[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"health-study-detail:100658797":3},{"organization":4,"outcomesModule":7,"designInfo":18,"detailedDescription":20,"studyPopulation":21,"armGroups":22,"interventions":28,"overallOfficials":17,"centralContacts":33,"locations":39,"responsibleParty":53,"collaborators":17,"id":57,"slug":58,"hasResults":59,"nctId":60,"briefTitle":61,"officialTitle":62,"acronym":63,"eligibilityCriteria":64,"healthyVolunteers":59,"sex":65,"minAge":66,"maxAge":17,"enrollmentInfo":67,"targetDuration":70,"studyType":71,"phases":17,"briefSummary":72,"conditions":73,"keywords":79,"overallStatus":41,"whyStopped":17,"lastUpdateSubmitDate":85,"lastUpdatePostDateStruct":86,"startDateStruct":89,"completionDateStruct":91,"leadSponsor":93,"locationsCount":94},{"fullName":5,"class":6},"Inha University Hospital","OTHER",{"primaryOutcomes":8,"secondaryOutcomes":13,"otherOutcomes":17},[9],{"measure":10,"description":11,"timeFrame":12},"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.","Baseline",[14],{"measure":15,"description":16,"timeFrame":12},"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.",null,{"allocation":17,"interventionModel":17,"interventionModelDescription":17,"primaryPurpose":17,"observationalModel":19,"timePerspective":6,"maskingInfo":17},"COHORT","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.\n\nThis study is a retrospective, multicenter investigation conducted across multiple tertiary medical centers in South Korea. The primary objectives are:\n\n* To extract and encrypt raw 12-lead ECG data (XML format) into binary datasets to ensure patient privacy and data standardization.\n* 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.\n* To assess the clinical utility and prognostic performance of AI-ECG risk prediction models in real-world cohorts spanning data from 2005 to 2022.","Patients visiting the participating tertiary hospitals with extractable electrocardiogram records and diagnosed with cardiovascular diseases.",[23],{"label":24,"type":17,"description":25,"interventionNames":26},"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.",[27],"Other: Retrospective ECG Data Analysis",[29],{"type":6,"name":30,"description":31,"armGroupLabels":32,"otherNames":17},"Retrospective ECG Data Analysis","Analysis of de-identified 12-lead electrocardiogram raw data using deep learning models for cardiovascular disease diagnosis and prognosis.",[24],[34],{"name":35,"role":36,"phone":37,"phoneExt":17,"email":38},"Yongsoo Baek, MD, PhD","CONTACT","+82-32-890-2200","existsoo@inha.ac.kr",[40],{"facility":5,"status":41,"city":42,"state":42,"zip":43,"country":44,"countryCode":17,"cosmosGeoPoint":45,"geoPoint":50,"contacts":51},"RECRUITING","Incheon","22332","South Korea",{"type":46,"coordinates":47},"Point",[48,49],126.70515,37.45646,{"lat":49,"lon":48},[52],{"name":35,"role":36,"phone":37,"phoneExt":17,"email":38},{"type":54,"investigatorFullName":55,"investigatorTitle":56,"investigatorAffiliation":5,"oldNameTitle":17,"oldOrganization":17},"PRINCIPAL_INVESTIGATOR","Yong-Soo Baek","Professor","100658797","ai-powered-electrocardiography-for-diagnosis-and-prognostic-prediction-in-cardiovascular-disease-ai-cvd-multicenter-retrospective-study-100658797",false,"NCT07856472","AI-Powered Electrocardiography for Diagnosis and Prognostic Prediction in Cardiovascular Disease (AI-CVD): Multicenter Retrospective Study","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","AI-CVD","Inclusion Criteria:\n\n* Patients aged 18 years or older diagnosed with cardiovascular diseases, including coronary artery disease and heart failure.\n* Patients with 12-lead electrocardiogram (ECG) records extractable as text (XML\n\nExclusion Criteria:\n\n\\- Patients deemed inappropriate as study subjects by the investigator's judgment","ALL","18 Years",{"count":68,"type":69},10000,"ESTIMATED","5 Years","OBSERVATIONAL","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.",[74,75,76,77,78],"Cardiovascular Diseases","Coronary Artery Disease","Heart Failure","Atrial Fibrillation (AF)","Ventricular Hypertrophy",[80,81,82,83,84],"Artificial Intelligence","Electrocardiogram","Deep Learning","Multicenter Study","Retrospective Study","2026-09-28",{"date":87,"type":88},"2026-10-02","ACTUAL",{"date":90,"type":88},"2023-03-01",{"date":92,"type":69},"2028-03-01",{"name":5,"class":6},1]