Эта страница была переведена автоматически, точность перевода не гарантируется. Пожалуйста, обратитесь к английской версии для исходного текста.

AI-Based Risk Prediction Model for Upper Digestive Tract Cancer

25 мая 2026 г. обновлено: National Taiwan University Hospital

Development of Artificial Intelligence Risk Prediction Model for Upper Digestive Tract Cancer Using High Resolution Endoscopic Image, Digital Pathology, Genetics, and Oro-gastro-intestinal Microbiota.

Upper digestive tract cancers are often preceded by pre-malignant lesions, but there is limited evidence regarding optimal risk prediction models and screening strategies for disease progression and cancer development. This prospective multicenter cohort study aims to establish a longitudinal database integrating clinical information, endoscopic findings, pathology, genetics, epigenetics, and gastrointestinal microbiota data from subjects undergoing upper digestive tract endoscopy.

The study will develop explainable artificial intelligence (AI)-based risk prediction models to identify factors associated with disease progression, treatment response, and cancer development. Participants will be followed longitudinally to evaluate changes in lesion severity and clinical outcomes.

Обзор исследования

Статус

Еще не набирают

Условия

Подробное описание

Objectives:

There is no solid evidence about the risk prediction model and screening duration for upper digestive tract pre-malignant lesions and its progression. There is also no longitudinal study combining multi-omic approach, endoscopic and pathologic images and the association with disease development. Hence we design a prospective cohort targeting upper digestive tract disease progression and cancer development, with standardized clinical data collection, quality control and explainable AI (artificial intellegence) model for better reliability of risk prediction model.

Aims:

We aim to develop risk prediction model for the progression of upper digestive tract disease and cancer development.

Methods:

The study is disigned as a multi-center prospective cohort, targeting subjects undergoing upper digestive tract endoscopy. The development of AI risk prediction models will combine endoscopic pre-malignant lesion, pathology, genetics, epigenetics, oro-gastro-intestinal microbiota, and follow-up longitudinally with change in lesion severity, medication response, cancer development.

Outcome measurement:

Primary endpoints: upper digestive tract cancer development. Secondary endpoints: progression in pre-malignant lesions, recurrent colon polyps, other cancer developement, metabolic and cardiovascular disease, response to medication in gastro-esophageal reflux and dyspepsia population.

Тип исследования

Наблюдательный

Регистрация (Оцененный)

10000

Контакты и местонахождение

В этом разделе приведены контактные данные лиц, проводящих исследование, и информация о том, где проводится это исследование.

Контакты исследования

Имя: Jyh-Ming Liou, MD, PhD
Номер телефона: +886972651883
Электронная почта: jyhmingliou@gmail.com

Учебное резервное копирование контактов

Имя: Tzu-Chan Hong, MD, PhD
Номер телефона: 238061 +886-2-2322-0322
Электронная почта: edisonhong77@gmail.com

Критерии участия

Исследователи ищут людей, которые соответствуют определенному описанию, называемому критериям приемлемости. Некоторыми примерами этих критериев являются общее состояние здоровья человека или предшествующее лечение.

Критерии приемлемости

Возраст, подходящий для обучения

Взрослый
Пожилой взрослый

Принимает здоровых добровольцев

Да

Метод выборки

Невероятностная выборка

Исследуемая популяция

Patients with a history of surgery involving the esophagus, stomach, or duodenum.
Patients with gastric deformity secondary to severe gastric inflammation.
Patients unable to undergo regular follow-up upper gastrointestinal endoscopy every 1-3 years.
Patients with severe comorbidities that preclude follow-up upper gastrointestinal endoscopy or with an estimated life expectancy of less than 10 years.

Описание

Inclusion Criteria:

Patients undergoing upper gastrointestinal endoscopy.
Patients with at least one of the following conditions or indications:
- Previous or current Helicobacter pylori infection (confirmed by serology, histopathology, urea breath test, rapid urease test, or stool antigen test);
- Dyspeptic symptoms;
- Gastroesophageal reflux disease;
- History of oral, oropharyngeal, or hypopharyngeal squamous cell carcinoma;
- Barrett's esophagus;
- Gastric premalignant lesions (intestinal metaplasia or atrophic gastritis);
- Gastric subepithelial lesions.

Exclusion Criteria:

Учебный план

В этом разделе представлена подробная информация о плане исследования, в том числе о том, как планируется исследование и что оно измеряет.

Как устроено исследование?

Детали дизайна

Что измеряет исследование?

Первичные показатели результатов

Мера результата	Мера Описание	Временное ограничение
Number of participants with upper digestive tract cancer confirmed by histopathological examination Временное ограничение: "From enrollment to the end of follow-up at 10 years"	Upper digestive tract cancer development will be defined as newly diagnosed upper digestive tract malignancy during follow-up, including esophageal cancer and gastric cancer. Diagnosis will be confirmed by histopathological examination of biopsy or resection specimens.	"From enrollment to the end of follow-up at 10 years"

Вторичные показатели результатов

Мера результата	Мера Описание	Временное ограничение
Recurrent colon polyps Временное ограничение: From enrollment to the end of follow-up at 10 years		From enrollment to the end of follow-up at 10 years
Number of participants with progression of gastric premalignant lesions assessed by OLGA, OLGIM, and EGGIM staging systems Временное ограничение: From enrollment to the end of follow-up at 10 years	Progression of premalignant lesions will be defined as worsening of gastric atrophy and intestinal metaplasia during follow-up based on histological and endoscopic assessment. Histological progression will be evaluated using changes in OLGA and OLGIM stages, while endoscopic progression will be assessed using EGGIM scores. Progression is defined as an increase in stage or score compared with baseline evaluation.	From enrollment to the end of follow-up at 10 years
Number of participants with non-upper digestive tract malignancies confirmed by histopathological examination Временное ограничение: From enrollment to the end of follow-up at 10 years	Other cancer development will be defined as newly diagnosed malignancies other than upper digestive tract cancers during follow-up, including but not limited to colorectal cancer, hepatobiliary cancer, pancreatic cancer, lung cancer, breast cancer, prostate cancer, and hematologic malignancies. Diagnosis will be confirmed by histopathological examination, imaging findings, or cancer registry records.	From enrollment to the end of follow-up at 10 years
Number of participants with newly diagnosed metabolic and cardiovascular diseases Временное ограничение: From enrollment to the end of follow-up at 10 years	Metabolic and cardiovascular disease development will be defined as newly diagnosed metabolic or cardiovascular conditions during follow-up, including diabetes mellitus, hypertension, dyslipidemia, coronary artery disease, cerebrovascular disease, heart failure, and peripheral arterial disease. Diagnoses will be confirmed based on medical records and clinical assessments.	From enrollment to the end of follow-up at 10 years
Number of participants with symptom or endoscopic improvement after medication treatment in gastroesophageal reflux disease and dyspepsia populations Временное ограничение: From enrollment to the end of follow-up at 10 years	Treatment response will be defined as improvement of reflux and dyspeptic symptoms after medical therapy during follow-up. Symptom response will be assessed based on patient-reported symptom improvement and medical records. Endoscopic response will be assessed endoscopically	From enrollment to the end of follow-up at 10 years

Соавторы и исследователи

Здесь вы найдете людей и организации, участвующие в этом исследовании.

Спонсор

National Taiwan University Hospital

Даты записи исследования

Эти даты отслеживают ход отправки отчетов об исследованиях и сводных результатов на сайт ClinicalTrials.gov. Записи исследований и сообщаемые результаты проверяются Национальной медицинской библиотекой (NLM), чтобы убедиться, что они соответствуют определенным стандартам контроля качества, прежде чем публиковать их на общедоступном веб-сайте.

Изучение основных дат

Начало исследования (Оцененный)

18 мая 2026 г.

Первичное завершение (Оцененный)

18 мая 2030 г.

Завершение исследования (Оцененный)

18 мая 2030 г.

Даты регистрации исследования

Первый отправленный

17 мая 2026 г.

Впервые представлено, что соответствует критериям контроля качества