Artificial intelligence-assisted endobronchial ultrasound for differentiating between benign and malignant thoracic lymph nodes: a meta-analysis

Abstract Background Endobronchial ultrasound (EBUS) is a widely used imaging modality for evaluating thoracic lymph nodes (LNs), particularly in the staging of lung cancer. Artificial intelligence (AI)-assisted EBUS has emerged as a promising tool to enhance diagnostic accuracy. However, its effecti...

Full description

Saved in:
Bibliographic Details
Main Authors: Fei Tang, Xian-Kui Zha, Wei Ye, Yue-Ming Wang, Ying-Feng Wu, Li-Na Wang, Li-Ping Lyu, Xiao-Mei Lyu
Format: Article
Language:English
Published: BMC 2025-07-01
Series:BMC Pulmonary Medicine
Subjects:
Online Access:https://doi.org/10.1186/s12890-025-03760-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849335394185773056
author Fei Tang
Xian-Kui Zha
Wei Ye
Yue-Ming Wang
Ying-Feng Wu
Li-Na Wang
Li-Ping Lyu
Xiao-Mei Lyu
author_facet Fei Tang
Xian-Kui Zha
Wei Ye
Yue-Ming Wang
Ying-Feng Wu
Li-Na Wang
Li-Ping Lyu
Xiao-Mei Lyu
author_sort Fei Tang
collection DOAJ
description Abstract Background Endobronchial ultrasound (EBUS) is a widely used imaging modality for evaluating thoracic lymph nodes (LNs), particularly in the staging of lung cancer. Artificial intelligence (AI)-assisted EBUS has emerged as a promising tool to enhance diagnostic accuracy. However, its effectiveness in differentiating benign from malignant thoracic LNs remains uncertain. This meta-analysis aimed to evaluate the diagnostic performance of AI-assisted EBUS compared to the pathological reference standards. Methods A systematic search was conducted across PubMed, Embase, and Web of Science for studies assessing AI-assisted EBUS in differentiating benign and malignant thoracic LNs. The reference standard included pathological confirmation via EBUS-guided transbronchial needle aspiration, surgical resection, or other histological/cytological validation methods. Sensitivity, specificity, diagnostic likelihood ratios, and diagnostic odds ratio (OR) were pooled using a random-effects model. The area under the receiver operating characteristic curve (AUROC) was summarized to evaluate diagnostic accuracy. Subgroup analyses were conducted by study design, lymph node location, and AI model type. Results Twelve studies with a total of 6,090 thoracic LNs were included. AI-assisted EBUS showed a pooled sensitivity of 0.75 (95% confidence interval [CI]: 0.60–0.86, I² = 97%) and specificity of 0.88 (95% CI: 0.83–0.92, I² = 96%). The positive and negative likelihood ratios were 6.34 (95% CI: 4.41–9.08) and 0.28 (95% CI: 0.17–0.47), respectively. The pooled diagnostic OR was 22.38 (95% CI: 11.03–45.38), and the AUROC was 0.90 (95% CI: 0.88–0.93). The subgroup analysis showed higher sensitivity but lower specificity in retrospective studies compared to prospective ones (sensitivity: 0.87 vs. 0.42; specificity: 0.80 vs. 0.93; both p < 0.001). No significant differences were found by lymph node location or AI model type. Conclusion AI-assisted EBUS shows promise in differentiating benign from malignant thoracic LNs, particularly those with high specificity. However, substantial heterogeneity and moderate sensitivity highlight the need for cautious interpretation and further validation. Systematic review registration PROSPERO CRD42025637964.
format Article
id doaj-art-19db95f1ba32417bbe4f5e46b5da6a49
institution Kabale University
issn 1471-2466
language English
publishDate 2025-07-01
publisher BMC
record_format Article
series BMC Pulmonary Medicine
spelling doaj-art-19db95f1ba32417bbe4f5e46b5da6a492025-08-20T03:45:18ZengBMCBMC Pulmonary Medicine1471-24662025-07-0125111310.1186/s12890-025-03760-4Artificial intelligence-assisted endobronchial ultrasound for differentiating between benign and malignant thoracic lymph nodes: a meta-analysisFei Tang0Xian-Kui Zha1Wei Ye2Yue-Ming Wang3Ying-Feng Wu4Li-Na Wang5Li-Ping Lyu6Xiao-Mei Lyu7Respiratory and Critical Care Medicine Department and Endoscopic Diagnosis and Treatment Center, Anhui Chest HospitalRespiratory and Critical Care Medicine Department and Endoscopic Diagnosis and Treatment Center, Anhui Chest HospitalRespiratory and Critical Care Medicine Department and Endoscopic Diagnosis and Treatment Center, Anhui Chest HospitalRespiratory and Critical Care Medicine Department and Endoscopic Diagnosis and Treatment Center, Anhui Chest HospitalRespiratory and Critical Care Medicine Department and Endoscopic Diagnosis and Treatment Center, Anhui Chest HospitalRespiratory and Critical Care Medicine Department and Endoscopic Diagnosis and Treatment Center, Anhui Chest HospitalRespiratory and Critical Care Medicine Department and Endoscopic Diagnosis and Treatment Center, Anhui Chest HospitalRespiratory and Critical Care Medicine Department and Endoscopic Diagnosis and Treatment Center, Anhui Chest HospitalAbstract Background Endobronchial ultrasound (EBUS) is a widely used imaging modality for evaluating thoracic lymph nodes (LNs), particularly in the staging of lung cancer. Artificial intelligence (AI)-assisted EBUS has emerged as a promising tool to enhance diagnostic accuracy. However, its effectiveness in differentiating benign from malignant thoracic LNs remains uncertain. This meta-analysis aimed to evaluate the diagnostic performance of AI-assisted EBUS compared to the pathological reference standards. Methods A systematic search was conducted across PubMed, Embase, and Web of Science for studies assessing AI-assisted EBUS in differentiating benign and malignant thoracic LNs. The reference standard included pathological confirmation via EBUS-guided transbronchial needle aspiration, surgical resection, or other histological/cytological validation methods. Sensitivity, specificity, diagnostic likelihood ratios, and diagnostic odds ratio (OR) were pooled using a random-effects model. The area under the receiver operating characteristic curve (AUROC) was summarized to evaluate diagnostic accuracy. Subgroup analyses were conducted by study design, lymph node location, and AI model type. Results Twelve studies with a total of 6,090 thoracic LNs were included. AI-assisted EBUS showed a pooled sensitivity of 0.75 (95% confidence interval [CI]: 0.60–0.86, I² = 97%) and specificity of 0.88 (95% CI: 0.83–0.92, I² = 96%). The positive and negative likelihood ratios were 6.34 (95% CI: 4.41–9.08) and 0.28 (95% CI: 0.17–0.47), respectively. The pooled diagnostic OR was 22.38 (95% CI: 11.03–45.38), and the AUROC was 0.90 (95% CI: 0.88–0.93). The subgroup analysis showed higher sensitivity but lower specificity in retrospective studies compared to prospective ones (sensitivity: 0.87 vs. 0.42; specificity: 0.80 vs. 0.93; both p < 0.001). No significant differences were found by lymph node location or AI model type. Conclusion AI-assisted EBUS shows promise in differentiating benign from malignant thoracic LNs, particularly those with high specificity. However, substantial heterogeneity and moderate sensitivity highlight the need for cautious interpretation and further validation. Systematic review registration PROSPERO CRD42025637964.https://doi.org/10.1186/s12890-025-03760-4Artificial intelligenceEndobronchial ultrasoundMalignancyMeta-analysisThoracic lymph node
spellingShingle Fei Tang
Xian-Kui Zha
Wei Ye
Yue-Ming Wang
Ying-Feng Wu
Li-Na Wang
Li-Ping Lyu
Xiao-Mei Lyu
Artificial intelligence-assisted endobronchial ultrasound for differentiating between benign and malignant thoracic lymph nodes: a meta-analysis
BMC Pulmonary Medicine
Artificial intelligence
Endobronchial ultrasound
Malignancy
Meta-analysis
Thoracic lymph node
title Artificial intelligence-assisted endobronchial ultrasound for differentiating between benign and malignant thoracic lymph nodes: a meta-analysis
title_full Artificial intelligence-assisted endobronchial ultrasound for differentiating between benign and malignant thoracic lymph nodes: a meta-analysis
title_fullStr Artificial intelligence-assisted endobronchial ultrasound for differentiating between benign and malignant thoracic lymph nodes: a meta-analysis
title_full_unstemmed Artificial intelligence-assisted endobronchial ultrasound for differentiating between benign and malignant thoracic lymph nodes: a meta-analysis
title_short Artificial intelligence-assisted endobronchial ultrasound for differentiating between benign and malignant thoracic lymph nodes: a meta-analysis
title_sort artificial intelligence assisted endobronchial ultrasound for differentiating between benign and malignant thoracic lymph nodes a meta analysis
topic Artificial intelligence
Endobronchial ultrasound
Malignancy
Meta-analysis
Thoracic lymph node
url https://doi.org/10.1186/s12890-025-03760-4
work_keys_str_mv AT feitang artificialintelligenceassistedendobronchialultrasoundfordifferentiatingbetweenbenignandmalignantthoraciclymphnodesametaanalysis
AT xiankuizha artificialintelligenceassistedendobronchialultrasoundfordifferentiatingbetweenbenignandmalignantthoraciclymphnodesametaanalysis
AT weiye artificialintelligenceassistedendobronchialultrasoundfordifferentiatingbetweenbenignandmalignantthoraciclymphnodesametaanalysis
AT yuemingwang artificialintelligenceassistedendobronchialultrasoundfordifferentiatingbetweenbenignandmalignantthoraciclymphnodesametaanalysis
AT yingfengwu artificialintelligenceassistedendobronchialultrasoundfordifferentiatingbetweenbenignandmalignantthoraciclymphnodesametaanalysis
AT linawang artificialintelligenceassistedendobronchialultrasoundfordifferentiatingbetweenbenignandmalignantthoraciclymphnodesametaanalysis
AT lipinglyu artificialintelligenceassistedendobronchialultrasoundfordifferentiatingbetweenbenignandmalignantthoraciclymphnodesametaanalysis
AT xiaomeilyu artificialintelligenceassistedendobronchialultrasoundfordifferentiatingbetweenbenignandmalignantthoraciclymphnodesametaanalysis