Actively Recruiting
Prospective User Study and Multicenter Validation of Multimodal Medical Imaging Large Models in the Diagnosis of Common Systemic Diseases
Led by The Third Affiliated Hospital of Southern Medical University · Updated on 2026-05-08
1000
Participants Needed
1
Research Sites
N/A
Total Duration
On this page
AI-Summary
What this Trial Is About
Researchers are evaluating the diagnostic ability and clinical usefulness of a multimodal medical imaging large model to identify common systemic diseases. This observational study involves multiple centers and compares radiologists' accuracy, sensitivity, and specificity when interpreting images with and without AI assistance. The goal is to confirm the model's reliability and its effect on improving diagnostic efficiency across diverse healthcare settings. The study uses a large retrospective dataset of medical images, including CT and MRI scans, collected from various institutions. Licensed radiologists will review these images in two sessions: one without AI help and another with AI assistance, separated by a washout period. The model was pre-trained on about 1,000,000 cases, and here it will be validated using an independent test group of 1,000 cases. Participants are not directly involved as this is a retrospective study using anonymized data. Researchers will measure diagnostic accuracy using the Area Under the Receiver Operating Characteristic Curve (AUC), along with sensitivity, specificity, and average reading time per case. Clinical report quality and semantic accuracy will also be assessed. The study will last approximately 12 months and does not affect patient treatment.
CONDITIONS
Brief Title
Prospective User Study and Multicenter Validation of Multimodal Medical Imaging Large Models
Who Can Participate
Eligibility Criteria
You may qualify if you...
- Patients who underwent systemic medical imaging examinations (e.g., CT or MRI) at participating centers for common systemic diseases.
- Imaging data must have confirmed clinical reference standards, expert consensus, or pathological diagnosis.
- Availability of complete DICOM format images with standard acquisition protocols.
You will not qualify if you...
- Poor image quality (e.g., severe motion or metal artifacts) that precludes definitive diagnosis.
- Cases with incomplete clinical or pathological reference standards.
- Corrupted image files or duplicate cases.
AI-Screening
AI-Powered Screening
Complete this quick 3-step screening to check your eligibility
Your Study Journey
Duration - 2 to 4 weeks
Participants are screened for eligibility to participate in the trial.
1 visit (in-person)
Duration - Approximately 12 months
Participants' medical images are evaluated by radiologists without AI assistance and then with AI assistance after a washout period to assess diagnostic accuracy and efficiency.
2 separate reading sessions per participant with a washout period in between
Duration - Through study completion, approximately 12 months
Data analysis and comparison of diagnostic performance metrics including accuracy, sensitivity, specificity, and reading time are conducted.
No participant visits required
Trial Site Locations
Total: 1 location
1
The Third Affiliated Hospital of Southern Medical University
Guangzhou, Guangdong, China, 510630
Actively Recruiting
Research Team
T
Tao Li, MD
How is the study designed?
Study Type
OBSERVATIONAL
Masking
N/A
Allocation
N/A
Model
N/A
Primary Purpose
N/A
Number of Arms
1
Similar Trials
Frequently Asked Questions
Have more questions? Get in touch with our team for quick support
Not the Right Trial for You?
Explore thousands of other clinical trials that might be a better match.
Sign up to get personalized trial recommendations delivered to your inbox.
Already have an account? Log in here