Multimodal Deep Learning for Lymph Node Metastasis Prediction and Physician Performance Assessment in T1 Gastric Cancer

NCT07124754 | Recruiting

• 1 other identifier: GC-RAD-AI-2025-04
• Study Type: observational
• Target: 300
• Locations: 1 country
• Sites: 1

Brief Summary

This study aims to develop and validate an artificial intelligence (AI) model that integrates clinical, pathological, and imaging data to predict the presence of lymph node metastasis (LNM) in patients with T1-stage gastric cancer. The study will also compare the diagnostic performance of physicians with and without AI assistance, including clinicians with varying levels of experience. The goal is to improve early decision-making and support more personalized treatment strategies for patients with early gastric cancer.

Conditions

T1 Gastric Cancer Lymph Node Metastasis Early Gastric Cancer Artificial Intelligence-Assisted Diagnosis Multimodal Data Integration

Keywords

T1 Gastric Cancer Lymph Node Metastasis Early Gastric Cancer Artificial Intelligence-Assisted Diagnosis Multimodal Data Integration

Outcome Measures

Primary Outcomes (2)

• Diagnostic Accuracy of the AI Model for Predicting Lymph Node Metastasis in T1 Gastric Cancer

  Immediately after surgery (within 7 days postoperatively, based on final pathological report)

• Diagnostic Accuracy of the AI Model for Predicting Lymph Node Metastasis in T1 Gastric Cancer

  At the time of final pathological diagnosis (typically within 3-7 days after surgery)

Interventions

Multimodal Artificial Intelligence Diagnostic Model for Lymph Node Metastasis in T1 Gastric Cancer DIAGNOSTIC_TEST

This intervention involves the use of a custom-built artificial intelligence (AI) diagnostic model that integrates multimodal data-including clinical variables, histopathological features, and imaging data-to predict lymph node metastasis in patients with T1-stage gastric cancer. The model provides risk probability scores and classification outputs that assist physicians in diagnostic decision-making. The AI system will be compared with physician performance at different levels of experience (resident, attending, senior) to assess its impact on diagnostic accuracy and clinical decision support.

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Probability Sample

Study Population

Patients diagnosed with T1-stage gastric adenocarcinoma who undergo radical gastrectomy with lymph node dissection at participating centers. Participants must have available preoperative clinical, imaging, and pathological data for AI model input and postoperative histopathological confirmation of lymph node status.

You may qualify if:

• Age 18 years or older
• Histologically confirmed primary gastric adenocarcinoma
• Clinical stage T1 (T1a or T1b) confirmed by endoscopy and imaging
• Undergoing radical gastrectomy with lymph node dissection
• Preoperative data available: clinical variables, CT imaging, and pathology slides
• Written informed consent provided

You may not qualify if:

• History of other malignancies within the past 5 years
• Received neoadjuvant chemotherapy or radiotherapy
• Incomplete clinical or pathological data
• Poor quality or missing CT or histopathology images
• Patients with distant metastasis (M1) at diagnosis
• Inability or refusal to provide informed consent

Sponsors & Collaborators

• Qun Zhao: lead

Study Sites (1)

the Fourth Hospital of Hebei Medical University

Shijiazhuang, None Selected, 050011, China

RECRUITING

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Target Duration: 36 Months
• Sponsor Type: OTHER
• Responsible Party: SPONSOR INVESTIGATOR
• PI Title: Professor

Study Record Dates

• First Submitted: August 3, 2025
• First Posted: August 15, 2025
• Study Start: January 1, 2025
• Primary Completion: December 30, 2025
• Study Completion: December 30, 2025
• Last Updated: August 15, 2025

Record last verified: 2025-08

Locations

CN (1)