Artificial intelligence versus radiologists in predicting lung cancer treatment response: a systematic review and meta-analysis.

IF 3.5 3区医学 Q2 ONCOLOGY

Frontiers in Oncology Pub Date : 2025-10-08 eCollection Date: 2025-01-01 DOI:10.3389/fonc.2025.1634694

Nehemias Guevara Rodriguez, Noemy Coreas Mercado, Kumar Panjiyar, Ranju Kunwor

{"title":"Artificial intelligence versus radiologists in predicting lung cancer treatment response: a systematic review and meta-analysis.","authors":"Nehemias Guevara Rodriguez, Noemy Coreas Mercado, Kumar Panjiyar, Ranju Kunwor","doi":"10.3389/fonc.2025.1634694","DOIUrl":null,"url":null,"abstract":"Background: Artificial intelligence (AI) has emerged as a promising adjunct to radiologist interpretation in oncology imaging. This systematic review and meta-analysis compares the diagnostic performance of AI systems versus radiologists in predicting lung cancer treatment response, focusing solely on treatment response rather than diagnosis.Methods: We systematically searched PubMed, Embase, Scopus, Web of Science, and the Cochrane Library from inception to March 31, 2025; Google Scholar and CINAHL were used for citation chasing/grey literature. The review protocol was prospectively registered in PROSPERO (CRD420251048243). Studies directly comparing AI-based imaging analysis with radiologist interpretation for predicting treatment response in lung cancer were included. Two reviewers extracted data independently (Cohen's κ = 0.87). We pooled sensitivity, specificity, accuracy, and risk differences using DerSimonian-Laird random-effects models. Heterogeneity (I²), threshold effects (Spearman correlation), and publication bias (funnel plots, Egger's test) were assessed. Subgroups were prespecified by imaging modality and therapy class.Results: Eleven retrospective studies (n = 6,615) were included. Pooled sensitivity for AI was 0.9 (95% CI: 0.8-0.9; I² = 58%), specificity 0.8 (95% CI: 0.8-0.9; I² = 52%), and accuracy 0.9 (95% CI: 0.8-0.9; pooled OR = 1.4, 95% CI: 1.2-1.7). Risk difference favored AI by 0.06 for sensitivity and 0.04 for specificity. AI's advantage was most apparent in CT and PET/CT, with smaller/non-significant gains in MRI. Egger's test suggested no significant publication bias (p = 0.21).Conclusion: AI demonstrates modest but statistically significant superiority over radiologists in predicting lung cancer treatment response, particularly in CT and PET/CT imaging. However, generalizability is limited by retrospective study dominance, incomplete demographic reporting, lack of regulatory clearance, and minimal cost-effectiveness evaluation. Prospective, multicenter trials incorporating explainable AI (e.g., SHAP, Grad-CAM), equity assessments, and formal economic analyses are needed.Systematic review registration: https://www.crd.york.ac.uk/prospero/, identifier CRD420251048243.","PeriodicalId":12482,"journal":{"name":"Frontiers in Oncology","volume":"15 ","pages":"1634694"},"PeriodicalIF":3.5000,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12540067/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers in Oncology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.3389/fonc.2025.1634694","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"ONCOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Background: Artificial intelligence (AI) has emerged as a promising adjunct to radiologist interpretation in oncology imaging. This systematic review and meta-analysis compares the diagnostic performance of AI systems versus radiologists in predicting lung cancer treatment response, focusing solely on treatment response rather than diagnosis.

Methods: We systematically searched PubMed, Embase, Scopus, Web of Science, and the Cochrane Library from inception to March 31, 2025; Google Scholar and CINAHL were used for citation chasing/grey literature. The review protocol was prospectively registered in PROSPERO (CRD420251048243). Studies directly comparing AI-based imaging analysis with radiologist interpretation for predicting treatment response in lung cancer were included. Two reviewers extracted data independently (Cohen's κ = 0.87). We pooled sensitivity, specificity, accuracy, and risk differences using DerSimonian-Laird random-effects models. Heterogeneity (I²), threshold effects (Spearman correlation), and publication bias (funnel plots, Egger's test) were assessed. Subgroups were prespecified by imaging modality and therapy class.

Results: Eleven retrospective studies (n = 6,615) were included. Pooled sensitivity for AI was 0.9 (95% CI: 0.8-0.9; I² = 58%), specificity 0.8 (95% CI: 0.8-0.9; I² = 52%), and accuracy 0.9 (95% CI: 0.8-0.9; pooled OR = 1.4, 95% CI: 1.2-1.7). Risk difference favored AI by 0.06 for sensitivity and 0.04 for specificity. AI's advantage was most apparent in CT and PET/CT, with smaller/non-significant gains in MRI. Egger's test suggested no significant publication bias (p = 0.21).

Conclusion: AI demonstrates modest but statistically significant superiority over radiologists in predicting lung cancer treatment response, particularly in CT and PET/CT imaging. However, generalizability is limited by retrospective study dominance, incomplete demographic reporting, lack of regulatory clearance, and minimal cost-effectiveness evaluation. Prospective, multicenter trials incorporating explainable AI (e.g., SHAP, Grad-CAM), equity assessments, and formal economic analyses are needed.

Systematic review registration: https://www.crd.york.ac.uk/prospero/, identifier CRD420251048243.

查看原文本刊更多论文

人工智能与放射科医生预测肺癌治疗反应：系统回顾和荟萃分析。

背景：人工智能（AI）已经成为肿瘤学影像中放射科医生解释的一个有前途的辅助手段。本系统综述和荟萃分析比较了人工智能系统与放射科医生在预测肺癌治疗反应方面的诊断性能，仅关注治疗反应而不是诊断。方法：系统检索PubMed、Embase、Scopus、Web of Science、Cochrane Library自成立至2025年3月31日的数据库；引用追踪/灰色文献使用谷歌Scholar和CINAHL。该审查方案在PROSPERO中前瞻性注册（CRD420251048243）。直接比较人工智能成像分析与放射科医生解释预测肺癌治疗反应的研究包括在内。两位审稿人独立提取数据（Cohen’s κ = 0.87）。我们使用dersimonan - laird随机效应模型汇总敏感性、特异性、准确性和风险差异。评估异质性（I²）、阈值效应（Spearman相关）和发表偏倚（漏斗图、Egger检验）。亚组按影像学方式和治疗类别预先指定。结果：纳入11项回顾性研究（n = 6615）。AI的合并敏感性为0.9 (95% CI: 0.8-0.9; I²= 58%)，特异性为0.8 (95% CI: 0.8-0.9; I²= 52%)，准确度为0.9 （95% CI: 0.8-0.9；合并OR = 1.4, 95% CI: 1.2-1.7）。AI在敏感性和特异性方面的风险差异分别为0.06和0.04。AI的优势在CT和PET/CT上最为明显，在MRI上的优势较小/不显著。Egger检验未发现显著的发表偏倚（p = 0.21）。结论：人工智能在预测肺癌治疗反应方面比放射科医生表现出适度但有统计学意义的优势，特别是在CT和PET/CT成像方面。然而，由于回顾性研究的优势、不完整的人口统计报告、缺乏监管许可和最小的成本效益评估，通用性受到限制。需要前瞻性、多中心试验，包括可解释的人工智能（例如，SHAP、Grad-CAM）、公平评估和正式的经济分析。系统综述注册：https://www.crd.york.ac.uk/prospero/，标识符CRD420251048243。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Frontiers in Oncology Biochemistry, Genetics and Molecular Biology-Cancer Research

CiteScore

6.20

自引率

10.60%

发文量

6641

审稿时长

14 weeks

期刊介绍： Cancer Imaging and Diagnosis is dedicated to the publication of results from clinical and research studies applied to cancer diagnosis and treatment. The section aims to publish studies from the entire field of cancer imaging: results from routine use of clinical imaging in both radiology and nuclear medicine, results from clinical trials, experimental molecular imaging in humans and small animals, research on new contrast agents in CT, MRI, ultrasound, publication of new technical applications and processing algorithms to improve the standardization of quantitative imaging and image guided interventions for the diagnosis and treatment of cancer.