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
试验速览
- 阶段
- 不适用
- 状态
- 招募中
- 发起方
- 入组人数
- 500
- 试验地点
- 1
- 主要终点
- Human-AI Collaborative Diagnostic Performance in Gastric Cancer Surgery: Accuracy and Observer Agreement
研究概览
简要总结
Gastric cancer is a leading cause of cancer-related mortality, and radical surgery remains the primary treatment. However, postoperative complications are common and can significantly impact patient recovery and quality of life. Currently, doctors lack precise tools to accurately predict which patients are at high risk for developing severe complications before surgery.
This study aims to validate a novel artificial intelligence (AI) model called "DeepComp." The DeepComp model integrates clinical data with advanced radiomic features derived from routine preoperative CT scans. Specifically, it analyzes both the tumor characteristics and the patient's body composition (including skeletal muscle and fat distribution) to assess physiological reserve.
In this prospective, multicenter observational study, researchers will enroll patients scheduled for gastric cancer surgery across five medical centers. The DeepComp model will be used to predict the risk of moderate-to-severe postoperative complications (Clavien-Dindo grade II or higher). These predictions will then be compared with the actual clinical outcomes observed 30 days after surgery. The goal is to determine the accuracy and reliability of the DeepComp model in a real-world clinical setting, potentially providing a powerful tool for personalized surgical risk assessment.
研究设计
- 研究类型
- Observational
- 观察模型
- Cohort
- 时间视角
- Prospective
入排标准
- 年龄范围
- 18 Years 至 85 Years（Adult, Older Adult）
- 性别
- All
- 接受健康志愿者
- 否
入选标准
- •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.
排除标准
- •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.
研究组 & 干预措施
Gastric Cancer Surgery Cohort
Patients diagnosed with gastric cancer who are scheduled to undergo radical gastrectomy (open, laparoscopic, or robotic). All participants will receive standard preoperative contrast-enhanced CT scans. The DeepComp AI model will be applied to these scans to predict the risk of postoperative complications.
结局指标
主要结局
Human-AI Collaborative Diagnostic Performance in Gastric Cancer Surgery: Accuracy and Observer Agreement
时间窗: From preoperative assessment through 30 days post-surgery
In a subset of 120 randomly selected gastric cancer surgery patients, ten surgeons of varying experience levels (Junior \<5 years, n=4; Intermediate 5-10 years, n=3; Senior ≥10 years, n=3) will first independently assess postoperative complication risk using blinded preoperative data. Subsequently, they will receive predictions from the DeepComp AI model and update their assessments.
Incidence of Major Postoperative Complications (Clavien-Dindo Grade ≥ II)
时间窗: Postoperative 30 days
Postoperative complications will be graded according to the Clavien-Dindo classification system. Major complications are defined as Grade II or higher, which require pharmacological treatment, surgical/endoscopic/radiological intervention, or life-threatening complications (including death). The occurrence of these events will be recorded and compared with the model's preoperative predictions.
次要结局
- Predictive Performance of the DeepComp Model (AUC)(Postoperative 30 days)
- Length of Hospital Stay(Up to 30 days)
研究者
Qun Zhao
Professor
Hebei Medical University