Evaluation of Deep Learning ECG Algorithm to Detect Left Ventricular Systolic Dysfunction in Adults Undergoing Echocardiography at Ajou University Hospital
Led by Ajou University School of Medicine · Updated on 2026-08-07
1500
Participants Needed
1
Research Sites
N/A
Total Duration
AI-Summary
What This Trial Is About
Researchers are evaluating the clinical performance of a deep learning-based electrocardiography ECG algorithm called DeepECG LVSD to detect left ventricular systolic dysfunction LVSD, defined as a left ventricular ejection fraction LVEF of 40% or less. The study focuses on adult patients who have undergone both ECG and transthoracic echocardiography, which is the standard method for assessing LVEF but limited by cost and availability. This prospective observational cohort study aims to provide real-world evidence on the accuracy and clinical utility of the AI algorithm.
Approximately 15,000 adult patients aged 19 years or older who had ECG and echocardiography performed within 30 days at Ajou University Hospital will be enrolled. There is no intervention or treatment given as part of the study. Instead, the AI algorithms diagnostic performance will be assessed by comparing its predictions to echocardiographic measurements. Secondary analyses will explore the relationship between AI-predicted LVSD and short-term clinical outcomes such as 30-day all-cause mortality, emergency department visits, and heart failure rehospitalization.
Participants will undergo routine clinical procedures including ECG and echocardiography, with data collected for analysis. Researchers will evaluate the accuracy of the AI tool using measures like the area under the receiver operating characteristic curve AUROC, sensitivity, and specificity. Additional subgroup analyses will consider factors like age, sex, and medical conditions. The study is designed as a minimal-risk observational study and will contribute to understanding AI-based ECG screenings role in early detection of patients at risk for heart failure.
CONDITIONS
Brief Title
AI ECG Algorithm for Detecting LV Systolic Dysfunction
Research Team
M
MOONSEUNG SOH, MD
Not the Right Trial for You?
Explore thousands of other clinical trials that might be a better match. Sign up to get personalized trial recommendations delivered to your inbox.
Patients who underwent both transthoracic echocardiography and 12-lead electrocardiography (ECG) at Ajou University Hospital in outpatient, inpatient, or emergency settings
ECG and echocardiography performed within 30 days of each other
You will not qualify if you...
Interval between ECG and echocardiography greater than 30 days
Missing or corrupted original ECG waveform data (XML or HL7 format)
Presence of implanted cardiac devices such as permanent pacemaker, implantable cardioverter-defibrillator (ICD), or cardiac resynchronization therapy (CRT) device
Missing age, sex, or left ventricular ejection fraction (LVEF) data
Your Study Journey
Screening
Duration - 2 to 4 weeks
Participants are screened for eligibility to participate in the trial.
1 visit (in-person or remote) for eligibility assessment
Observation
Duration - Up to 30 days
Participants undergo routine ECG and echocardiography as part of their clinical care. Data from these tests are collected and analyzed using the AI algorithm to evaluate heart function.
1 to 2 clinical visits for ECG and echocardiography
Follow-up
Duration - 30 days after ECG and echocardiography
Researchers monitor clinical outcomes including 30-day all-cause mortality, emergency department visits, and heart failure rehospitalization to assess the AI algorithm's predictive value.
Follow-up via medical records or clinical contacts
How is the study designed?
Study Type
OBSERVATIONAL
Masking
N/A
Allocation
N/A
Model
N/A
Primary Purpose
N/A
Number of Arms
1
Similar Trials
Study of Lying-Sitting-Standing Sequential Baduanjin on Heart and Lung Function and Quality of Life in Patients with Acute Coronary Syndrome and Heart Failure
Evaluation of Deep Learning ECG Algorithm to Detect Left Ventricular Systolic Dysfunction in Adults Undergoing Echocardiography at Ajou University Hospital
Have more questions? Get in touch with our team for quick support
Published Research Related To This Trial
A multicenter pragmatic implementation study of AI-ECG-based clinical decision support software to identify low LVEF: Clinical trial design and methods.
Francisco Lopez-Jimenez, Heather M Alger, Zachi I Attia...