Cardiovascular DiseasesAI-CVDNCT07856472
AI-Powered Electrocardiography for Diagnosis and Prognostic Prediction in Cardiovascular Disease (AI-CVD): Multicenter Retrospective Study
An observational study of Cardiovascular Diseases and Coronary Artery Disease, run by Inha University Hospital at 1 site in South Korea.
Trial summary
This multicenter retrospective study aims to develop, validate, and clinically apply an artificial intelligence (AI)-powered electrocardiography (ECG) algorithm for the diagnosis and prognostic prediction of cardiovascular diseases, including coronary artery disease and heart failure. Read more about this study
- Who is it for?
- Ages 18 years and older
- Conditions the study is for
- Cardiovascular Diseases, Coronary Artery Disease, Heart Failure
- What is being tested?
- Retrospective ECG Data Analysis
- How many people
- 10,000 participants
- Where
- 1 siteSouth Korea
- Study dates
- 1 Mar 2023to 1 Mar 2028
- How long will I take part?
- 5 Years
- Phase
- Observational
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages 18 years and older
- All sexes
- No healthy volunteers
- Adult, Older adult
Study population: Patients visiting the participating tertiary hospitals with extractable electrocardiogram records and diagnosed with cardiovascular diseases.
Who may be able to join
- Patients aged 18 years or older diagnosed with cardiovascular diseases, including coronary artery disease and heart failure.
- Patients with 12-lead electrocardiogram (ECG) records extractable as text (XML
Who cannot join
- Patients deemed inappropriate as study subjects by the investigator's judgment
Trial locations and contacts
1 site in 1 country. Contact the study team or a site near you to ask about taking part.
South Korea1 site, 1 recruiting
- Recruiting
Inha University Hospital
Incheon, Incheon, 22332
Yongsoo Baek, MD, PhD, +82-32-890-2200, existsoo@inha.ac.kr
About this study
Official title: Research for the Development and Clinical Application of Artificial Intelligence-powered Electrocardiography for Diagnosis and Prognostic Prediction in Cardiovascular Disease (AI-CVD): Multicenter Retrospective Study
This multicenter retrospective study aims to develop, validate, and clinically apply an artificial intelligence (AI)-powered electrocardiography (ECG) algorithm for the diagnosis and prognostic prediction of cardiovascular diseases, including coronary artery disease and heart failure. By utilizing encrypted raw 12-lead ECG text data and deep neural network models, the study evaluates the effectiveness of AI-enhanced ECG in detecting cardiac abnormalities and predicting clinical outcomes.
Read the detailed description
Cardiovascular diseases (CVDs) remain a leading cause of global morbidity and mortality. Standard 12-lead ECGs are widely accessible tools for cardiovascular screening and diagnosis; however, traditional visual interpretations have limitations. Recent advancements in deep learning offer unprecedented performance in extracting hidden patterns from ECG signals.
This study is a retrospective, multicenter investigation conducted across multiple tertiary medical centers in South Korea. The primary objectives are:
- To extract and encrypt raw 12-lead ECG data (XML format) into binary datasets to ensure patient privacy and data standardization.
- To advance and validate deep neural network models-specifically combining Bi-LSTM and attention mechanisms-for diagnosing conditions such as coronary artery disease, heart failure, and related structural heart diseases.
- To assess the clinical utility and prognostic performance of AI-ECG risk prediction models in real-world cohorts spanning data from 2005 to 2022.
- Conditions
- Cardiovascular Diseases, Coronary Artery Disease, Heart Failure, Atrial Fibrillation (AF), Ventricular Hypertrophy
- Being tested
- Retrospective ECG Data Analysis
- Keywords
- Artificial Intelligence, Electrocardiogram, Deep Learning, Multicenter Study, Retrospective Study
- Medical subject headings
- Cardiovascular Diseases, Coronary Artery Disease, Heart Failure, Atrial Fibrillation
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
Retrospective ECG Data AnalysisOther
Analysis of de-identified 12-lead electrocardiogram raw data using deep learning models for cardiovascular disease diagnosis and prognosis.
| Study group | Role | What they receive |
|---|---|---|
| Cardiovascular Disease Cohort | Patients aged 18 years or older diagnosed with cardiovascular diseases, including coronary artery disease and heart failure, who have extractable text-format (XML) 12-lead electrocardiogram records. Receives: Other: Retrospective ECG Data Analysis |
What is being measured
The primary outcome is the main question the study is designed to answer.
Diagnostic Performance (AUC-ROC) of AI-ECG Models
To evaluate the area under the receiver operating characteristic curve (AUC-ROC) of the deep neural network-based 12-lead ECG model for diagnosing cardiovascular diseases compared to reference clinical standards.
Measured: Baseline
Secondary outcomes (1)
Sensitivity and Specificity of AI-ECG Models
To evaluate the association between AI-ECG risk scores and long-term clinical outcomes, including all-cause mortality and heart failure-related hospitalizations.
Measured: Baseline
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted2 Oct 2026
- Study start1 Mar 2023
- Primary completion1 Mar 2028 (estimated)
- Study completion1 Mar 2028 (estimated)
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Other trials for Cardiovascular DiseasesStudies of the same condition, open and under way.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Observational
- Observational model
- Cohort
- Time perspective
- Other
- Enrolment
- 10,000 participants (estimated)
- Target duration
- 5 Years
Sponsor and investigators
- Lead sponsor
- Inha University Hospital
- Sponsor type
- University, hospital or other
- Responsible party
- Principal investigator, Yong-Soo Baek, Inha University Hospital
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07856472
- Sponsor's protocol ID
- 2023-03-024
- Other IDs
- 2023-03-024
- Acronym
- AI-CVD
- Status last verified
- Sep 2026
- First submitted
- 28 Sep 2026
- Last updated
- 2 Oct 2026
- Results posted
- No
- Data monitoring committee
- No
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- No: Data are not available due to institutional policy and patient privacy regulations regarding retrospective clinical records.