AI Assisted Screening for VHD Using Routine Chest CT Scans

This is a prospective, multicenter study designed to validate a deep learning model for screening valvular heart diseases using routine, non-contrast chest computed tomography (CT) scans. The primary objective is to evaluate the model's diagnostic performance, with the sensitivity serving as the primary efficacy endpoint. Secondary endpoints will include other performance metrics such as area under the receiver operating characteristic curve (AUC), specificity, and accuracy, etc.

NCT Number	NCT07449130
Lead Sponsor	Second Affiliated Hospital, School of Medicine, Zhejiang University
Conditions	Heart Valve Diseases
Enrollment	3,000 participants
Start Date	2026-03-02
Primary Completion	2026-11-01 (estimated)
Study Completion	2026-11-01 (estimated)
Updated on ClinicalTrials.gov	2026-05-12