AI-Based Differential Diagnosis and Localization of Tachycardia Using ECG: Multicenter Registry (EP-AI ASSIST) (EP-AI ASSIST)
AI-based Differential Diagnosis and Localization of Tachycardia Using ECG: Multicenter Registry (EP-AI ASSIST)
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.
Study Overview
Status
Status
Conditions
Conditions
Intervention / Treatment
Intervention / Treatment
Study Type
Study Type
Enrollment (Estimated)
Enrollment
Contacts and Locations
Study Contact
Study Contact
- Name: Yongsoo Baek, MD, PhD
- Phone Number: +82-32-890-2200
- Email: existsoo@inha.ac.kr
Study Locations
-
-
Incheon
-
Incheon, Incheon, South Korea, 22332
- Recruiting
- Inha University Hospital
-
Contact:
- Yongsoo Baek, MD, PhD
- Phone Number: +82-32-890-2200
- Email: existsoo@inha.ac.kr
-
-
Participation Criteria
Eligibility Criteria
Eligibility Criteria
Ages Eligible for Study
Accepts Healthy Volunteers
Genders Eligible for Study
Sampling Method
Study Population
Retrospective cohort of patients aged 19 years or older with PSVT, WPW syndrome, PVC, or VT who underwent electrophysiological study and catheter ablation at participating institutions between January 2005 and December 2023.
Description
Inclusion Criteria:
- Age 19 years or older
- Diagnosis of one of the following arrhythmias: paroxysmal supraventricular tachycardia (PSVT), Wolff-Parkinson-White (WPW) syndrome, premature ventricular contractions (PVC), or ventricular tachycardia (VT)
- Underwent an electrophysiological study (EPS) and catheter ablation
- Available 12-lead electrocardiogram (ECG) records that can be extracted as text (XML) files
Exclusion Criteria:
- Inadequate ECG data quality, as judged by the investigator
- Missing medical records required for the study, as judged by the investigator
Study Plan
How is the study designed?
Design Details
- Observational Models: COHORT
- Time Perspectives: RETROSPECTIVE
Number of groups / cohorts
Cohorts and Interventions
Group / CohortGroup / Cohort |
Intervention / TreatmentIntervention / Treatment |
|---|---|
|
Cardiovascular Disease and Tachycardia Cohort
Patients aged 19 years or older diagnosed with tachycardias (including PSVT, WPW syndrome, PVC, or VT) who underwent an electrophysiological study (EPS) and radiofrequency catheter ablation (RFCA), with extractable 12-lead ECG text data[cite: 1]. |
Application of a deep learning-based 12-lead electrocardiogram (ECG) algorithm to analyze raw text data for the differential diagnosis and localization of tachycardias, including PSVT, WPW syndrome, PVC, and VT[cite: 1]. |
What is the study measuring?
Primary Outcome Measures
Primary Outcome Measures
Outcome Measure |
Measure Description |
Time Frame |
|---|---|---|
|
Area Under the ROC Curve (AUC) of AI-ECG Models for Differentiating Tachycardia Mechanisms Confirmed by Electrophysiological Study
Time Frame: Baseline
|
Diagnostic performance of Transformer-based deep learning models applied to 12-lead ECG raw data for differentiating tachycardia mechanisms, including atrioventricular nodal reentrant tachycardia (AVNRT) versus atrioventricular reentrant tachycardia (AVRT). The reference standard is the diagnosis confirmed by electrophysiological study and catheter ablation. Performance is summarized as AUC with 95% confidence interval (range 0-1; higher values indicate better discrimination). |
Baseline
|
Secondary Outcome Measures
Secondary Outcome Measures
Outcome Measure |
Measure Description |
Time Frame |
|---|---|---|
|
Area Under the ROC Curve (AUC) of AI-ECG Models for Localizing Arrhythmia Origin Sites (Accessory Pathway, PVC, and VT) Confirmed by Successful Catheter Ablation
Time Frame: Baseline
|
Performance of AI-ECG models in classifying the anatomical site of the arrhythmia substrate from the pre-ablation 12-lead ECG, including (1) accessory pathway location in Wolff-Parkinson-White syndrome, (2) the origin of premature ventricular contractions, and (3) the origin of ventricular tachycardia. The reference standard is the site identified by electrophysiological mapping and confirmed by successful catheter ablation. For each classification task, performance is reported as AUC with 95% confidence interval (range 0-1; higher values indicate better classification). |
Baseline
|
Collaborators and Investigators
Sponsor
Sponsor
Study record dates
Study Major Dates
Study Start (Actual)
Study Start
Primary Completion (Estimated)
Primary Completion
Study Completion (Estimated)
Study Completion
Study Registration Dates
First Submitted
First Submitted
First Submitted That Met QC Criteria
First Submitted That Met QC Criteria
First Posted (Actual)
First Posted
Study Record Updates
Last Update Posted (Actual)
Last Update Posted
Last Update Submitted That Met QC Criteria
Last Update Submitted That Met QC Criteria
Last Verified
Last Verified
More Information
Terms related to this study
Additional Relevant MeSH Terms
- Cardiac Conduction System Disease
- Cardiovascular Diseases
- Pathologic Processes
- Heart Diseases
- Arrhythmias, Cardiac
- Congenital Abnormalities
- Cardiovascular Abnormalities
- Heart Defects, Congenital
- Cardiac Complexes, Premature
- Pre-Excitation Syndromes
- Congenital, Hereditary, and Neonatal Diseases and Abnormalities
- Pathological Conditions, Signs and Symptoms
- Tachycardia
- Tachycardia, Ventricular
- Ventricular Premature Complexes
- Wolff-Parkinson-White Syndrome
Other Study ID Numbers
Other Study ID Numbers
- 2023-12-033
- 2023-12-033 (Registry Identifier: Inha University Hospital Institutional Review Board)
Plan for Individual participant data (IPD)
Plan to Share Individual Participant Data (IPD)?
IPD Plan Description
Individual participant data (IPD) will not be shared with other researchers due to institutional data privacy policies and ethical regulations concerning retrospective clinical records and encrypted electrocardiogram data.
Drug and device information, study documents
Studies a U.S. FDA-regulated drug product
Studies a U.S. FDA-regulated device product
This information was retrieved directly from the website clinicaltrials.gov without any changes. If you have any requests to change, remove or update your study details, please contact register@clinicaltrials.gov. As soon as a change is implemented on clinicaltrials.gov, this will be updated automatically on our website as well.