AI and Cancer Research ── Gastric ── 2026-10-18

Meta-analysis of deep learning on H&E pathology images to predict MSI in gastric cancer. Four databases were searched and ten studies included; seven datasets from six studies entered the primary synthesis. Methods: PROSPERO registration, QUADAS-2 bias assessment, bivariate random-effects model. Pooled sensitivity 0.78, specificity 0.85, AUC 0.89. Hospital cohorts had higher sensitivity than TCGA cohorts, 0.86 vs 0.71, but few studies and heterogeneity limit this. Clinical utility needs multicentre, external and prospective confirmation. — Image abstract — the whole article on one page (click to enlarge)

1 Gastric papers. Lead: Diagnostic accuracy of deep learning for microsatellite instability prediction in gastric cancer: A systematic review and meta-analysis

Journals covered and how papers are chosen: see the index

Gastric cancer: treatment, trials and AI

Diagnostic accuracy of deep learning for microsatellite instability prediction in gastric cancer: A systematic review and meta-analysis
medRxiv · 2026-10-15 · Evidence: Systematic review and meta-analysis of diagnostic accuracy studies
Abstract
Deep learning (DL) applied to haematoxylin and eosin (H&E)-stained pathology images can predict microsatellite instability (MSI) in gastric cancer (GC). We evaluated its diagnostic accuracy and discriminative performance. PubMed, Embase, Cochrane Library and Web of Science were searched for studies applying DL to H&E images for MSI prediction in GC. The protocol was prospectively registered in PROSPERO (CRD420261503140). Risk of bias was assessed with QUADAS-2. Pooled sensitivity and specificity were estimated with a bivariate random-effects model, with subgroup analyses by validation strategy and data source; slide-level areas under the curve (AUCs) were pooled after logit transformation. Prespecified scenario analyses assessed robustness. Ten studies were included; seven independent datasets from six studies entered the primary synthesis. Pooled sensitivity, specificity and summary receiver operating characteristic AUC were 0.78 (95% CI 0.63–0.88), 0.85 (95% CI 0.77–0.90) and 0.89 (95% CI 0.86–0.91); nine studies contributed to the secondary AUC synthesis (pooled AUC 0.85, 95% CI 0.80–0.89). Hospital-derived cohorts showed numerically higher sensitivity (0.86) and diagnostic odds ratio (39.8) than TCGA-derived cohorts (0.71 and 11.5), but subgroup differences were limited by the small number of studies and substantial heterogeneity. DL models show good diagnostic accuracy for MSI prediction in GC, but clinical utility still requires confirmation in standardised multicentre, independent external and prospective studies.
Journal IF: unknown (could not be matched)
Reference: Du Y, Liao H, Li J, He Y, Di J. Diagnostic accuracy of deep learning for microsatellite instability prediction in gastric cancer: A systematic review and meta-analysis. medRxiv. 2026 Oct 15 [Epub ahead of print]. doi:10.64898/2026.10.12.26365351.
Checked: Abstract only

← Back to this issue