跳至主要内容
临床试验/NCT05462743
NCT05462743Unknown不适用

Artificial Intelligence-assisted Confocal Laser Endomicroscopy Identification of Intestinal Metaplasia Severity for Gastric Cancer Risk Assessment

Shandong University1 个研究点 分布在 1 个国家目标入组 1,000 人开始时间: 2022年7月1日最近更新:
适应症

试验速览

阶段
不适用
发起方
入组人数
1,000
试验地点
1
主要终点
Sensitivity of AI model to assess degree of intestinal metaplasia

研究概览

简要总结

Currently, the Correa cascade is a widely accepted model of gastric carcinogenesis. Intestinal metaplasia is a high risk factor for gastric cancer. According to Sydney criteria, mild intestinal metaplasia was not associated with gastric cancer, while moderate to severe intestinal metaplasia was strongly associated with the development of gastric cancer. Because intestinal metaplasia is distributed in various forms, the use of white light endoscopy lacks specificity, and the consistency with histopathological diagnosis is poor; Pathological biopsy is still needed to make a diagnosis. At present, national guidelines suggest that OLGIM score should be used to evaluate the risk of gastric cancer, and patients with OLGIM grade III/IV should be monitored by close gastroscopy. However, it requires at least four biopsies, which is clinically infeasible. Confocal laser endomicroscopy allows real-time observation of living tissue, comparable to pathological findings.

详细描述

Gastric cancer is a common malignant tumor in digestive system diseases. Currently, the Correa cascade is a widely accepted model of gastric carcinogenesis. Intestinal metaplasia is a high risk factor for gastric cancer and is considered a precancerous condition of intestinal type gastric cancer. According to Sydney criteria, mild intestinal metaplasia was not associated with gastric cancer, while moderate to severe intestinal metaplasia was strongly associated with the development of gastric cancer. Because intestinal metaplasia is distributed in various forms, the use of white light endoscopy lacks specificity, and the consistency with histopathological diagnosis is poor; Pathological biopsy is still needed to make a diagnosis. At present, our national guidelines suggest that OLGIM score should be used to evaluate the risk of gastric cancer, and patients with OLGIM grade III/IV should be monitored by close gastroscopy. However, it requires at least four biopsies, which is clinically infeasible. Confocal laser endomicroscopy allows real-time observation of living tissue, comparable to pathological findings. Therefore, we established artificial intelligence-assisted confocal laser endoscope technology to determine the high risk of gastric cancer in real time, instead of tissue biopsy.

研究设计

研究类型
Observational
观察模型
Other
时间视角
Retrospective

入排标准

年龄范围
18 Years 至 80 Years(Adult, Older Adult)
性别
All
接受健康志愿者
否

入选标准

  • •Patients aged 18-80 years undergoing confocal gastroscopy

排除标准

  • •Patients with severe cardiac, cerebral, pulmonary or renal dysfunction or psychiatric disorders who cannot participate in gastroscopy
  • •Patients with previous surgical procedures on the stomach
  • •Patients with contraindications to biopsy
  • •Patients who refuse to sign the informed consent form

结局指标

主要结局

Sensitivity of AI model to assess degree of intestinal metaplasia

时间窗: 2 years

The sensitivity of the AI model to diagnose the degree of intestinal metaplasia at the biopsy site was assessed using pathological biopsy results as the gold standard

Specificity of AI model to assess degree of intestinal metaplasia

时间窗: 2 years

Pathological biopsy results were used as the gold standard to assess the specificity of the AI model in diagnosing the degree of intestinal metaplasia at the biopsy site

Accuracy of AI model in assessing degree of intestinal metaplasia

时间窗: 2 years

Pathological biopsy results were used as the gold standard to assess the accuracy of the AI model in diagnosing the degree of intestinal metaplasia at the biopsy site

次要结局

未报告次要终点

研究者

发起方
Shandong University
申办方类型
Other
责任方
Principal Investigator
主要研究者

Yanqing Li

Vice President of Qilu Hospital

Shandong University

研究点 (1)

Loading locations...

相似试验