{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T22:27:20Z","timestamp":1783463240505,"version":"3.55.0"},"reference-count":53,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T00:00:00Z","timestamp":1758844800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.mdpi.com"],"crossmark-restriction":true},"short-container-title":["ARM"],"abstract":"<jats:p>Non-small cell lung cancer (NSCLC) is the leading cause of cancer-related mortality worldwide. Accurate determination of epidermal growth factor receptor (EGFR) mutation status is essential for selecting patients eligible for tyrosine kinase inhibitors (TKIs). However, invasive genotyping is often limited by tissue accessibility and sample quality. This study presents a non-invasive machine learning model combining clinical data, CT morphological features, and radiomic descriptors to predict EGFR mutation status. A retrospective cohort of 138 patients with confirmed EGFR status and pre-treatment CT scans was analyzed. Radiomic features were extracted with PyRadiomics, and feature selection applied mutual information, Spearman correlation, and wrapper-based methods. Five Random Forest models were trained with different feature sets. The best-performing model, based on 11 selected variables, achieved an AUC of 0.91 (95% CI: 0.81\u20131.00) under stratified five-fold cross-validation, with an accuracy of 0.88 \u00b1 0.03. Subgroup analysis showed that EGFR-WT had a performance of precision 0.93 \u00b1 0.04, recall 0.92 \u00b1 0.03, F1-score 0.91 \u00b1 0.02, and EGFR-Mutant had a performance of precision 0.76 \u00b1 0.05, recall 0.71 \u00b1 0.05, F1-score 0.68 \u00b1 0.04. SHapley Additive exPlanations (SHAP) analysis identified tobacco use, enhancement pattern, and gray-level-zone entropy as key predictors. Decision curve analysis confirmed clinical utility, supporting its role as a non-invasive tool for EGFR-screening.<\/jats:p>","DOI":"10.3390\/arm93050039","type":"journal-article","created":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T08:31:28Z","timestamp":1758875488000},"page":"39","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["NSCLC EGFR Mutation Prediction via Random Forest Model: A Clinical\u2013CT\u2013Radiomics Integration Approach"],"prefix":"10.3390","volume":"93","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2061-1058","authenticated-orcid":false,"given":"Anass","family":"Benfares","sequence":"first","affiliation":[{"name":"Faculty of Sciences, Department of Computer Science, Sidi Mohammed Ben Abdellah University, Fez 30000, Morocco"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Badreddine","family":"Alami","sequence":"additional","affiliation":[{"name":"Faculty of Medicine, Department of Radiology, Sidi Mohammed Ben Abdellah University, Fez 30000, Morocco"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4297-3380","authenticated-orcid":false,"given":"Sara","family":"Boukansa","sequence":"additional","affiliation":[{"name":"Faculty of Sciences, Department of Computer Science, Sidi Mohammed Ben Abdellah University, Fez 30000, Morocco"},{"name":"Faculty of Medicine, Department of Radiology, Sidi Mohammed Ben Abdellah University, Fez 30000, Morocco"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mamoun","family":"Qjidaa","sequence":"additional","affiliation":[{"name":"Faculty of Sciences, Department of Computer Science, Mohammed V University, Rabat 10090, Morocco"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ikram","family":"Benomar","sequence":"additional","affiliation":[{"name":"Faculty of Sciences, Department of Computer Science, Sidi Mohammed Ben Abdellah University, Fez 30000, Morocco"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mounia","family":"Serraj","sequence":"additional","affiliation":[{"name":"Faculty of Medicine, Department of Radiology, Sidi Mohammed Ben Abdellah University, Fez 30000, Morocco"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmed","family":"Lakhssassi","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Universit\u00e9 du Qu\u00e9bec en Outaouais, Gatineau, QC J8X 3X7, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammed Ouazzani","family":"Jamil","sequence":"additional","affiliation":[{"name":"Faculty of Engineering Sciences, Private University of Fez, Fez 30000, Morocco"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mustapha","family":"Maaroufi","sequence":"additional","affiliation":[{"name":"Faculty of Medicine, Department of Radiology, Sidi Mohammed Ben Abdellah University, Fez 30000, Morocco"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hassan","family":"Qjidaa","sequence":"additional","affiliation":[{"name":"Faculty of Sciences, Department of Computer Science, Sidi Mohammed Ben Abdellah University, Fez 30000, Morocco"},{"name":"Faculty of Engineering Sciences, Private University of Fez, Fez 30000, Morocco"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,9,26]]},"reference":[{"key":"ref_1","first-page":"209","article-title":"Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide","volume":"71","author":"Sung","year":"2021","journal-title":"CA Cancer J. Clin."},{"key":"ref_2","unstructured":"World Health Organization (2025, July 28). International Agency for Research on Cancer. GLOBOCAN 2020, Available online: https:\/\/gco.iarc.fr\/today."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"446","DOI":"10.1038\/nature25183","article-title":"The biology and management of non-small cell lung cancer","volume":"553","author":"Herbst","year":"2018","journal-title":"Nature"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"S16","DOI":"10.1038\/modpathol.3801018","article-title":"Lung adenocarcinoma: Guiding EGFR-targeted therapy and beyond","volume":"21","author":"Ladanyi","year":"2008","journal-title":"Mod. Pathol."},{"key":"ref_5","first-page":"223","article-title":"Primary Resistance to EGFR Tyrosine Kinase Inhibitors (TKIs): Contexts and Comparisons in EGFR-Mutated Lung Cancer","volume":"3","author":"Kobayashi","year":"2023","journal-title":"J. Respir."},{"key":"ref_6","first-page":"153","article-title":"Prevalence of EGFR exon 20 insertions in NSCLC","volume":"17","author":"Murton","year":"2022","journal-title":"Target Oncol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1177\/0300891620964571","article-title":"Frequency of EGFR mutations in Moroccan NSCLC patients","volume":"107","author":"Sow","year":"2021","journal-title":"Tumori J."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1016\/S1470-2045(09)70364-X","article-title":"Gefitinib versus chemotherapy for NSCLC with EGFR mutations","volume":"11","author":"Mitsudomi","year":"2010","journal-title":"Lancet Oncol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"629","DOI":"10.1056\/NEJMoa1612674","article-title":"Osimertinib or standard EGFR-TKI in NSCLC","volume":"376","author":"Mok","year":"2017","journal-title":"N. Engl. J. Med."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"380","DOI":"10.1016\/j.jtho.2015.11.014","article-title":"First-Line Afatinib versus Chemotherapy in Patients with Non-Small Cell Lung Cancer and Common Epidermal Growth Factor Receptor Gene Mutations and Brain Metastases","volume":"11","author":"Schuler","year":"2016","journal-title":"J. Thorac. Oncol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2866","DOI":"10.1200\/JCO.2010.33.4235","article-title":"Biomarker analyses from a phase III gefitinib study","volume":"29","author":"Fukuoka","year":"2011","journal-title":"J. Clin. Oncol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2149","DOI":"10.1001\/jama.290.16.2149","article-title":"Efficacy of gefitinib in NSCLC: A randomized trial","volume":"290","author":"Kris","year":"2003","journal-title":"JAMA"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1016\/S1470-2045(11)70393-X","article-title":"Erlotinib versus standard chemotherapy in EGFR-mutant NSCLC","volume":"13","author":"Rosell","year":"2012","journal-title":"Lancet Oncol."},{"key":"ref_14","unstructured":"National Comprehensive Cancer Network (2024). NCCN Clinical Practice Guidelines in Oncology: Non-Small Cell Lung Cancer, National Comprehensive Cancer Network (NCCN). Version 3.2024."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"iv192","DOI":"10.1093\/annonc\/mdy275","article-title":"Metastatic Non-Small Cell Lung Cancer: ESMO Clinical Practice Guidelines for Diagnosis, Treatment and Follow-Up","volume":"29","author":"Planchard","year":"2018","journal-title":"Ann. Oncol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"613","DOI":"10.1038\/nature10937","article-title":"A Murine Lung Cancer Co-Clinical Trial Identifies Genetic Modifiers of Therapeutic Response","volume":"483","author":"Chen","year":"2012","journal-title":"Nature"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"709","DOI":"10.1016\/S2213-2600(20)30081-3","article-title":"Circulating tumor cells in lung cancer screening","volume":"8","author":"Marquette","year":"2020","journal-title":"Lancet Respir. Med."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Oh, M.S., Abascal, J., Rennels, A.K., Salehi-Rad, R., Dubinett, S.M., and Liu, B. (2025). Tumor Heterogeneity and the Immune Response in Non-Small Cell Lung Cancer: Emerging Insights and Implications for Immunotherapy. Cancers, 17.","DOI":"10.3390\/cancers17061027"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Yamazaki, K., Kawauchi, S., Okamoto, M., Tanabe, K., Hayashi, C., Mikami, M., and Kusumoto, T. (2025). Comprehensive Serum Glycopeptide Spectra Analysis Combined with Machine Learning for Early Detection of Lung Cancer: A Case\u2013Control Study. Cancers, 17.","DOI":"10.3390\/cancers17091474"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1647","DOI":"10.1016\/j.jtho.2021.06.017","article-title":"Liquid biopsy for advanced NSCLC: A consensus statement from the International Association for the Study of Lung Cancer","volume":"16","author":"Rolfo","year":"2021","journal-title":"J. Thorac. Oncol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"725","DOI":"10.1038\/s41416-019-0573-8","article-title":"Resistance mechanisms to osimertinib in EGFR-mutated non-small cell lung cancer","volume":"121","author":"Leonetti","year":"2019","journal-title":"Br. J. Cancer"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1016\/j.ejca.2011.11.036","article-title":"Radiomics: Extracting more from medical images","volume":"48","author":"Lambin","year":"2012","journal-title":"Eur. J. Cancer"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"4006","DOI":"10.1038\/ncomms5006","article-title":"Decoding tumour phenotype by noninvasive imaging","volume":"5","author":"Aerts","year":"2014","journal-title":"Nat. Commun."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1148\/radiol.2015151169","article-title":"Radiomics: Images are more than pictures","volume":"278","author":"Gillies","year":"2016","journal-title":"Radiology"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1234","DOI":"10.1016\/j.mri.2012.06.010","article-title":"Radiomics: The process and the challenges","volume":"30","author":"Kumar","year":"2012","journal-title":"Magn. Reson. Imaging"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"749","DOI":"10.1038\/nrclinonc.2017.141","article-title":"Radiomics: The bridge between medical imaging and personalized medicine","volume":"14","author":"Lambin","year":"2017","journal-title":"Nat. Rev. Clin. Oncol."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Foresti, G.L., Fusiello, A., and Hancock, E. (2024). Grading and Staging of Bladder Tumors Using Radiomics Analysis in Magnetic Resonance Imaging. Image Analysis and Processing\u2014ICIAP 2023 Workshops, Springer. ICIAP 2023, Lecture Notes in Computer Science.","DOI":"10.1007\/978-3-031-51026-7"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Mazzeo, P.L., Frontoni, E., Sclaroff, S., and Distante, C. (2022). A Predictive System to Classify Preoperative Grading of Rectal Cancer Using Radiomics Features. Image Analysis and Processing, Springer. ICIAP 2022 Workshops, ICIAP 2022, Lecture Notes in Computer Science.","DOI":"10.1007\/978-3-031-13324-4"},{"key":"ref_29","first-page":"e0181349","article-title":"Noninvasive EGFR mutation prediction","volume":"12","author":"Bakr","year":"2017","journal-title":"PLoS ONE"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"R150","DOI":"10.1088\/0031-9155\/61\/13\/R150","article-title":"Applications and limitations of radiomics","volume":"61","author":"Yip","year":"2016","journal-title":"Phys. Med. Biol."},{"key":"ref_31","first-page":"127","article-title":"Artificial intelligence in cancer imaging: Clinical challenges and applications","volume":"69","author":"Bi","year":"2019","journal-title":"CA Cancer J. Clin."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"924144","DOI":"10.3389\/fonc.2022.924144","article-title":"Explainable machine learning model to prediction EGFR mutation in lung cancer","volume":"12","author":"Yang","year":"2022","journal-title":"Front. Oncol."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"6683","DOI":"10.21037\/tcr-20-1216","article-title":"Application of CT radiomics features to predict the EGFR mutation status and therapeutic sensitivity to TKIs of advanced lung adenocarcinoma","volume":"9","author":"Yang","year":"2020","journal-title":"Transl. Cancer Res."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1576461","DOI":"10.3389\/fonc.2025.1576461","article-title":"Machine learning approaches for EGFR mutation status prediction in NSCLC: An updated systematic review","volume":"15","author":"Liu","year":"2025","journal-title":"Front. Oncol."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"5869","DOI":"10.1007\/s00330-022-08673-y","article-title":"Predicting EGFR mutation status in lung adenocarcinoma presenting as ground-glass opacity: Utilizing a radiomics model in clinical translation","volume":"32","author":"Cheng","year":"2022","journal-title":"Eur. Radiol."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"2400","DOI":"10.3390\/biomedinformatics4040129","article-title":"Uncovering the Diagnostic Power of Radiomic Feature Significance in Automated Lung Cancer Detection: An Integrative Analysis of Texture, Shape, and Intensity Contributions","volume":"4","author":"Raptis","year":"2024","journal-title":"BioMedInformatics"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"109769","DOI":"10.1016\/j.ejrad.2021.109769","article-title":"Radiomic features of plaques derived from coronary CT angiography to identify hemodynamically significant coronary stenosis using invasive fractional flow reserve as the reference standard","volume":"140","author":"Li","year":"2021","journal-title":"Eur. J. Radiol."},{"key":"ref_38","unstructured":"Lundberg, S.M., and Lee, S.I. (2017, January 4\u20139). SHAP: Unified model interpretability. Proceedings of the 31st International Conference on Neural Information Processing Systems (NeurIPS), Long Beach, CA, USA."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"e1312","DOI":"10.1002\/widm.1312","article-title":"Causability and explainability of artificial intelligence in medicine","volume":"9","author":"Holzinger","year":"2019","journal-title":"Wiley Interdiscip. Rev. Data Min. Knowl. Discov."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"272","DOI":"10.3389\/fonc.2015.00272","article-title":"Radiomic machine-learning classifiers for prognostic biomarkers of head-and-neck cancer","volume":"5","author":"Parmar","year":"2015","journal-title":"Front. Oncol."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1193","DOI":"10.1016\/S1470-2045(15)00223-5","article-title":"Global cancer surgery: Delivering safe, affordable, and timely cancer surgery","volume":"16","author":"Sullivan","year":"2015","journal-title":"Lancet Oncol."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"100400","DOI":"10.1016\/j.ejro.2022.100400","article-title":"Clinical and CT patterns to predict EGFR mutation in patients with non-small cell lung cancer: A systematic literature review and meta-analysis","volume":"9","author":"Ortiz","year":"2022","journal-title":"Eur. J. Radiol. Open"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Duranti, L., Tavecchio, L., Rolli, L., and Solli, P. (2025). New Perspectives on Lung Cancer Screening and Artificial Intelligence. Life, 15.","DOI":"10.3390\/life15030498"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1148\/radiol.2017161659","article-title":"Guidelines for Management of Incidental Pulmonary Nodules Detected on CT Images: From the Fleischner Society Radioloy 2017","volume":"284","author":"MacMahon","year":"2017","journal-title":"Radiology"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1097\/RTI.0000000000000140","article-title":"Lung Nodule and Cancer Detection in Computed Tomography Screening","volume":"30","author":"Rubin","year":"2015","journal-title":"J. Thorac. Imaging"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"100649","DOI":"10.1016\/j.ejro.2025.100649","article-title":"Ultrasound-based radiomics and machine learning for enhanced diagnosis of knee osteoarthritis: Evaluation of diagnostic accuracy, sensitivity, specificity, and predictive value","volume":"14","author":"Kiso","year":"2025","journal-title":"Eur. J. Radiol. Open"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1097\/RTI.0000000000000268","article-title":"Cardiac computed tomography radiomics: A comprehensive review on radiomic techniques","volume":"33","author":"Kellermayer","year":"2018","journal-title":"J. Thorac. Imaging"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"100594","DOI":"10.1016\/j.ejro.2024.100594","article-title":"Using machine learning to predict carotid artery symptoms from CT angiography: A radiomics and deep learning approach","volume":"13","author":"Elizabeth","year":"2024","journal-title":"Eur. J. Radiol. Open"},{"key":"ref_49","unstructured":"Seshadri, R. (2025, March 28). Github\u2014Autoviml\/Featurewiz: Use Advanced Feature Engineering Strategies and Select the Best Features from Your Data Set Fast with a Single Line of Code. Available online: https:\/\/github.com\/AutoViML\/featurewiz."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"2046","DOI":"10.1200\/JCO.2010.33.1280","article-title":"Clinical characteristics of patients with lung adenocarcinomas harboring BRAF mutations","volume":"29","author":"Paik","year":"2011","journal-title":"J. Clin. Oncol."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"664","DOI":"10.1016\/j.jtcvs.2020.05.099","article-title":"Prognostic value of epidermal growth factor receptor gene mutation in resected lung adenocarcinoma","volume":"162","author":"Deng","year":"2021","journal-title":"J. Thorac. Cardiovasc. Surg."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1016\/j.lungcan.2021.07.018","article-title":"Prognostic influence of epidermal growth factor receptor mutation and radiological ground glass appearance in patients with early-stage lung adenocarcinoma","volume":"160","author":"Aokage","year":"2021","journal-title":"Lung Cancer"},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1016\/j.annonc.2020.01.013","article-title":"TATTON: A multi-arm, phase Ib trial of osimertinib combined with selumetinib, savolitinib, or durvalumab in EGFR-mutant lung cancer","volume":"31","author":"Oxnard","year":"2020","journal-title":"Ann. Oncol."}],"container-title":["Advances in Respiratory Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2543-6031\/93\/5\/39\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T09:06:46Z","timestamp":1758877606000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2543-6031\/93\/5\/39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,26]]},"references-count":53,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["arm93050039"],"URL":"https:\/\/doi.org\/10.3390\/arm93050039","relation":{},"ISSN":["2543-6031"],"issn-type":[{"value":"2543-6031","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,26]]}}}