Diagnostic accuracy of artificial intelligence models in the detection of gastric cancer and early gastric cancer: a systematic review and network meta-analysis
Diagnostische Genauigkeit von KI-Modellen bei der Erkennung von Magenkarzinom und frühem Magenkarzinom: systematische Übersicht und Netzwerk-Metaanalyse
Frontiers in Oncology · 12.11.2026 · 16
DOI: 10.3389/fonc.2026.1947619 ↗Auf einen Blick
59 Studien zeigen: Bei der Erkennung von Magenkarzinom hatte multimodales Deep Learning die höchsten Punktwerte. Für frühes Magenkarzinom ließ sich kein Modell klar als überlegen einstufen.
Fragestellung
Wie genau sind verschiedene KI-Modelle bei der Erkennung von Magenkarzinom und frühem Magenkarzinom?
Methode
Systematische Übersicht und Netzwerk-Metaanalyse; Suche in PubMed, Embase, Cochrane Library und Web of Science bis September 2026; Vergleich nach histopathologischem Referenzstandard.
Ergebnisse
59 Studien. GC: multimodales DL SROC 0,98, DOR 166,02; basic CNN SROC 0,95, DOR 105,29; traditionelles ML SROC 0,87, DOR 35,83. EGC: ML SROC 0,91, DOR 182,13, aber nur 3 Studien.
Einschränkungen
Hohe Heterogenität (I² > 90 % für die meisten DL-Kategorien); etwa 35 % mit hohem Risiko für Selektionsbias, 8 mit hohem Index-Test-Bias.
Schlussfolgerung der Autor:innen
Die Autoren schließen, dass KI-Modelle zur Diagnose von GC und EGC generell wirksam sind. Die Rangfolgen sind wegen Heterogenität und Bias vorsichtig zu interpretieren und als hypothesengenerierend zu sehen.
Kernaussagen
- GC: multimodales DL mit höchsten Punktwerten
- EGC: keine Modellkategorie klar überlegen
- Ergebnisse durch Heterogenität und Bias eingeschränkt
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Systematische Übersicht in der Zeitschrift Frontiers in Oncology, online erschienen am 12.11.2026. Verfasst von Nan Jiang und 7 weiteren Autor:innen. Die Arbeit nennt 95 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background
This study aimed to evaluate and rank the diagnostic accuracy of different Artificial intelligence (AI) models for GC and EGC detection across imaging modalities through a systematic review and network meta-analysis.
Methods
PubMed, Embase, Cochrane Library, and Web of Science were comprehensively searched from inception to September 2026. Studies assessing AI models against histopathological reference standards (endoscopic biopsy or surgical specimens) were included. Four main model categories (traditional machine learning (ML), basic convolutional neural network (CNN), object detection systems (DS), and multimodal deep learning (DL)) and five subcategories (ML, ResNet, Fusion, Det, CNN_other) were compared. Bayesian network meta-analysis was used to estimate pooled sensitivity, specificity, diagnostic odds ratio (DOR), superiority index, and the summary receiver operating characteristic (SROC) curves.
Results
59 studies were included. In primary analyses, for GC detection, multimodal DL showed the highest SROC area (0.98) and DOR (166.02), followed by basic CNN (SROC, 0.95; DOR, 105.29) and traditional ML (0.87; 35.83). For EGC detection, traditional ML showed the highest point estimates (SROC, 0.91; DOR, 182.13), but these were based on only three studies with wide confidence intervals, and no model category could be reliably ranked as superior. In subcategory analyses, CNN_other showed the highest GC point estimates and ML showed the highest EGC point estimates. Heterogeneity was high (I² > 90% for most DL categories). About 35% of studies had high risk of selection bias, and 8 had high risk of index-test bias, potentially inflating accuracy estimates.
Conclusions
This network meta-analysis revealed that AI models are generally effective in diagnosing GC and EGC. Multimodal DL and non-ResNet CNNs yield the highest point estimates for GC. For EGC, no model category clearly outperformed the others. Traditional ML had numerically higher point estimates, but this result was based on few studies with wide uncertainty. These rankings are limited by substantial heterogeneity, indirect comparisons, and a high prevalence of selection and index-test bias, and should be regarded as hypothesis-generating and require modality-specific validation. Prospective, multicenter head-to-head studies with standardized imaging protocols are needed to validate these findings and guide model selection. Systematic review registration https://www.crd.york.ac.uk/prospero/ , identifier CRD420261368020.
Zitieren
APA
Jiang, N., Yan, S., Liu, R., Kang, Y., Hao, Y., Cen, Y., Wang, S., & Liu, Z. (2026). Diagnostic accuracy of artificial intelligence models in the detection of gastric cancer and early gastric cancer: a systematic review and network meta-analysis. Frontiers in Oncology, 16. https://doi.org/10.3389/fonc.2026.1947619
Vancouver
Jiang N, Yan S, Liu R, Kang Y, Hao Y, Cen Y, et al. Diagnostic accuracy of artificial intelligence models in the detection of gastric cancer and early gastric cancer: a systematic review and network meta-analysis. Frontiers in Oncology. 2026;16. doi:10.3389/fonc.2026.1947619
BibTeX
@article{Jiang2026,
author = {Jiang, Nan and Yan, Shaoshuai and Liu, Ruikang and Kang, Yifan and Hao, Yuhan and Cen, Yilu and Wang, Shaoli and Liu, Zhen},
title = {Diagnostic accuracy of artificial intelligence models in the detection of gastric cancer and early gastric cancer: a systematic review and network meta-analysis},
journal = {Frontiers in Oncology},
year = {2026},
volume = {16},
doi = {10.3389/fonc.2026.1947619}
}
EUVIMED