AI-guided reoperation decisions for bleeding after stomach cancer surgery

A Multicenter Observational Study to Develop and Validate a Deep Learning Model for Dynamic Assessment of Postoperative Bleeding Risk to Assist Re-operation Decision-Making in Patients With Gastric Cancer

This project will test whether an AI model can predict serious postoperative bleeding and help doctors decide if and when to reoperate for adults after radical gastrectomy for gastric cancer.

Quick facts

• Study type: Observational
• Enrollment: 7000 (estimated)
• Ages: 18 Years to 90 Years
• Sex: All
• Sponsor: First Affiliated Hospital of Zhejiang University (Academic / other)
• Locations: 1 site (Hangzhou, Zhejiang)
• Trial ID: NCT07525765 on ClinicalTrials.gov

What this trial studies

This observational hybrid study will develop and validate a deep learning model using both retrospective and prospective perioperative data from adults undergoing radical gastrectomy for primary gastric cancer. The model will integrate dynamic physiological parameters and precise intraoperative blood loss to predict the risk of postoperative bleeding that requires reoperation. Investigators will report model performance using metrics such as sensitivity, negative predictive value, AUC, and calibration and will examine whether the model could provide earlier warning times or better timing for interventions. Because there are no intervention arms, researchers will not randomize treatments but will test the predictive accuracy and potential clinical utility of the model using collected clinical records.

Who should consider this trial

Good fit: Adults (≥18) with histologically confirmed primary gastric cancer who underwent radical gastrectomy and have complete preoperative, intraoperative, and at least 15 days of postoperative follow-up data are the intended participants.

Not a fit: Patients who had non-radical or emergency surgery, have severe preoperative infection or organ failure, have key data missing >20%, or cannot complete prospective follow-up are unlikely to benefit from this model.

Why it matters

Potential benefit: If successful, this AI tool could provide earlier warnings and more precise timing for reoperation, potentially reducing mortality and shortening hospital stays for affected patients.

How similar studies have performed: Some AI models for predicting postoperative complications have shown promising accuracy in single-center reports, but applying AI specifically to guide reoperation for postoperative bleeding after gastrectomy is relatively novel and not yet widely validated.

Eligibility criteria

Inclusion Criteria:

1. Age: Patients aged ≥ 18 years.
2. Diagnosis: Histologically confirmed primary gastric cancer.
3. Surgical Procedure: Underwent radical gastrectomy (including proximal, distal, or total gastrectomy).
4. Consent: Provision of written informed consent (required specifically for the prospective phase).
5. Data Completeness: Availability of complete preoperative clinical data and postoperative follow-up records covering at least the first 15 days post-surgery.
6. Oncological History: No history of other primary malignant tumors.

Exclusion Criteria:

1. Surgical Type: Patients who underwent non-radical resection or emergency surgery.
2. Data Quality: Missing rate of key data fields exceeds 20%.
3. Preoperative Condition: Presence of severe preoperative infection or organ failure.
4. Follow-up Compliance: Unwillingness to participate in prospective follow-up or inability to complete the follow-up schedule (applicable only to the prospective phase).

Where this trial is running

Hangzhou, Zhejiang

• The First Affiliated Hospital, Zhejiang University School of Medicine Yuhang Campus — Hangzhou, Zhejiang, China (Recruiting)

Study contacts

• Study coordinator: Jianghao Li, B.S. in Computer Science

Conditions Gastrectomy for Gastric Cancer; Gastric Cancer