AI-Based Differential Diagnosis and Localization of Tachycardia Using ECG: Multicenter Registry (EP-AI ASSIST) (EP-AI ASSIST)

October 28, 2026 updated by: Yong-Soo Baek, Inha University Hospital

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

Recruiting

Conditions

Intervention / Treatment

Study Type

Observational

Enrollment (Estimated)

10000

Contacts and Locations

This section provides the contact details for those conducting the study, and information on where this study is being conducted.

Study Contact

Study Locations

    • Incheon
      • Incheon, Incheon, South Korea, 22332
        • Recruiting
        • Inha University Hospital
        • Contact:

Participation Criteria

Researchers look for people who fit a certain description, called eligibility criteria. Some examples of these criteria are a person's general health condition or prior treatments.

Eligibility Criteria

Ages Eligible for Study

19 years and older (Adult, Older Adult)

Accepts Healthy Volunteers

No

Genders Eligible for Study

All

Sampling Method

Non-Probability Sample

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

This section provides details of the study plan, including how the study is designed and what the study is measuring.

How is the study designed?

Design Details

  • Observational Models: COHORT
  • Time Perspectives: RETROSPECTIVE

Cohorts and Interventions

Group / Cohort
Intervention / 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

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

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

This is where you will find people and organizations involved with this study.

Sponsor

Study record dates

These dates track the progress of study record and summary results submissions to ClinicalTrials.gov. Study records and reported results are reviewed by the National Library of Medicine (NLM) to make sure they meet specific quality control standards before being posted on the public website.

Study Major Dates

Study Start (Actual)

December 1, 2023

Primary Completion (Estimated)

December 1, 2028

Study Completion (Estimated)

December 1, 2028

Study Registration Dates

First Submitted

September 29, 2026

First Submitted That Met QC Criteria

September 29, 2026

First Posted (Actual)

October 5, 2026

Study Record Updates

Last Update Posted (Actual)

October 30, 2026

Last Update Submitted That Met QC Criteria

October 28, 2026

Last Verified

October 1, 2026

More Information

Terms related to this study

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)?

NO

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

No

Studies a U.S. FDA-regulated device product

No

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.