Deep Learning CAD Screening on Chest CT

NCT07181512 | Recruiting DMC

• 1 other identifier: CAD-AI-2025-V1.0
• Study Type: observational
• Target: 200
• Locations: 1 country
• Sites: 2

Brief Summary

Coronary artery disease (CAD) is one of the leading causes of death worldwide. Many people have early atherosclerosis without symptoms, and some may develop significant coronary stenosis before any warning signs appear. Identifying high-risk individuals at an early stage is important to prevent heart attacks and other cardiovascular events. Coronary CT angiography (CCTA) can directly evaluate plaque type and the degree of narrowing in the coronary arteries, but it is expensive, requires contrast injection, and involves higher radiation, making it unsuitable for large-scale screening. In contrast, non-contrast chest CT is widely used for health check-ups and lung disease follow-up. Such scans often provide clear views of certain coronary segments, which creates an opportunity to screen for CAD without additional cost or risk. This multicenter study aims to develop and validate deep learning models to analyze coronary calcified segments that are visible on non-contrast chest CT. Two main objectives are: (1) to predict whether calcified segments contain mixed plaque components (both calcified and non-calcified); and (2) to predict whether these segments have significant narrowing (≥50% stenosis) as determined by CCTA. The study will also describe how often ≥50% stenosis is found in non-calcified segments, in order to demonstrate their low-risk nature. The study includes retrospective data collected between 2015 and 2024, and a prospective external validation cohort starting in 2025. Approximately 1,417 patients with paired chest CT and CCTA have already been included for model development and testing. An additional 200 or more patients will be prospectively recruited for external validation. This research may provide evidence that deep learning applied to routine non-contrast chest CT can serve as an opportunistic tool for early CAD risk screening in the general population.

Conditions

Coronary Artery Disease; Coronary Artery Stenosis Stent

Keywords

Coronary Artery Disease; Non-contrast Chest CT; Coronary CT Angiography; Opportunistic Screening; Artificial Intelligence

Outcome Measures

Primary Outcomes (2)

• Accuracy of plaque composition prediction

  Discrimination ability of the deep learning model to classify calcified coronary segments as purely calcified or mixed plaque, using CCTA as the reference standard. Evaluated with AUC, sensitivity, specificity.

  Baseline non-contrast chest CT to reference CCTA (within 30 days)

• Accuracy of ≥50% stenosis prediction

  Discrimination ability of the deep learning model to predict ≥50% luminal stenosis in calcified coronary segments, using CCTA as the reference standard. Evaluated with AUC, sensitivity, specificity, PPV, NPV.

  Baseline non-contrast chest CT to reference CCTA (within 30 days)

Secondary Outcomes (1)

• Incidence of ≥50% stenosis in non-calcified segments

  Baseline non-contrast chest CT to CCTA (within 30 days)

Study Arms (1)

Patients undergoing non-contrast chest CT and CCTA

A cohort of patients who underwent both non-contrast chest CT and coronary CT angiography (CCTA) within 30 days. Clearly visualized coronary segments will be analyzed at the segment level for plaque composition and ≥50% stenosis using deep learning models. Both retrospective (2015-2024) and prospective (2025) cases are included.

Other: Deep Learning Analysis of Non-contrast Chest CT

Interventions

Deep Learning Analysis of Non-contrast Chest CT OTHER

Analysis of clearly visualized coronary segments on non-contrast chest CT using deep learning models, compared with CCTA reference standard.

Patients undergoing non-contrast chest CT and CCTA

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 undergoing non-contrast chest CT and CCTA, either during outpatient or inpatient clinical care, or as part of high-risk health examinations. Both retrospective cases (2015-2024) and prospectively recruited patients (2025) are included from five medical centers in China.

You may qualify if:

• Age ≥18 years
• Patients who underwent both non-contrast chest CT and coronary CT angiography (CCTA) within 30 days
• Coronary segments clearly visualized on non-contrast chest CT

You may not qualify if:

• Segments with motion artifacts, metal artifacts, or stents preventing analysis
• Vessel lumen completely obscured by calcification (unrecognizable vascular course)
• Inability to match coronary segment location between non-contrast chest CT and CCTA

Sponsors & Collaborators

• The Second Affiliated Hospital of Fujian Medical University: collaborator
• Yifan Guo: lead
• First Affiliated Hospital of Ningbo University: collaborator
• Jinhua Municipal Central Hospital: collaborator

Study Sites (2)

The First Affiliated Hospital of Zhejiang Chinese Medical University

Hangzhou, Zhejiang, 310006, China

RECRUITING

The First Affiliated Hospital of Ningbo University

Ningbo, Zhejiang, 315000, China

RECRUITING

MeSH Terms

Conditions

Coronary Artery Disease

Condition Hierarchy (Ancestors)

Coronary Disease; Myocardial Ischemia; Heart Diseases; Cardiovascular Diseases; Arteriosclerosis; Arterial Occlusive Diseases; Vascular Diseases

Central Study Contacts

Yifan Guo, MD

CONTACT

+86-18072947783; 20193071@zcmu.edu.cn

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: OTHER
• Target Duration: 1 Year
• Sponsor Type: OTHER GOV
• Responsible Party: SPONSOR INVESTIGATOR
• PI Title: Lecturer, Department of Radiology, First Affiliated Hospital of Zhejiang Chinese Medical University

Study Record Dates

• First Submitted: September 11, 2025
• First Posted: September 18, 2025
• Study Start: September 1, 2025
• Primary Completion: April 20, 2026
• Study Completion (Estimated): December 31, 2027
• Last Updated: February 17, 2026

Record last verified: 2026-02

Data Sharing

• IPD Sharing: Will not share

Locations

CN (2)