NCT07454967

Development of a Multimodal AI System for GIST Management

Development and Validation of a Multimodal Artificial Intelligence Model Integrating CT Radiomics, Pathomics, and Clinical Features for the Diagnosis, Risk Stratification, and Genotype Prediction of Gastrointestinal Stromal Tumors

• Status: Completed
• Phase: —
• Study type: Observational
• Enrollment: 300 (actual)
• Sponsor: Qun Zhao · Academic / Other
• Sex: All
• Age: 18 Years
• Healthy volunteers: —

Summary

Background: Gastrointestinal Stromal Tumors (GISTs) are the most common mesenchymal tumors of the gastrointestinal tract. Accurate pre-operative diagnosis, risk stratification, and genotyping are critical for determining the appropriate surgical approach and targeted therapy (such as Imatinib). However, current methods often rely on invasive postoperative pathology and expensive genetic testing. Study Objective: The purpose of this study is to develop and validate a multimodal Artificial Intelligence (AI) model that integrates clinical data, CT radiomics (imaging features), and pathomics (digital pathology features) to improve the precision of GIST management. Study Design: This is a prospective, observational study. The researchers will recruit patients with suspected gastric submucosal tumors who are scheduled for surgery or biopsy at The Fourth Hospital of Hebei Medical University. Core Tasks: The AI model will be trained to perform three specific tasks: Diagnosis: Distinguish GISTs from other non-GIST mesenchymal tumors (e.g., leiomyomas, schwannomas). Risk Assessment: Stratify GISTs into risk categories (e.g., Low vs. High risk) to predict malignant potential. Genotyping: Predict specific gene mutations (e.g., KIT or PDGFRA mutations) to guide immunotherapy or targeted therapy. Methodology: Patient data (CT scans, pathology slides, and clinical history) will be collected and analyzed by the AI system. The AI's predictions will be compared against the "Gold Standard" results derived from postoperative pathological examination and Next-Generation Sequencing (NGS). This study is non-interventional; the AI results will not affect the standard of care received by the patients.

Conditions

• Gastrointestinal Stromal Tumors
• Gastric Subepithelial Tumors
• Gastric Leiomyoma
• Artificial Intelligence (AI)
• Multimodal Imaging

Interventions

Type	Name	Description
DIAGNOSTIC_TEST	Multimodal AI Analysis System	The Multimodal AI System utilizes deep learning algorithms to integrate patient data from three sources: preoperative CT images (Radiomics), digitized pathology slides (Pathomics), and clinical characteristics. The model generates probability scores for: 1) Differential diagnosis of GIST vs. non-GIST, 2) Risk stratification, and 3) Genotype prediction. Note: This is an observational study. The AI model's analysis is performed in parallel to standard clinical care. The results are blinded to the treating physicians and will NOT influence the surgical plan or medical management of the participants.

Timeline

• Start date: 2024-01-01
• Primary completion: 2026-01-01
• Completion: 2026-01-01
• First posted: 2026-03-06
• Last updated: 2026-04-02

Locations

9 sites across 1 country: China