CT Imaging and Clinical Features to Predict Outcomes in Patients With Gastric Cancer | NCT07776067 | Trialant

RecruitingObservationalUpdated Aug 20, 2026

CT Imaging and Clinical Features to Predict Outcomes in Patients With Gastric Cancer

Prospective Validation of a CT Radiomics-Based Model Combined With Clinical Features for Prognosis Prediction in Gastric Cancer Patients

Overview

Key facts that identify this study and show where it stands today.

ClinicalTrials.gov ID: NCT07776067
Lead Sponsor: Union Hospital, Tongji Medical College, Huazhong University of Science and TechnologyOTHER
Overall Status: Recruiting
Study Type: Observational
Enrollment: 600Estimated
Last Update Posted: Aug 20, 2026Actual
Start Date: Apr 1, 2026Actual
Primary Completion Date: Apr 1, 2027Estimated
Completion Date: Apr 1, 2027Estimated

Description

What the study is about and why it is being run, in the researchers' own words.

Official Title: Prospective Validation of a CT Radiomics-Based Model Combined With Clinical Features for Prognosis Prediction in Gastric Cancer Patients
Brief Summary: The goal of this prospective observational study is to evaluate how well a previously developed prediction model can estimate outcomes in adults with gastric cancer. The model combines information from computed tomography (CT) images obtained before treatment with routine clinical information. The main questions are how well the model predicts how long participants live after treatment begins and whether their cancer progresses.

Participants will receive their usual medical care. Researchers will collect pretreatment CT images, basic clinical and tumor information, laboratory and tumor marker results, treatment information, and follow-up outcomes obtained during routine care. These data will be entered into the predefined prediction model, and the model's predictions will be compared with what actually happens during follow-up.

The study will not change the participants' usual treatment. Model predictions will be used for research purposes only and will not be used to make treatment decisions.

Conditions

The medical conditions and diseases this study investigates.

Gastric Cancer

Interventions

The treatments and procedures being evaluated in this study.

No intervention (observational study)

Participation

Who can join this study and the criteria used to decide.

Ages Eligible for Study: Adult (18-64)Older Adult (65+)
Sexes Eligible for Study: All
Accepts Healthy Volunteers: No
Eligibility Criteria: Inclusion Criteria:

Histologically or pathologically confirmed gastric cancer and receiving treatment at the study center.

Age ≥18 years. Complete pretreatment CT imaging data available from the study center.

Exclusion Criteria:

Pretreatment CT images of insufficient quality for analysis. Incomplete clinical data. Presence of another malignant tumor in addition to gastric cancer.

Design

How the study is designed and how its participant groups are organized.

Observational Model: Cohort
Time Perspective: Prospective

Contacts

The people to reach with questions about this study or how to join it.

No central contacts

There are no central contacts for this study.

Locations

Where the study is run and whether each site is currently recruiting.

Union Hospital, Tongji Medical College, Huazhong University of Science and TechnologyRecruiting

Wuhan, Hubei 430022, China

Collaborators

The organizations and people involved in this study.

Lead Sponsor: Union Hospital, Tongji Medical College, Huazhong University of Science and TechnologyOTHER

Similar Studies

Other registered studies that closely resemble this one.

Detailed Description

This is a single-center, non-interventional prospective observational cohort study designed to validate a prognostic prediction model for gastric cancer that integrates pretreatment CT imaging features with clinical variables. The model was developed from a previous retrospective cohort of patients with gastric cancer using pretreatment CT images, clinicopathological information, treatment data, and survival outcomes.

Adults with newly diagnosed gastric cancer who are scheduled to receive surgery, chemotherapy, immunotherapy, or combined treatment at the study center will be prospectively enrolled. During routine clinical care, researchers will collect pretreatment CT images and relevant demographic, clinicopathological, laboratory, tumor marker, treatment, and follow-up data. Quantitative CT features related to tumor morphology, density, texture, and spatial heterogeneity will be integrated with clinical variables such as age, sex, TNM stage, Lauren classification, serum tumor markers, and treatment modality to generate individualized prognostic risk estimates.

Model predictions will be compared with observed clinical outcomes during follow-up to evaluate prognostic performance and risk stratification. Model performance will also be assessed in clinically relevant subgroups, including groups defined by treatment modality, clinical stage, age, and sex. Statistical analyses will include Kaplan-Meier survival analysis, log-rank tests, and Cox proportional hazards regression with adjustment for potential confounding factors.

This study will not assign treatment or alter routine clinical care. All treatment decisions will be made by treating clinicians according to each participant's clinical condition and current clinical practice. Model-generated predictions will be stored for research purposes only and will not be provided to clinicians for treatment decision-making. Clinical and imaging data will be coded and de-identified and stored in a password-protected research database. Data quality will be supported by standardized data collection procedures, investigator training, independent data checking, imaging quality review, and standardized follow-up procedures.