DeepComp: AI prediction of complications after stomach cancer surgery
A Prospective, Multicenter, Observational Study Validating the Multimodal Deep Learning Radiomics Model (DeepComp) for Preoperative Prediction of Major Postoperative Complications in Patients With Gastric Cancer
This project will try an AI tool called DeepComp to predict which adults with gastric adenocarcinoma scheduled for curative stomach surgery are at high risk of moderate-to-severe postoperative complications using routine preoperative CT scans and clinical data.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 500 (estimated) |
| Ages | 18 Years to 85 Years |
| Sex | All |
| Sponsor | Hebei Medical University Academic / other |
| Locations | 1 site (Shijiazhuang, None Selected) |
| Trial ID | NCT07401173 on ClinicalTrials.gov |
What this trial studies
This prospective, multicenter observational study will enroll adults with histologically confirmed gastric adenocarcinoma who are scheduled for elective radical gastrectomy. Researchers will collect routine preoperative contrast-enhanced abdominal CT scans (venous phase) performed within 14 days before surgery plus standard clinical data, then extract radiomic features and body-composition measures (muscle and fat distribution). The DeepComp AI model will integrate these imaging-derived features with clinical variables to generate preoperative risk predictions for moderate-to-severe postoperative complications. Predicted risks will be compared with actual postoperative outcomes to validate the model's performance across participating centers.
Who should consider this trial
Good fit: Adults aged 18 or older with histologically confirmed gastric adenocarcinoma who are scheduled for elective curative radical gastrectomy and have a standard contrast-enhanced abdominal CT within 14 days before surgery and can provide informed consent.
Not a fit: Patients undergoing emergency surgery, those found to have unresectable or metastatic disease intraoperatively, recent other malignancies, pregnant or lactating patients, or those with CT scans rendered unreadable by severe metallic artifacts are unlikely to benefit from this protocol.
Why it matters
Potential benefit: If successful, DeepComp could help doctors identify patients at higher risk before surgery so perioperative care can be personalized to reduce complications and improve recovery.
How similar studies have performed: Retrospective studies combining radiomics and body-composition metrics have shown promising results for predicting surgical risk, but prospective multicenter validation like this is limited.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: Age ≥ 18 years. Histologically confirmed gastric adenocarcinoma. Scheduled for elective radical gastrectomy (open, laparoscopic, or robotic) with curative intent. Standard preoperative contrast-enhanced abdominal CT scans (venous phase) performed within 14 days prior to surgery. Willingness to sign informed consent. Exclusion Criteria: Emergency surgery due to perforation, obstruction, or massive bleeding. Intraoperative findings of distant metastasis (Stage IV) or unresectable disease preventing R0 resection. Concurrent or previous malignant tumors within the last 5 years (except gastric cancer). Pregnancy or lactation. Severe metallic artifacts on CT images preventing radiomic analysis.
Where this trial is running
Shijiazhuang, None Selected
- the Fourth Hospital of Hebei Medical University — Shijiazhuang, None Selected, China (Recruiting)
Study contacts
- Principal investigator: Qun Zhao — th
- Study coordinator: Ping'an Ding, PhD
- Email: ding_ping_an@hebmu.edu.cn
- Phone: +8631186095363
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.