, and cost in mediastinal diagnostics: a systematic review of EBUS and mediastinoscopy in NSCLC","volume":"13","author":"Matache","year":"2025","journal-title":"Healthcare"},{"issue":"8","key":"10.7717\/peerj.20788\/ref-24","doi-asserted-by":"publisher","first-page":"1207","DOI":"10.1097\/JTO.0000000000000601","article-title":"A predictive model for lymph node involvement with malignancy on PET\/CT in non-small-cell lung cancer","volume":"10","author":"Mattes","year":"2015","journal-title":"Journal of Thoracic Oncology"},{"issue":"9","key":"10.7717\/peerj.20788\/ref-25","doi-asserted-by":"publisher","first-page":"2068","DOI":"10.1093\/annonc\/mdq693","article-title":"Significance of smoking history and FDG uptake for pathological N2 staging in clinical N2-negative non-small-cell lung cancer","volume":"22","author":"Na","year":"2011","journal-title":"Annals of Oncology"},{"issue":"1","key":"10.7717\/peerj.20788\/ref-26","doi-asserted-by":"publisher","first-page":"983","DOI":"10.1186\/s12885-021-08688-6","article-title":"Diagnostic utility of metabolic parameters on FDG PET\/CT for lymph node metastasis in patients with cN2 non-small cell lung cancer","volume":"21","author":"Nakanishi","year":"2021","journal-title":"BMC Cancer"},{"issue":"8","key":"10.7717\/peerj.20788\/ref-27","doi-asserted-by":"publisher","first-page":"1179","DOI":"10.1111\/j.1440-1843.2010.01793.x","article-title":"Occult nodal metastasis in patients with non-small cell lung cancer at clinical stage IA by PET\/CT","volume":"15","author":"Park","year":"2010","journal-title":"Respirology"},{"key":"10.7717\/peerj.20788\/ref-28","doi-asserted-by":"publisher","first-page":"683282","DOI":"10.3389\/fonc.2021.683282","article-title":"Development of nomograms for predicting lymph node metastasis and distant metastasis in newly diagnosed T1-2 non-small cell lung cancer: a population-based analysis","volume":"11","author":"Qi","year":"2021","journal-title":"Frontiers in Oncology"},{"key":"10.7717\/peerj.20788\/ref-29","doi-asserted-by":"publisher","first-page":"974934","DOI":"10.3389\/fonc.2022.974934","article-title":"18F-FDG PET\/CT radiomics nomogram for predicting occult lymph node metastasis of non-small cell lung cancer","volume":"12","author":"Qiao","year":"2022","journal-title":"Frontiers in Oncology"},{"issue":"12","key":"10.7717\/peerj.20788\/ref-30","doi-asserted-by":"publisher","first-page":"1637","DOI":"10.1016\/j.annonc.2021.08.1994","article-title":"Early and locally advanced non-small-cell lung cancer: an update of the ESMO clinical practice guidelines focusing on diagnosis, staging, systemic and local therapy","volume":"32","author":"Remon","year":"2021","journal-title":"Annals of Oncology"},{"issue":"7","key":"10.7717\/peerj.20788\/ref-31","doi-asserted-by":"publisher","first-page":"2140","DOI":"10.1007\/s00259-023-06145-z","article-title":"A machine learning tool to improve prediction of mediastinal lymph node metastases in non-small cell lung cancer using routinely obtainable [(18)F]FDG-PET\/CT parameters","volume":"50","author":"Rogasch","year":"2023","journal-title":"European Journal of Nuclear Medicine and Molecular Imaging"},{"issue":"5","key":"10.7717\/peerj.20788\/ref-32","doi-asserted-by":"publisher","first-page":"568","DOI":"10.1097\/JTO.0b013e3181a0d82e","article-title":"The IASLC lung cancer staging project: a proposal for a new international lymph node map in the forthcoming seventh edition of the TNM classification for lung cancer","volume":"4","author":"Rusch","year":"2009","journal-title":"Journal of Thoracic Oncology"},{"issue":"3","key":"10.7717\/peerj.20788\/ref-33","doi-asserted-by":"publisher","first-page":"1332","DOI":"10.1093\/ejcts\/ezae059","article-title":"Multiparametric evaluation of mediastinal lymph node metastases in clinical T0-T1c stage non-small-cell lung cancers","volume":"65","author":"Wang","year":"2024","journal-title":"European Journal of Cardio-Thoracic Surgery"},{"issue":"1","key":"10.7717\/peerj.20788\/ref-34","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1007\/s00432-022-04545-6","article-title":"Developing a primary tumor and lymph node 18F-FDG PET\/CT-clinical (TLPC) model to predict lymph node metastasis of resectable T2-4 NSCLC","volume":"149","author":"Wang","year":"2023","journal-title":"Journal of Cancer Research and Clinical Oncology"},{"key":"10.7717\/peerj.20788\/ref-35","doi-asserted-by":"publisher","first-page":"743","DOI":"10.3389\/fonc.2020.00743","article-title":"Preoperative prediction of lymph node metastasis in patients with early-T-stage non-small cell lung cancer by machine learning algorithms","volume":"10","author":"Wu","year":"2020","journal-title":"Frontiers in Oncology"},{"issue":"6","key":"10.7717\/peerj.20788\/ref-36","doi-asserted-by":"publisher","first-page":"3983","DOI":"10.1007\/s00330-020-07466-5","article-title":"Prediction of mediastinal lymph node metastasis based on 18F-FDG PET\/CT imaging using support vector machine in non-small cell lung cancer","volume":"31","author":"Yin","year":"2021","journal-title":"European Radiology"},{"issue":"4","key":"10.7717\/peerj.20788\/ref-37","doi-asserted-by":"publisher","first-page":"615","DOI":"10.1002\/ijc.34740","article-title":"Differences in the incidence and mortality of digestive cancer between global cancer observatory 2020 and global burden of disease 2019","volume":"154","author":"Yu","year":"2024","journal-title":"International Journal of Cancer"},{"key":"10.7717\/peerj.20788\/ref-38","doi-asserted-by":"publisher","first-page":"1517805","DOI":"10.3389\/fmed.2024.1517805","article-title":"[18F]FDG PET\/CT versus [18F]FDG PET\/MRI in staging of non-small cell lung cancer: a head-to-head comparative meta-analysis","volume":"11","author":"Yu","year":"2024","journal-title":"Frontiers in Medicine"},{"issue":"1","key":"10.7717\/peerj.20788\/ref-39","doi-asserted-by":"publisher","first-page":"8501819","DOI":"10.1155\/2022\/8501819","article-title":"A machine learning approach using XGBoost predicts lung metastasis in patients with ovarian cancer","volume":"2022","author":"Yuan","year":"2022","journal-title":"Biomed Research International"},{"issue":"12","key":"10.7717\/peerj.20788\/ref-40","doi-asserted-by":"publisher","first-page":"8967162","DOI":"10.1155\/2022\/8967162","article-title":"Construction and validation of a recurrent risk nomogram model for non-small cell lung cancer within 1 year after radical resection","volume":"2022","author":"Zeng","year":"2022","journal-title":"Journal of Oncology"},{"key":"10.7717\/peerj.20788\/ref-41","doi-asserted-by":"publisher","first-page":"585029","DOI":"10.3389\/fgene.2020.585029","article-title":"A novel XGBoost method to identify cancer tissue-of-origin based on copy number variations","volume":"11","author":"Zhang","year":"2020","journal-title":"Frontiers in Genetics"}],"container-title":["PeerJ"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/20788.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/20788.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/20788.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/20788.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T08:58:03Z","timestamp":1770109083000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/20788"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,3]]},"references-count":41,"alternative-id":["10.7717\/peerj.20788"],"URL":"https:\/\/doi.org\/10.7717\/peerj.20788","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2167-8359"],"issn-type":[{"value":"2167-8359","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,3]]},"article-number":"e20788"}}