Unique ID issued by UMIN | UMIN000057846 |
---|---|
Receipt number | R000066120 |
Scientific Title | Establishment of a Non-Invasive Risk Stratification Approach for Helicobacter pylori-Negative Gastric Cancer Aimed at Optimizing Population-Based Gastric Cancer Screening Programs |
Date of disclosure of the study information | 2025/06/01 |
Last modified on | 2025/05/13 06:18:16 |
Development of a Non-Invasive Method for Assessing the Risk of H. pylori-Negative Gastric Cancer to Optimize Gastric Cancer Screening Programs
Development of Artificial Intelligence for Risk Assessment of H. pylori-Negative Gastric Cancer
Establishment of a Non-Invasive Risk Stratification Approach for Helicobacter pylori-Negative Gastric Cancer Aimed at Optimizing Population-Based Gastric Cancer Screening Programs
Artificial Intelligence-Based Risk Assessment of H. pylori-Negative Gastric Cancer: Development and Validation
Japan |
Gastric cancer
Gastroenterology |
Malignancy
NO
Gastric cancer screening using endoscopy, implemented as a population-based measure to facilitate early detection and reduce mortality, may become less effective in the future as the prevalence of Helicobacter pylori (H. pylori) infection continues to decline. Although rare, gastric cancer can still occur in individuals uninfected with H. pylori, making risk prediction for H. pylori-negative gastric cancer an important public health concern.
Recent efforts have aimed to develop artificial intelligence (AI) models that predict the risk of gastric cancer using variables such as age, comorbidities, endoscopic findings, and histopathological data among individuals who have undergone upper gastrointestinal endoscopy. However, all of these approaches rely on endoscopic examination for risk stratification.
Considering future social implementation, there is a need to establish risk assessment methods that do not depend on endoscopic data. This study aims to develop an AI-based model capable of stratifying gastric cancer risk in H. pylori-negative individuals using non-endoscopic variables, such as dietary habits, lifestyle factors, and underlying health conditions, by conducting a cross-sectional survey of patients with and without gastric cancer.
Efficacy
Accuracy, precision, recall, AUC of the ROC curve, and RMSE of the constructed AI.
The background and lesion characteristics of H. pylori-naive gastric cancer cases and H. pylori-naive non-gastric cancer cases.
Observational
18 | years-old | <= |
100 | years-old | >= |
Male and Female
1. H. pylori-Negative Gastric Cancer Cases
All patients diagnosed and treated for Helicobacter pylori (H. pylori)-negative gastric cancer during the study period will be included. The target population also includes gastric cancers located at the esophagogastric junction classified as Siewert type II or III, as well as gastric cancers occurring in patients with hereditary diffuse gastric cancer (HDGC), familial adenomatous polyposis (FAP), and other hereditary gastrointestinal cancer syndromes.
H. pylori-negative status is defined as meeting all of the following criteria:
i) At least one negative result in H. pylori diagnostic tests (e.g., serum anti-H. pylori IgG antibody, urea breath test, or direct microscopic examination of gastric mucosal biopsy specimens),
ii) No endoscopic evidence of gastric mucosal atrophy,
iii) No history of H. pylori eradication therapy.
2. H. pylori-Negative Non-Gastric Cancer Cases
Patients confirmed to be H. pylori-negative and without evidence of gastric cancer on upper gastrointestinal endoscopy performed under the national health insurance system are eligible.
To confirm H. pylori-negative status endoscopically, the following criteria are used:
i) Presence of regular arrangement of collecting venules (RAC),
ii) Presence of foveolar-hyperplastic red streaks (linear red streaks), hematin adherence, or fundic gland polyps, which are indicative of an uninfected gastric mucosa,
iii) Absence of endoscopic atrophy, and
iv) Absence of active H. pylori infection findings such as diffuse redness, increased mucus secretion, or thickened folds of the greater curvature of the gastric body.
A comprehensive judgment is made based on these findings to confirm H. pylori-negative status.
Patients with an undetermined final pathological diagnosis will be excluded. In addition, H. pylori-negative gastric tumors classified as foveolar-type gastric adenomas -such as raspberry-type and flat-type lesions- will be excluded, as they are categorized as adenomas under the 5th edition of the WHO Classification of Tumors.
3000
1st name | Fumiaki |
Middle name | |
Last name | Ishibashi |
International University of Health and Welfare Ichikawa Hospital
Department of Gastroenterology
272-0827
6-1-14, Konodai, Ichikawa-shi, Chiba
047-375-1111
ishibashi-gast@iuhw.ac.jp
1st name | Fumiaki |
Middle name | |
Last name | Ishibashi |
International University of Health and Welfare Ichikawa Hospital
Department of Gastroenterology
272-0827
6-1-14, Konodai, Ichikawa-shi, Chiba
047-375-1111
ishibashi-gast@iuhw.ac.jp
International University of Health and Welfare Ichikawa Hospital
self-procurement
Self funding
International University of Health and Welfare
4-3, Kozunomori, Narita-shi, Chiba
0476-20-7708
rinri_md@iuhw.ac.jp
NO
2025 | Year | 06 | Month | 01 | Day |
Unpublished
Preinitiation
2025 | Year | 05 | Month | 12 | Day |
2025 | Year | 08 | Month | 01 | Day |
2026 | Year | 07 | Month | 31 | Day |
Basic Information:
Name of a participating institution, participant's name, date of birth, age, sex, place of birth, height and weight at the time of the most recent endoscopic examination, smoking and alcohol consumption history at the time of gastric cancer diagnosis, family history of gastric cancer within second-degree relatives, personal history of gastric cancer, and history of other malignancies.
Medical Information:
Presence of comorbidities at the time of gastric cancer diagnosis (including diabetes mellitus, hypertension, coronary artery disease, chronic obstructive pulmonary disease, chronic kidney disease, osteoporosis) and history of medication use.
Dietary Habits:
Data collected using a semi-quantitative food frequency questionnaire, covering the intake frequency and content of staple and side dishes (dairy products, legumes, seafood, eggs, meat, oils, vegetables, mushrooms, seaweed), fruits, snacks, and beverages for breakfast, lunch, and dinner.
Data Collection Schedule:
Data will be collected over a one-year period following approval by the ethics committee.
2025 | Year | 05 | Month | 13 | Day |
2025 | Year | 05 | Month | 13 | Day |
Value
https://center6.umin.ac.jp/cgi-open-bin/ctr_e/ctr_view.cgi?recptno=R000066120