Comparative diagnostic accuracy of image-enhanced endoscopy modalities and artificial intelligence-assisted endoscopy for gastric intestinal metaplasia and gastric dysplasia: protocol for a systematic review and diagnostic test network meta-analysis.

Clinical Snapshot

Key Findings

• P Value: Not yet available (protocol stage)

• Effect Size: Not yet available (protocol stage)

• Primary Outcome: No results available — this is a protocol paper. The planned co-primary outcomes are sensitivity and specificity for detection of gastric intestinal metaplasia (GIM) and gastric dysplasia, to be estimated jointly via hierarchical bivariate diagnostic test network meta-analysis.

• Nnt Or Sensitivity: Planned diagnostic accuracy measures: sensitivity, specificity (co-primary); diagnostic odds ratio (DOR) and AUC-ROC (secondary). No numerical estimates available at protocol stage.

• Confidence Interval: Not yet available (protocol stage)

Clinical Application

The planned review is feasible given the growing body of diagnostic accuracy literature on NBI, BLI, LCI, and AI-assisted endoscopy. However, the network structure may be sparse for some modality comparisons, particularly for newer AI systems and less-studied IEE technologies such as iScan. The bivariate network meta-analysis approach requires substantial statistical expertise and adequate numbers of comparative studies to yield stable estimates. Gastric cancer incidence in Australia is relatively low compared to East Asia (approximately 5–6 per 100,000), but GIM surveillance remains clinically relevant in high-risk groups including patients of East Asian, Eastern European, and South American background, and those with confirmed H. pylori infection or atrophic gastritis. The RACGP and Gastroenterological Society of Australia (GESA) do not currently mandate routine GIM surveillance endoscopy in the general population. NBI endoscopy systems (Olympus) are widely available in Australian tertiary endoscopy units; BLI and LCI (Fujifilm) are increasingly available. AI-assisted endoscopy systems are not yet TGA-approved or PBS-subsidised for routine GIM detection in Australia. The completed review could inform future GESA guideline updates and support TGA/MSAC submissions for AI-assisted endoscopy reimbursement. The findings will be most directly applicable to Australian gastroenterologists managing high-risk surveillance populations. Adult patients undergoing upper gastrointestinal endoscopy for surveillance or detection of gastric premalignant conditions, particularly those with known Helicobacter pylori infection history, atrophic gastritis, or family history of gastric cancer. Most directly applicable to populations with elevated GIM prevalence.

Abstract

INTRODUCTION: Gastric intestinal metaplasia (GIM) and gastric dysplasia are critical precursors in the Correa cascade of gastric carcinogenesis. Although multiple image-enhanced endoscopy (IEE) modalities and artificial intelligence (AI)-assisted systems have been developed to improve their detection, the comparative diagnostic accuracy of these technologies remains unclear. Direct comparative studies are limited and conventional pairwise meta-analyses do not provide a coherent framework for comparing multiple diagnostic technologies. METHODS AND ANALYSIS: This protocol follows the Preferred Reporting Items for Systematic Review and Meta-Analysis Protocols (PRISMA-P) and PRISMA-Network Meta-Analysis guidelines. We will search MEDLINE (Ovid), Embase (Ovid), the Cochrane Central Register of Controlled Trials (CENTRAL; Cochrane Library/Wiley), Web of Science Core Collection (Clarivate), Scopus (Elsevier), ClinicalTrials.gov and the WHO International Clinical Trials Registry Platform from inception, without date or language restrictions. Eligible studies will be diagnostic accuracy studies evaluating IEE modalities (including narrow-band imaging with or without magnification, blue laser imaging, linked colour imaging and iScan) or AI-assisted endoscopy against histology. Comparative studies will form the primary evidence base for the diagnostic test network meta-analysis; single-arm studies will be summarised separately and will not contribute to the primary network estimates. The coprimary diagnostic parameters will be sensitivity and specificity for GIM and dysplasia. These will be analysed jointly using a hierarchical bivariate diagnostic test network meta-analysis with binomial likelihoods and correlated random effects. Diagnostic OR and area under the receiver operating characteristic curve will be treated as secondary summary measures. Two reviewers will independently screen, extract data and apply Quality Assessment of Diagnostic Accuracy Studies 2. Heterogeneity, transitivity and inconsistency will be assessed using prespecified clinical and methodological effect modifiers, model-based diagnostics and sensitivity analyses. The certainty of evidence will be assessed using Confidence in Network Meta-Analysis, with interpretation adapted to diagnostic accuracy outcomes. ETHICS AND DISSEMINATION: This study does not require ethical approval as it relies on secondary analysis of published literature. Findings will be disseminated through peer-reviewed publication and conference presentations. PROSPERO REGISTRATION NUMBER: CRD420261363078.

References

1. 1.Xia, R., Yang, Y., & Zhang, W. (2026). Comparative diagnostic accuracy of image-enhanced endoscopy modalities and artificial intelligence-assisted endoscopy for gastric intestinal metaplasia and gastric dysplasia: protocol for a systematic review and diagnostic test network meta-analysis. BMJ Open. https://doi.org/10.1136/bmjopen-2026-121644