Prospective User Study and Multicenter Validation of Multimodal Medical Imaging Large Models

NCT07555002 | Completed

• 1 other identifier: 2025-ER-141
• Study Type: observational
• Target: 310
• Locations: 1 country
• Sites: 1

Brief Summary

Following model development and locking, the fixed model is evaluated in prospectively collected CT cohorts from two centers. The study is observational and does not affect clinical care. A subset of cases is used in a randomized crossover reader study.

Conditions

Diagnostic Imaging; Common Systemic Diseases; Artificial Intelligence (AI)

Keywords

Multimodal Large Model; Deep Learning; Radiology; Multicenter Study; Diagnostic Performance

Outcome Measures

Primary Outcomes (1)

• Case-level Diagnostic Accuracy and Area Under the ROC Curve (AUC)

  Evaluation of case-level diagnostic accuracy (defined as the proportion of diagnostic decisions matching the clinical ground-truth label) and discrimination performance (measured by AUC) to compare unaided radiologist performance versus AI-assisted performance.

  Up to 1 week per evaluation period

Secondary Outcomes (3)

• Diagnostic Efficiency (Reading and Reporting Time)

  Up to 1 week per evaluation period

• Inter-rater Agreement (Fleiss' Kappa)

  Up to 1 week per evaluation period

• Clinical Report Quality and Semantic Accuracy Score

  Up to 1 week per evaluation period

Study Arms (1)

Validation Cohort

Prospective Observational Validation Cohorts CT data are prospectively collected at two centers after model locking and used for observational model validation. A subset is included in the randomized crossover reader study.

Other: Standalone Radiologist Interpretation; Other: AI-assisted Radiologist Interpretation

Interventions

Standalone Radiologist Interpretation OTHER

Radiologists interpret the medical images independently without any assistance from the AI model to establish a baseline performance.

Validation Cohort

AI-assisted Radiologist Interpretation OTHER

Radiologists interpret the same set of medical images with the assistance of the multimodal medical imaging large model to evaluate the improvement in diagnostic performance.

Validation Cohort

Eligibility Criteria

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

Study Population

Patients from multiple medical centers in China who underwent systemic CT imaging for various clinical indications, representing a broad range of common systemic diseases.

You may qualify if:

• Patients who underwent CT examinations 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 may not qualify if:

• 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.

Sponsors & Collaborators

• The Third Affiliated Hospital of Southern Medical University: lead

Study Sites (1)

The Third Affiliated Hospital of Southern Medical University

Guangzhou, Guangdong, 510630, China

Location

Study Officials

• Yinghua Zhao, PhD

  The Third Affiliated Hospital of Southern Medical University

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER GOV
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Scientific Research Administrator

Study Record Dates

• First Submitted: April 21, 2026
• First Posted: April 28, 2026
• Study Start: January 1, 2026
• Primary Completion: June 8, 2026
• Study Completion: July 10, 2026
• Last Updated: August 7, 2026

Record last verified: 2026-08

Data Sharing

• IPD Sharing: Will not share

Locations

CN (1)