The diagnostic accuracy of artificial intelligence models in detecting lymph node metastases in lung cancer using endobronchial ultrasound (EBUS) images: A bivariate meta-analysis.
| Title: | The diagnostic accuracy of artificial intelligence models in detecting lymph node metastases in lung cancer using endobronchial ultrasound (EBUS) images: A bivariate meta-analysis. |
|---|---|
| Authors: | Ohannesian VA; Department of Medicine, Albert Einstein Israeli Faculty of Health Sciences, São Paulo, Brazil; Department of Radiology and Diagnostic Imaging, Hospital Israelita Albert Einstein (HIAE), São Paulo, São Paulo, Brazil; Department of Interventional Radiology, Hospital Israelita Albert Einstein (HIAE), São Paulo, SP, Brazil. Electronic address: ohannesian.victor@gmail.com.; Falcão L; Department of Medicine, Bahiana School of Medicine and Public Health (BAHIANA), Salvador, Bahia, Brazil.; Ishizuka BM; Department of Medicine, Albert Einstein Israeli Faculty of Health Sciences, São Paulo, Brazil.; Menezes IR; Department of Medicine, State University of Rio Grande do Norte, Mossoró, Rio Grande do Norte, Brazil.; Han ML; Department of Medicine, Universidade of São Paulo, São Paulo, Brazil.; Suruagy-Motta RFO; Department of Medicine, Cesmac University Center, Maceió, Brazil.; Maximiano MLB; Department of Medicine, Federal Fluminense University, Niterói, RJ, Brazil.; Cordeiro DMH; Department of Medicine, Volta Redonda University Center (UniFOA), Rio de Janeiro, Brazil.; Baptista JM; Department of Medicine, State University of Maringá, Maringá, Paraná, Brazil.; Mariussi M; Department of Interventional Radiology, Hospital Israelita Albert Einstein (HIAE), São Paulo, SP, Brazil.; Taneja AK; Department of Radiology, Baptist Health South Florida and Florida International University, Miami, USA.; Francisco Neto MJ; Department of Medicine, Albert Einstein Israeli Faculty of Health Sciences, São Paulo, Brazil; Department of Radiology and Diagnostic Imaging, Hospital Israelita Albert Einstein (HIAE), São Paulo, São Paulo, Brazil.; Garcia RG; Department of Radiology and Diagnostic Imaging, Hospital Israelita Albert Einstein (HIAE), São Paulo, São Paulo, Brazil; Department of Interventional Radiology, Hospital Israelita Albert Einstein (HIAE), São Paulo, SP, Brazil.; Jacomelli M; Bronchoscopy Section, Center of Interventional Medicine, Hospital Israelita Albert Einstein (HIAE), São Paulo, Brazil. |
| Source: | Clinical imaging [Clin Imaging] 2025 Dec; Vol. 128, pp. 110633. Date of Electronic Publication: 2025 Oct 08. |
| Publication Type: | Journal Article; Meta-Analysis; Systematic Review |
| Language: | English |
| Journal Info: | Publisher: Elsevier Country of Publication: United States NLM ID: 8911831 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1873-4499 (Electronic) Linking ISSN: 08997071 NLM ISO Abbreviation: Clin Imaging Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: [New York, NY] : Elsevier, [c1989- |
| MeSH Terms: | Lung Neoplasms*/pathology ; Lung Neoplasms*/diagnostic imaging ; Lymphatic Metastasis*/diagnostic imaging ; Endosonography*/methods ; Artificial Intelligence*; Lymph Nodes/diagnostic imaging ; Lymph Nodes/pathology ; Humans ; Sensitivity and Specificity |
| Abstract: | Purpose: This study systematically evaluated AI models for detecting lymph node metastases in lung cancer using EBUS images and assessed their role in thoracic oncology.; Materials and Methods: A systematic search following PRISMA-DTA guidelines was conducted in PubMed, Embase, Scopus, and Web of Science. Studies using AI models with cytologic or histologic analysis as the reference standard were included (PROSPERO: CRD42025635581). A bivariate random-effects model pooled sensitivity, specificity, diagnostic odds ratio (DOR), and area under the curve (AUC). AI models were categorized as CNN-A (Convolutional Neural Networks), BASM (Biomedical Application-Specific Models), AFP (Automated Frameworks and Platforms), and G-DDN (Generic Deep Neural Networks).; Results: Twenty-two studies were included. The pooled sensitivity was 0.87 (95 % CI: 0.68-0.95), specificity 0.90 (95 % CI: 0.83-0.94), AUC 0.94 (95 % CI: 0.92-0.96), and DOR 56 (95 % CI: 17-182). CNN-A showed the highest accuracy, with an AUC of 0.970 and a DOR of 182, while AFP had the lowest sensitivity (0.058) and DOR (5.125), suggesting limited clinical applicability. Likelihood ratios were LR+ 8.39 (95 % CI: 4.93-14.28) and LR- 0.15 (95 % CI: 0.06-0.39), corresponding to post-test probabilities of 74 % for positive and 5 % for negative results. Subgroup analyses highlighted performance variations, emphasizing the need for refinement and validation in diverse settings.; Conclusion: AI models demonstrate high diagnostic accuracy in detecting lymph node metastases in lung cancer using EBUS images, reinforcing their potential in clinical decision-making. Future studies should refine accuracy metrics and further evaluate CNN-A across disease contexts.; (Copyright © 2025 Elsevier Inc. All rights reserved.) |
| Competing Interests: | Declaration of competing interest The authors declare no conflicts of interest related to this work. |
| Contributed Indexing: | Keywords: Artificial intelligence; Bivariate analysis; Diagnostic accuracy; Endobronchial ultrasound; Lung cancer; Lymph node metastases |
| Entry Date(s): | Date Created: 20251015 Date Completed: 20251114 Latest Revision: 20251216 |
| Update Code: | 20260130 |
| DOI: | 10.1016/j.clinimag.2025.110633 |
| PMID: | 41092753 |
| Database: | MEDLINE |
Journal Article; Meta-Analysis; Systematic Review