Machine learning approaches for EGFR mutation status prediction in NSCLC: an updated systematic review

BackgroundWith the rapid advances in artificial intelligence—particularly convolutional neural networks—researchers now exploit CT, PET/CT and other imaging modalities to predict epidermal growth factor receptor (EGFR) mutation status in non-small-cell lung cancer (NSCLC) non-invasively, rapidly and...

Full description

Saved in:
Bibliographic Details
Main Authors: Liu Haixian, Pang Shu, Li Zhao, Lu Chunfeng, Li Lun
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-07-01
Series:Frontiers in Oncology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fonc.2025.1576461/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849428000621199360
author Liu Haixian
Liu Haixian
Pang Shu
Pang Shu
Li Zhao
Li Zhao
Lu Chunfeng
Lu Chunfeng
Li Lun
author_facet Liu Haixian
Liu Haixian
Pang Shu
Pang Shu
Li Zhao
Li Zhao
Lu Chunfeng
Lu Chunfeng
Li Lun
author_sort Liu Haixian
collection DOAJ
description BackgroundWith the rapid advances in artificial intelligence—particularly convolutional neural networks—researchers now exploit CT, PET/CT and other imaging modalities to predict epidermal growth factor receptor (EGFR) mutation status in non-small-cell lung cancer (NSCLC) non-invasively, rapidly and repeatably. End-to-end deep-learning models simultaneously perform feature extraction and classification, capturing not only traditional radiomic signatures such as tumour density and texture but also peri-tumoural micro-environmental cues, thereby offering a higher theoretical performance ceiling than hand-crafted radiomics coupled with classical machine learning. Nevertheless, the need for large, well-annotated datasets, the domain shifts introduced by heterogeneous scanning protocols and preprocessing pipelines, and the “black-box” nature of neural networks all hinder clinical adoption. To address fragmented evidence and scarce external validation, we conducted a systematic review to appraise the true performance of deep-learning and radiomics models for EGFR prediction and to identify barriers to clinical translation, thereby establishing a baseline for forthcoming multicentre prospective studies.MethodsFollowing PRISMA 2020, we searched PubMed, Web of Science and IEEE Xplore for studies published between 2018 and 2024. Fifty-nine original articles met the inclusion criteria. QUADAS-2 was applied to the eight studies that developed models using real-world clinical data, and details of external validation strategies and performance metrics were extracted systematically.ResultsThe pooled internal area under the curve (AUC) was 0.78 for radiomics–machine-learning models and 0.84 for deep-learning models. Only 17 studies (29%) reported independent external validation, where the mean AUC fell to 0.77, indicating a marked domain-shift effect. QUADAS-2 showed that 31% of studies had high risk of bias in at least one domain, most frequently in Index Test and Patient Selection.ConclusionAlthough deep-learning models achieved the best internal performance, their reliance on single-centre data, the paucity of external validation and limited code availability preclude their use as stand-alone clinical decision tools. Future work should involve multicentre prospective designs, federated learning, decision-curve analysis and open sharing of models and data to verify generalisability and facilitate clinical integration.
format Article
id doaj-art-c1a37ff849ee41b4b3b5cd2e0c41caee
institution Kabale University
issn 2234-943X
language English
publishDate 2025-07-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Oncology
spelling doaj-art-c1a37ff849ee41b4b3b5cd2e0c41caee2025-08-20T03:28:50ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2025-07-011510.3389/fonc.2025.15764611576461Machine learning approaches for EGFR mutation status prediction in NSCLC: an updated systematic reviewLiu Haixian0Liu Haixian1Pang Shu2Pang Shu3Li Zhao4Li Zhao5Lu Chunfeng6Lu Chunfeng7Li Lun8Respiratory and Critical Care Medicine Center, Weifang People’s Hospital, Weifang, ChinaThe First Affiliated Hospital, Shandong Second Medical University, Weifang, ChinaThe First Affiliated Hospital, Shandong Second Medical University, Weifang, ChinaPrecision Pathology Diagnosis Center, Weifang People’s Hospital, Weifang, ChinaRespiratory and Critical Care Medicine Center, Weifang People’s Hospital, Weifang, ChinaThe First Affiliated Hospital, Shandong Second Medical University, Weifang, ChinaThe First Affiliated Hospital, Shandong Second Medical University, Weifang, ChinaCritical care medicine, Weifang People’s Hospital, Weifang, ChinaCollege of Mechanical Engineering and Automation, Weifang University, Weifang, ChinaBackgroundWith the rapid advances in artificial intelligence—particularly convolutional neural networks—researchers now exploit CT, PET/CT and other imaging modalities to predict epidermal growth factor receptor (EGFR) mutation status in non-small-cell lung cancer (NSCLC) non-invasively, rapidly and repeatably. End-to-end deep-learning models simultaneously perform feature extraction and classification, capturing not only traditional radiomic signatures such as tumour density and texture but also peri-tumoural micro-environmental cues, thereby offering a higher theoretical performance ceiling than hand-crafted radiomics coupled with classical machine learning. Nevertheless, the need for large, well-annotated datasets, the domain shifts introduced by heterogeneous scanning protocols and preprocessing pipelines, and the “black-box” nature of neural networks all hinder clinical adoption. To address fragmented evidence and scarce external validation, we conducted a systematic review to appraise the true performance of deep-learning and radiomics models for EGFR prediction and to identify barriers to clinical translation, thereby establishing a baseline for forthcoming multicentre prospective studies.MethodsFollowing PRISMA 2020, we searched PubMed, Web of Science and IEEE Xplore for studies published between 2018 and 2024. Fifty-nine original articles met the inclusion criteria. QUADAS-2 was applied to the eight studies that developed models using real-world clinical data, and details of external validation strategies and performance metrics were extracted systematically.ResultsThe pooled internal area under the curve (AUC) was 0.78 for radiomics–machine-learning models and 0.84 for deep-learning models. Only 17 studies (29%) reported independent external validation, where the mean AUC fell to 0.77, indicating a marked domain-shift effect. QUADAS-2 showed that 31% of studies had high risk of bias in at least one domain, most frequently in Index Test and Patient Selection.ConclusionAlthough deep-learning models achieved the best internal performance, their reliance on single-centre data, the paucity of external validation and limited code availability preclude their use as stand-alone clinical decision tools. Future work should involve multicentre prospective designs, federated learning, decision-curve analysis and open sharing of models and data to verify generalisability and facilitate clinical integration.https://www.frontiersin.org/articles/10.3389/fonc.2025.1576461/fullartificial intelligenceNon-small cell lung cancer (NSCLC)EGFR mutationdeep learningmedical imaging
spellingShingle Liu Haixian
Liu Haixian
Pang Shu
Pang Shu
Li Zhao
Li Zhao
Lu Chunfeng
Lu Chunfeng
Li Lun
Machine learning approaches for EGFR mutation status prediction in NSCLC: an updated systematic review
Frontiers in Oncology
artificial intelligence
Non-small cell lung cancer (NSCLC)
EGFR mutation
deep learning
medical imaging
title Machine learning approaches for EGFR mutation status prediction in NSCLC: an updated systematic review
title_full Machine learning approaches for EGFR mutation status prediction in NSCLC: an updated systematic review
title_fullStr Machine learning approaches for EGFR mutation status prediction in NSCLC: an updated systematic review
title_full_unstemmed Machine learning approaches for EGFR mutation status prediction in NSCLC: an updated systematic review
title_short Machine learning approaches for EGFR mutation status prediction in NSCLC: an updated systematic review
title_sort machine learning approaches for egfr mutation status prediction in nsclc an updated systematic review
topic artificial intelligence
Non-small cell lung cancer (NSCLC)
EGFR mutation
deep learning
medical imaging
url https://www.frontiersin.org/articles/10.3389/fonc.2025.1576461/full
work_keys_str_mv AT liuhaixian machinelearningapproachesforegfrmutationstatuspredictioninnsclcanupdatedsystematicreview
AT liuhaixian machinelearningapproachesforegfrmutationstatuspredictioninnsclcanupdatedsystematicreview
AT pangshu machinelearningapproachesforegfrmutationstatuspredictioninnsclcanupdatedsystematicreview
AT pangshu machinelearningapproachesforegfrmutationstatuspredictioninnsclcanupdatedsystematicreview
AT lizhao machinelearningapproachesforegfrmutationstatuspredictioninnsclcanupdatedsystematicreview
AT lizhao machinelearningapproachesforegfrmutationstatuspredictioninnsclcanupdatedsystematicreview
AT luchunfeng machinelearningapproachesforegfrmutationstatuspredictioninnsclcanupdatedsystematicreview
AT luchunfeng machinelearningapproachesforegfrmutationstatuspredictioninnsclcanupdatedsystematicreview
AT lilun machinelearningapproachesforegfrmutationstatuspredictioninnsclcanupdatedsystematicreview