ClinicalTrials.gov record NCT06748261
AI-enabled Screening and Diagnosis of Cardiomyopathies Using Coronary CTA
Artificial Intelligence-enabled Screening and Diagnosis of Cardiomyopathies Using Coronary Computer Tomography Angiography
AI summaryWhat this study is about, in plain languageShow ▾Hide ▴
AI-written from the registry record, not the study's own wording. May contain errors or omissions. Check the registry text on this page and the original record ↗ before acting on it.
This observational, diagnostic study uses coronary CT angiography (CCTA) images to develop and validate artificial-intelligence (AI) models for screening and multi-class diagnosis of cardiomyopathies. It compares CCTA images from a cardiomyopathy cohort (those with clinical diagnoses) and a control cohort (those without cardiovascular disease). The study trains AI models and evaluates their diagnostic performance in internal and external validation sets using measures such as sensitivity, specificity, AUC and F1 score.
What it is studying. The study is testing whether an AI-based approach applied to coronary CT angiography (CCTA) can (1) screen for cardiac abnormalities versus normal controls and (2) produce multi-class diagnostic outputs distinguishing different cardiomyopathy types. Investigators will develop models on labeled CCTA images (labels come from patients' clinical records and available imaging/biopsy data) and measure model accuracy with standard diagnostic metrics.
What the researchers hope to learn. To develop and validate AI-assisted CCTA tools for screening and diagnosing multiple types of cardiomyopathy, and to measure their diagnostic performance (sensitivity, specificity, AUC, F1 score, and related metrics).
What this study is about
The study's own summary, as published on ClinicalTrials.gov. Underlined terms have a short explanation.
The goal of this observational and diagnostic study is to develop and validate an artificial intelligence assisted approach for coronary computer tomography angiography-(CCTA)-based screening and diagnosis of cardiomyopathies in patients with suspected coronary artery diseases. This study aims to develop a computerized CCTA interpretation using artificial intelligence for multi-label classification task to assist cardiomyopathy diagnosis in the clinical workflow.
Interventions being studied
Being studied in this trial does not mean the treatment or procedure is approved or available for this condition.
- Diagnostic test
- CCTAI model
Eligibility
The criteria exactly as listed on ClinicalTrials.gov. Only the study team can say whether they apply to you.
Inclusion criteria
- Cardiomyopathy cohort:
- A clinical diagnosis of cardiomyopathies, including hypertrophic cardiomyopathy, dilated cardiomyopathy, restrictive cardiomyopathy, cardiac amyloidosis, myocarditis, arrhythmogenic right ventricular cardiomyopathy, and coronary artery disease/ischemic heart disease.
- At least one CCTA before surgery or implantable device treatment.
Exclusion criteria
- No recorded diagnosis of cardiomyopathy or undetermined type of cardiomyopathy.
- A clinical diagnosis of secondary cardiac abnormalities due to other organic or systemic diseases.
- Surgery or implantable device treatment before CCTA examination.
- Control cohort:
- Inclusion Criteria: participants with at least one CCTA examination.
- Exclusion Criteria: clinical diagnosis of cardiovascular diseases (including cardiomyopathy, history of myocardial infarction, history of cardiac surgery, stent implantation, ICD implantation and so on) or secondary cardiac abnormalities due to systemic diseases.
Study description and what participation involves
The study's detailed description, as published on ClinicalTrials.gov.
Show the detailed description from the registry
Cardiovascular diseases (CVD) are the leading causes of death and disability worldwide. With coronary artery disease accounting for a large proportion of CVD disease burden, coronary computer tomography angiography (CCTA) has become widely used for a comprehensive assessment of the total coronary atherosclerotic burden. In contrast, cardiac magnetic resonance (CMR) remains the gold standard for evaluating and diagnosing cardiomyopathies. However, clinical application of CMR has been hindered by the time and cost of examination and shortage of qualified doctors and staff. Consequently, the value of CCTA in screening and diagnosis in cardiomyopathies warrants further investigation. The ability of artificial intelligence to learn distinctive features and to recognize characteristic patterns on big data without extensive manual labor makes it highly effective for interpreting CCTA data. Although very few studies investigated the diagnostic value of CCTA for myocardiopathies, which is by far not established or applied in clinical practice by radiologists, automated image analysis has a clear advantage compared to humans by offering objective and uniform solutions. Further, whether a comprehensive, end-to-end, artificial intelligent approach can be used to analyse CCTA for diagnosis multi-classifications of cardiomyopathies remains unknown. Therefore, this study aims to develop and validate an artificial intelligence assisted approach on CCTA for screening and diagnosis of cardiomyopathies in patients with suspected coronary artery diseases.
AI summaryWhat participation may involve, in plain languageShow ▾Hide ▴
AI-written from the registry record, not the study's own wording. May contain errors or omissions. Check the registry text on this page and the original record ↗ before acting on it.
The study uses existing CCTA scans and participants' electronic medical records. Researchers will analyze those imaging and clinical records with an AI-based CCTA interpretation (the CCTAI model) and compare the AI results to the recorded clinical diagnoses for model development and validation. The registry describes internal and external validation of the models. The record does not specify additional procedures, invasive tests, or extra study visits beyond use of the CCTA images and medical record data.
How the study is structured. An observational case-control, cross-sectional study that analyzes CCTA exams collected from people with documented cardiomyopathies and from controls without cardiovascular disease. No new treatments are given; existing CCTA images and medical records are used to train and test AI diagnostic models. Model performance will be checked in separate internal and external validation groups.
Questions you could ask
These questions are suggestions for a conversation with the study team or your own clinician, not advice.
- This is an observational study, so the study itself gives no treatment. What would taking part involve for me, and would it change my usual care?
- The registry says recruitment has not started. When is it expected to open, and can I register interest now?
- No sites are listed on the registry yet. Where will the study take place?
- Which of the eligibility criteria would need to be checked with tests before I could join?
More on wild-type ATTR amyloidosis
This trial is also listed on this site under ATTRv amyloidosis.
Important dates
- Study start
- Dec 30, 2024 (estimated)
- Primary completion
- Jun 30, 2025 (estimated)
- Study completion
- Dec 30, 2025 (estimated)
- Target enrollment
- 5000 participants (estimated)
- Last updated on registry
- Dec 27, 2024
- Data verified
- Oct 10, 2026
Sponsor and research team
The lead sponsor funds and oversees the trial. A pharmaceutical or biotech company sponsor typically means the study is testing that company's drug or device; a hospital, university, or government agency usually indicates investigator-initiated or publicly funded research.
- Lead sponsor
- Shanghai Zhongshan Hospital
- Principal investigator
- Junbo Ge, Prof
Shanghai Zhongshan Hospital
Central study contact
If you're interested in participating, the central contact can answer general questions about the study — including eligibility requirements and how to find a recruiting site near you. Actual eligibility is determined by the site's medical team.
- Junbo Ge, MD, PhD 📞 008664041990 ✉ jbge@zs-hospital.sh.cn
- Chenguang Li, MD, PhD ✉ li.chenguang@zs-hospital.sh.cn
Participating sites
Study locations have not been posted on ClinicalTrials.gov yet. This study is not yet recruiting, so sites may be added when recruitment begins. The central study contact above may be able to tell you about planned sites.
Terms used on this page · explanations by MedicalUpdates.ai
- cohort
- A group of people who share a characteristic, such as a diagnosis, and are studied together. 'Prospective' means they are followed forward from enrolment; 'retrospective' means existing records are reviewed.
- Inclusion Criteria
- The conditions a person must meet to be considered for the study, for example a confirmed diagnosis, an age range or a test result.
- Exclusion Criteria
- The conditions that rule a person out even if they meet the inclusion criteria, for example other illnesses, certain medicines or pregnancy.
The study record on this page is reproduced from ClinicalTrials.gov, a database of the U.S. National Library of Medicine, where it was submitted by the study sponsor. MedicalUpdates.ai does not own this content, is not affiliated with or endorsed by ClinicalTrials.gov, NIH, or the U.S. Government, and does not verify the record. Plain-language notes, the glossary and the questions above are added by this site; text in the boxes marked "AI summary" was written by an AI model and may contain errors. Registry records change over time. Check the original record for the current version and discuss eligibility or participation with a qualified healthcare professional.
← Back to clinical trials