NSCLC EGFR Mutation Prediction via Random Forest Model: A Clinical–CT–Radiomics Integration Approach
Authors:
- Anass BenfaresABAnass Benfares
- Badreddine AlamiBABadreddine Alami
- Sara BoukansaSBSara Boukansa
- Mamoun QjidaaMQMamoun Qjidaa
- Ikram BenomarIBIkram Benomar
- Mounia SerrajMSMounia Serraj
- Ahmed LakhssassiALAhmed Lakhssassi
- Mohammed Ouazzani JamilMJMohammed Ouazzani Jamil
- Mustapha MaaroufiMMMustapha Maaroufi
- Hassan QjidaaHQHassan Qjidaa
Open Access
- 26 September 2025
- journal article
- research article
- Published by MDPI AG in Advances in Respiratory Medicine
- Vol. 93 (5) , 39
Abstract
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: 0.81–1.00) under stratified five-fold cross-validation, with an accuracy of 0.88 ± 0.03. Subgroup analysis showed that EGFR-WT had a performance of precision 0.93 ± 0.04, recall 0.92 ± 0.03, F1-score 0.91 ± 0.02, and EGFR-Mutant had a performance of precision 0.76 ± 0.05, recall 0.71 ± 0.05, F1-score 0.68 ± 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.Keywords
This publication has 52 references indexed in Scilit:
- Grading and Staging of Bladder Tumors Using Radiomics Analysis in Magnetic Resonance Imaging2024
- A Predictive System to Classify Preoperative Grading of Rectal Cancer Using Radiomics Features2022
- Predicting EGFR mutation status in lung adenocarcinoma presenting as ground-glass opacity: utilizing radiomics model in clinical translationEuropean Radiology, 2022
- Prevalence of Epidermal Growth Factor Receptor Exon 20 Insertion Mutations in Non-small-Cell Lung Cancer in Europe: A Pragmatic Literature Review and Meta-analysisTargeted Oncology, 2022
- Clinical and CT patterns to predict EGFR mutation in patients with non-small cell lung cancer: A systematic literature review and meta-analysisEuropean Journal of Radiology Open, 2022
- Radiomic features of plaques derived from coronary CT angiography to identify hemodynamically significant coronary stenosis, using invasive FFR as the reference standardEuropean Journal of Radiology, 2021
- TATTON: a multi-arm, phase Ib trial of osimertinib combined with selumetinib, savolitinib, or durvalumab in EGFR-mutant lung cancerAnnals of Oncology, 2020
- Causability and explainability of artificial intelligence in medicineWIREs Data Mining and Knowledge Discovery, 2019
- Radiomics: Extracting more information from medical images using advanced feature analysisEuropean Journal of Cancer, 2012
- Efficacy of Gefitinib, an Inhibitor of the Epidermal Growth Factor Receptor Tyrosine Kinase, in Symptomatic Patients With Non–Small Cell Lung CancerJAMA, 2003