{"title":"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。","authors":"Nehemias Guevara Rodriguez, Noemy Coreas Mercado, Kumar Panjiyar, Ranju Kunwor","doi":"10.3389/fonc.2025.1634694","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>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.</p><p><strong>Methods: </strong>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.</p><p><strong>Results: </strong>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).</p><p><strong>Conclusion: </strong>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.</p><p><strong>Systematic review registration: </strong>https://www.crd.york.ac.uk/prospero/, identifier CRD420251048243.</p>","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":"{\"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\":\"<p><strong>Background: </strong>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.</p><p><strong>Methods: </strong>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.</p><p><strong>Results: </strong>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).</p><p><strong>Conclusion: </strong>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.</p><p><strong>Systematic review registration: </strong>https://www.crd.york.ac.uk/prospero/, identifier CRD420251048243.</p>\",\"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}","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}
Artificial intelligence versus radiologists in predicting lung cancer treatment response: a systematic review and meta-analysis.
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.
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.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
