Alternative Splicing Based Prediction of Chemotherapy Response in Gastric Cancer

A Multicenter Observational Study to Develop and Validate an Alternative Splicing-Based Machine Learning Model for Predicting Response to 5-FU-Based Adjuvant Chemotherapy in Gastric Cancer (VERSA-GC Study)

This study aims to develop a model to predict response to chemotherapy in gastric cancer using RNA splicing information from tumor tissue.

By analyzing genetic patterns and applying machine learning, the study seeks to identify patients who are less likely to benefit from treatment, helping guide clinical decision-making.

Study Overview

• Status: Recruiting
• Conditions: Gastric Cancer
• Intervention / Treatment: Other: Observational study (no intervention)

Detailed Description

This multicenter observational study aims to develop and validate an alternative splicing (AS)-based model to predict response to 5-FU-based adjuvant chemotherapy in stage II/III gastric cancer.

AS events were identified using TCGA SpliceSeq and UCSC Xena data, and selected candidates were quantified by RT-qPCR.

A predictive model was constructed using Elastic Net-based feature selection and XGBoost, and evaluated in independent training and validation cohorts. An integrated model incorporating clinicopathological factors was also developed.

The primary endpoint is treatment response defined by 3-year recurrence-free survival. Patients with recurrence within 3 years are classified as non-responders, and those without recurrence as responders.

This study aims to establish a clinically applicable biomarker for risk stratification and treatment decision support.

• Study Type: Observational
• Enrollment (Estimated): 329

Contacts and Locations

• Study Contact: Name: Ajay Goel; Phone Number: 626-256-4673; Email: ajgoel@coh.org

Study Locations

• United States
  • California
    • Duarte, California, United States, 91016
      • Recruiting
      • City of Hope Medical Center

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

Patients with stage II and III gastric cancer who underwent curative resection and received 5-FU-based adjuvant chemotherapy across multiple institutions.

Description

Inclusion Criteria:

• Pathologically confirmed stage II or III gastric cancer
• Underwent curative surgical resection
• Received 5-FU-based adjuvant chemotherapy
• Availability of tumor tissue samples for analysis

Exclusion Criteria:

• History of other malignancies
• Inadequate or poor-quality tissue samples (e.g., contamination)

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Responder; Patients with stage II/III gastric cancer who did not develop recurrence within 3 years after curative surgery following adjuvant chemotherapy.	Other: Observational study (no intervention); This is an observational study without assigned interventions. All patients received standard-of-care 5-FU-based adjuvant chemotherapy, and no experimental intervention was performed.
Non-responder; Patients with stage II/III gastric cancer who developed recurrence within 3 years after curative surgery following adjuvant chemotherapy.	Other: Observational study (no intervention); This is an observational study without assigned interventions. All patients received standard-of-care 5-FU-based adjuvant chemotherapy, and no experimental intervention was performed.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Treatment response based on 3-year recurrence-free survival	Treatment response was defined based on recurrence-free survival (RFS). Patients who developed recurrence within 3 years after curative surgery were classified as non-responders, whereas those without recurrence were classified as responders.	3 years after surgery

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Diagnostic performance of the predictive model	Model performance was assessed using the area under the receiver operating characteristic curve, sensitivity, and specificity in the training and validation cohorts.	At model evaluation
Recurrence-free survival stratified by predefined model-derived risk score	Recurrence-free survival will be evaluated according to the predefined model-derived risk score using Kaplan-Meier survival analysis and Cox proportional hazards models. Recurrence status within 3 years after surgery will be used to define treatment response.	Up to 5 years after surgery

Collaborators and Investigators

• Sponsor: City of Hope Medical Center

Study record dates

Study Major Dates

• Study Start (Actual): May 1, 2026
• Primary Completion (Estimated): January 1, 2027
• Study Completion (Estimated): January 1, 2027

Study Registration Dates

• First Submitted: May 1, 2026
• First Submitted That Met QC Criteria: May 8, 2026
• First Posted (Actual): May 14, 2026

Study Record Updates

• Last Update Posted (Actual): May 14, 2026
• Last Update Submitted That Met QC Criteria: May 8, 2026
• Last Verified: May 1, 2026

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Neoplasms by Site; Neoplasms; Gastrointestinal Neoplasms; Digestive System Neoplasms; Digestive System Diseases; Gastrointestinal Diseases; Stomach Diseases; Stomach Neoplasms; Investigative Techniques; Methods; Observation
• Other Study ID Numbers: 23228/VERSA

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No