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
AI tool to improve diagnosis and treatment of stomach tumors
Plain English Summary
Development of a Multimodal AI System for GIST Management is a Not Applicable clinical trial sponsored by Qun Zhao studying Gastrointestinal Stromal Tumors, Gastric Subepithelial Tumors, Gastric Leiomyoma, Artificial Intelligence (AI), Multimodal Imaging. This study tests an Artificial Intelligence (AI) tool that combines imaging, pathology, and patient data to help diagnose and assess the risk of gastrointestinal stromal tumors (GISTs). It is for patients with suspected gastric submucosal tumors who are scheduled for surgery or biopsy. Participation involves providing CT scans, pathology slides, and clinical information for the AI to analyze. This is observational, meaning the AI's findings will not change your standard medical care. Alternatives include traditional methods like surgery, biopsy, and genetic testing, which are often done after diagnosis. The trial aims to enroll 300 participants.
Official 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.
Who Can Participate
Here is what you need to know about eligibility for this trial. Adults aged 18 and older with a suspected gastric submucosal tumor or GIST. Patients scheduled for surgery or biopsy of a gastric submucosal tumor. Individuals who have had a recent CT scan (within 2 weeks of surgery) and can provide informed consent. People who have not received prior treatment like Imatinib, chemotherapy, or radiation for this condition. This trial is studying Gastrointestinal Stromal Tumors, Gastric Subepithelial Tumors, Gastric Leiomyoma, Artificial Intelligence (AI), Multimodal Imaging, so participants generally need a confirmed diagnosis.
What They're Measuring
The primary outcome measures how accurately the AI tool can tell the difference between GISTs and other types of stomach tumors, which helps doctors make a correct diagnosis. The specific primary outcome measures are: Diagnostic Accuracy of the AI Model for Distinguishing GIST from Non-GIST Tumors (Up to 30 days post-surgery). These endpoints are how researchers determine whether the treatment is effective and will form the basis of any future regulatory submissions.
About This Phase
This study does not have a traditional clinical phase designation. It may be an observational study that follows patients without intervening in their care, an expanded access or compassionate use program, or other non-interventional research. These studies contribute valuable data about disease progression, treatment patterns, and patient outcomes.
Why This Trial Matters
This trial matters because it aims to develop a faster and more precise way to diagnose and understand the risk of GISTs, potentially reducing the need for invasive tests and guiding treatment decisio This research targets Gastrointestinal Stromal Tumors, Gastric Subepithelial Tumors, Gastric Leiomyoma, Artificial Intelligence (AI), Multimodal Imaging, where improved treatment options are needed.
Investor Insight
This trial signals a growing investment in AI for medical diagnostics, particularly for rare cancers like GISTs, with the potential to improve efficiency and accuracy in a competitive field.
Is This Trial Right for Me?
Ask your doctor if this AI analysis is being done alongside your standard care and how its findings might be used in the future. Your participation involves allowing researchers to use your CT scans, pathology slides, and clinical data for the AI analysis. This is done in parallel with your regular medical treatment. You will need to provide informed consent to participate. The trial is being conducted at 9 sites. Always discuss clinical trial participation with your healthcare provider before making any decisions. This information is for educational purposes only and is not medical advice.
AI-generated analysis for educational purposes only. This is not medical advice. Discuss clinical trial participation with your doctor. Data sourced from ClinicalTrials.gov.
Study Design
- Study Type: OBSERVATIONAL
- Enrollment: 300 participants
Interventions
- 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
Primary Outcomes
- Diagnostic Accuracy of the AI Model for Distinguishing GIST from Non-GIST Tumors (Up to 30 days post-surgery)
Secondary Outcomes
- Concordance Rate between AI-predicted Risk Grade and Pathological Modified NIH Criteria (Up to 30 days post-surgery)
- Sensitivity and Specificity of the AI Model in Predicting KIT/PDGFRA Gene Mutations (Up to 30 days post-surgery)
- Area Under the Receiver Operating Characteristic Curve (AUC) for All Tasks (Up to 30 days post-surgery)
Full Eligibility Criteria
Inclusion Criteria: Age ≥ 18 years, gender not limited. Clinical diagnosis of gastric submucosal tumor (SMT) or suspected gastrointestinal stromal tumor (GIST) based on gastroscopy or ultrasound. Scheduled for surgical resection or endoscopic biopsy at the study center. Standard preoperative contrast-enhanced CT scans are available (performed within 2 weeks prior to surgery). Patients or their legal guardians have signed the informed consent form. Exclusion Criteria: Received neoadjuvant therapy (e.g., Imatinib, chemotherapy, or radiotherapy) prior to surgery/biopsy. Poor quality of CT images (e.g., severe motion artifacts) affecting radiomics analysis. Insufficient tissue samples for pathological diagnosis or genetic testing. Confirmed diagnosis of other primary malignancies. Incomplete clinical data or lost to follow-up immediately after surgery.
Trial Locations
- The Fifth Affiliated Hospital of Anhui Medical University, Fuyang, Anhui, China
- Baoding Central Hospital, Baoding, Hebei, China
- Cangzhou People's Hospital, Cangzhou, Hebei, China
- Hengshui People's Hospital, Hengshui, Hebei, China
- Shijiazhuang People's Hospital, Shijiazhuang, Hebei, China
- The Second Affiliated Hospital of Xingtai Medical College, Xingtai, Hebei, China
- Renmin Hospital of Wuhan University, Wuhan, Hubei, China
- The First Affiliated Hospital of University of South China, Hengyang, Hunan, China
- Jinling Hospital, Nanjing, Jiangsu, China
Frequently Asked Questions
What is clinical trial NCT07454967?
NCT07454967 is a Not Applicable OBSERVATIONAL study titled "Development of a Multimodal AI System for GIST Management." It is currently completed and is sponsored by Qun Zhao. The trial targets enrollment of 300 participants.
What conditions does NCT07454967 study?
This trial investigates treatments for Gastrointestinal Stromal Tumors, Gastric Subepithelial Tumors, Gastric Leiomyoma, Artificial Intelligence (AI), Multimodal Imaging. The primary condition under study is Gastrointestinal Stromal Tumors.
What treatments are being tested in NCT07454967?
The interventions being studied include: Multimodal AI Analysis System (DIAGNOSTIC_TEST). 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
What does Not Applicable mean for NCT07454967?
This study does not have a defined clinical phase. It may be an observational study, expanded access program, or other non-interventional research.
What is the current status of NCT07454967?
This trial is currently "Completed." It started on 2024-01-01. The estimated completion date is 2026-01-01.
Who is sponsoring NCT07454967?
NCT07454967 is sponsored by Qun Zhao. The sponsor is responsible for funding, designing, and overseeing the clinical trial.
How many people can participate in NCT07454967?
The trial aims to enroll 300 participants. The trial status is completed.
How is NCT07454967 designed?
This is a observational study.
What are the primary outcomes being measured in NCT07454967?
The primary outcome measures are: Diagnostic Accuracy of the AI Model for Distinguishing GIST from Non-GIST Tumors (Up to 30 days post-surgery). These are the main endpoints researchers use to determine whether the treatment is effective.
Where is NCT07454967 being conducted?
This trial is being conducted at 9 sites, including Fuyang, Anhui; Baoding, Hebei; Cangzhou, Hebei; Hengshui, Hebei and 5 more sites (China).
Where can I find official information about NCT07454967?
The official record for NCT07454967 is available on ClinicalTrials.gov at https://clinicaltrials.gov/study/NCT07454967. This government database provides the most up-to-date and detailed information about the trial.
What is NCT07454967 testing in simple terms?
This study tests an Artificial Intelligence (AI) tool that combines imaging, pathology, and patient data to help diagnose and assess the risk of gastrointestinal stromal tumors (GISTs). It is for patients with suspected gastric submucosal tumors who are scheduled for surgery or biopsy.
Why is this trial significant?
This trial matters because it aims to develop a faster and more precise way to diagnose and understand the risk of GISTs, potentially reducing the need for invasive tests and guiding treatment decisio
What are the potential risks of participating in NCT07454967?
The AI tool itself does not pose direct risks to patients as it is an observational study and does not alter standard care. Potential risks are associated with the underlying medical conditions and standard procedures like surgery or biopsy, which carry their own risks and side effects. Data privacy and security are important considerations when using AI with patient information. As with any clinical trial, participants are closely monitored and can withdraw at any time.
Should I consider participating in NCT07454967?
Ask your doctor if this AI analysis is being done alongside your standard care and how its findings might be used in the future. Your participation involves allowing researchers to use your CT scans, pathology slides, and clinical data for the AI analysis. This is done in parallel with your regular medical treatment. You will need to provide informed consent to participate. Always discuss clinical trial participation with your healthcare provider to determine if it is appropriate for your specific situation.
What does NCT07454967 signal from an investment perspective?
This trial signals a growing investment in AI for medical diagnostics, particularly for rare cancers like GISTs, with the potential to improve efficiency and accuracy in a competitive field. This is a Not Applicable trial, which is in early development stages.
What happens if the treatment in this trial doesn't work?
Participation involves providing CT scans, pathology slides, and clinical information for the AI to analyze. This is observational, meaning the AI's findings will not change your standard medical care. Participants in clinical trials always have the right to withdraw and pursue alternative treatments. The study team will help transition patients to other available options.
Related Conditions
More Gastrointestinal Stromal Tumors Trials
This analysis is AI-generated and does not constitute medical advice. Always consult your healthcare provider before making decisions about clinical trial participation.