This study aims to evaluate the diagnostic performance and clinical utility of a multimodal medical imaging large model in identifying common systemic diseases. Through a retrospective reader study involving multiple centers, the research will compare the diagnostic accuracy, sensitivity, and specificity of radiologists with and without AI assistance. The goal is to validate the model's robustness and its impact on the diagnostic efficiency of clinicians across diverse healthcare settings.
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.
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.
Patients from multiple medical centers in China who underwent systemic medical imaging for various clinical indications, representing a broad range of common systemic diseases.
Cohort
Retrospective
Standalone Radiologist Interpretation
Other interventionRadiologists interpret the medical images independently without any assistance from the AI model to establish a baseline performance.
AI-assisted Radiologist Interpretation
Other interventionRadiologists interpret the same set of medical images with the assistance of the multimodal medical imaging large model to evaluate the improvement in diagnostic performance.
Area Under the Receiver Operating Characteristic Curve (AUC)
Evaluation of diagnostic accuracy using AUC to compare standalone radiologist performance versus AI-assisted performance.
Mean Reading and Reporting Time per Case
Assessment of diagnostic efficiency by recording the time (in seconds) taken by radiologists to complete the diagnosis and generate reports, with and without AI assistance.
Clinical Report Quality and Semantic Accuracy Score
The quality of AI-generated reports will be evaluated by senior experts using a 5-point Likert scale, focusing on semantic accuracy, clinical relevance, and completeness of the descriptions. The scale ranges from 1 to 5, where 1 indicates "poor quality" and 5 indicates "excellent quality." Higher scores represent better report quality and higher semantic accuracy.
Sensitivity and Specificity
To calculate and compare the sensitivity and specificity of radiologists' diagnostic decisions in both standalone and AI-assisted sessions.
Click on the lead sponsor to view all of their trials.
