# Transforming Gastric Biopsy Diagnostics: Integrating Omics Technologies and Artificial Intelligence

## TL;DR

This paper explores how combining omics technologies and AI can improve gastric biopsy diagnostics, leading to more accurate disease classification and better patient outcomes.

## Contribution

The paper introduces the integration of multi-omics and AI as a novel approach to modernize gastric biopsy diagnostics.

## Key findings

- Multi-omics profiling improves understanding of disease mechanisms and classification.
- AI applications enhance lesion detection and classification in gastric diagnostics.
- Combining AI and omics data can lead to precision gastroenterology but requires addressing technical and regulatory challenges.

## Abstract

Background: Gastric biopsy remains central to diagnosing Helicobacter pylori infection, autoimmune gastritis, intestinal metaplasia, dysplasia, and gastric cancer. However, morphology-based assessment is limited by interobserver variability, sampling constraints, and an incomplete ability to capture molecular heterogeneity and predict progression. Objective: This mini review summarizes how multi-omics technologies and artificial intelligence (AI) are modernizing gastric biopsy diagnostics, enabling precision classification, risk stratification, and workflow improvement. Methods: A narrative synthesis was undertaken across key literature on gastric pathology, multi-omics (genomics, transcriptomics, epigenomics, proteomics, lipidomics, metabolomics, microbiomics, and spatial approaches), and AI in endoscopy and computational pathology. Results: Multi-omics profiling enhances mechanistic understanding and refines disease classification by capturing clonal evolution, pathway dysregulation, immune–microenvironment interactions, and metabolic remodeling, with potential for biomarker discovery and therapy prediction. AI applications demonstrate strong performance across the gastric diagnostic pathway, including improved lesion detection during endoscopy, reduced miss rates, lesion segmentation, classification of precancerous conditions, H. pylori recognition, and near-expert histopathology classification. Evidence from systematic reviews supports robust diagnostic accuracy, while prospective studies highlight real-time feasibility. Conclusions: Integrating AI with multi-omics is shifting gastric biopsy from descriptive histology toward data-driven precision gastroenterology. Key barriers include dataset quality, standardization, interpretability, cost, and regulatory and ethical governance; addressing these will be essential for routine clinical adoption.