Your browser doesn't support javascript.
loading
Artificial Intelligence ⁃ based Colorectal Polyp Diagnostic System Can Increase the Detection Rate of Polyps: A Prospective Randomized Controlled Study / 胃肠病学
Article de Zh | WPRIM | ID: wpr-1016121
Bibliothèque responsable: WPRO
ABSTRACT
Colonoscopy with polypectomy significantly reduces the incidence of colorectal cancer and cancer - related mortality. However, a pooled miss rate of 22% for polyps was documented. Aims: To explore the clinical application value of an artificial intelligence (AI)-based colorectal polyp diagnostic system for polyp detection. Methods: A total of 400 patients who underwent colonoscopy in the First Affiliated Hospital of Soochow University from September to November 2021 were selected according to the inclusion and exclusion criteria and were randomly divided into two groups: one group received routine colonoscopy, and the other group received AI system assisted colonoscopy. There were 200 cases in each group. The Boston Bowel Preparation Scale (BBPS) was used to evaluate bowel preparation quality. The primary outcome was polyp detection rate (PDR), and the secondary outcome was polyps per colonoscopy (PPC). Results: AI system significantly increased PDR and PPC (37.0% vs. 23.0%, 0.775 vs. 0.495, all P0.05). The bowel preparation quality was classified as“poor”(BBPS 0-5 points),“qualified”(BBPS 6-7 points) and“excellent”(BBPS 8-9 points). There were no significant differences in polyp detection between the two groups when the bowel preparation quality was“poor”or “excellent”(all P>0.05). PDR and PPC were significantly increased in AI group when the bowel preparation quality was “qualified”(33.0% vs. 20.0%, 0.670 vs. 0.450, all P<0.05). Conclusions: AI-based colorectal polyp diagnostic system can significantly improve PDR and PPC because of the significant increase in the number of diminutive and small polyps detected. In addition, when the bowel preparation is qualified, the AI system can play better for polyp detection.
Mots clés
Texte intégral: 1 Indice: WPRIM langue: Zh Texte intégral: Chinese Journal of Gastroenterology Année: 2022 Type: Article
Texte intégral: 1 Indice: WPRIM langue: Zh Texte intégral: Chinese Journal of Gastroenterology Année: 2022 Type: Article