Effect of a Computer-Aided Device for Detecting Gastric Neoplasms: A Multicenter, Randomized Controlled Trial - PubMed
4 days ago
- #Endoscopy
- #Gastric Neoplasms
- #Artificial Intelligence
- AI-assisted esophagogastroduodenoscopy did not significantly improve the detection rate of gastric neoplasms after pathological review (RR, 1.13; P = .25).
- AI showed improvement in detection rate based on original pathology (RR, 1.14; P = .03).
- AI reduced the number of blind spots from 2.52 to 1.07 (P < .001) but prolonged procedure and inspection time.
- No significant differences were found in relative early gastric cancer detection ratio or detection rate of intestinal metaplasia/gastric atrophy.
- Subgroup analysis suggested potential benefits of AI for less experienced endoscopists and during fatigue periods.
- AI diagnosed 100%, 91.9%, and 57.1% of pathologically confirmed gastric adenocarcinoma, high-grade, and low-grade intraepithelial neoplasia, respectively.
- Further real-world studies are needed to assess AI's adaptability in clinical settings.