CClinicalTrials.gg
CompletedNCT04996381AI-CXRUpdated Sep 14, 2022

Feasibility of AI-based Heart Function Prediction Model Using CXR

An observational study in Chest X-ray for Clinical Evaluation, sponsored by Yonsei University. Completed at 1 site in Korea, Republic of. Open to participants aged 20 Years to 90 Years. Per ClinicalTrials.gov, last updated 2022-09-14.

Sponsored by Yonsei University · Observational

Study type
Observational
Model
Cohort
Time perspective
Prospective
Enrollment
505
Ages
20 Years to 90 Years
Sex
All
01

Study summary

The investigators will develop an artificial intelligence model to predict left ventricular ejection fraction using chest radiographic images and transthoracic echocardiography data.

Read the detailed description

Echocardiography should be considered at an early stage in patients who have first developed heart failure or who do not have information about heart function, but the examination may be delayed due to lack of time and manpower in the actual medical field.

Primary Objective: Use chest radiographs to predict the left ventricular ejection fraction

02

Conditions studied

  • Chest X-ray for Clinical Evaluation
03

In context

Lead sponsor

Yonsei University is the lead sponsor of 1,387 studies on the registry; 232 are open to participants now.

Counted across the registry records on this site, refreshed daily.

04

Who can participate

Ages eligible
20 Years to 90 Years
Sexes eligible
All
Accepts healthy volunteers
No
Sampling method
Non-probability sample

Study population

Patients undergoing a transthoracic echocardiogram will be enrolled.

Inclusion criteria

  • Adults who are 20 years and older
  • Patient who visited the emergency room or outpatient clinic due to dyspnea and chest pain

Exclusion criteria

Exclusion Criteria:

  • Patient refusal
  • Uncertain radiographs or transthoracic echocardiography
  • Uncertain tests results
05

Study design

Observational model
Cohort
Time perspective
Prospective
Enrollment
505 participants (actual)
Patient registry
No

Interventions

  • Diagnostic testScanning Chest X-rays and performing AI algorithms on images

    Chest X-Rays; AI CNNs; Results

06

What researchers measure

Primary outcomes

  1. Left Ventricular Ejection Fraction < 40%

    Evaluate the performance of chest X-ray based artificial intelligence algorithms to identify individuals with reduced ejection fraction (\<40%)

    Time frame: Within two weeks of chest X-ray

07

Study locations

1 site
  • Yongin Severance Hospital
    Yongin, Giheung-gu 16995, Korea, Republic of
08

Updates

Tracking since Sep 25, 2026
No changes since tracking began. The registry record was last updated on Sep 14, 2022, before this site started recording changes on Sep 25, 2026. Its history is on ClinicalTrials.gov ↗
09

Registry details

Key details

Study ID
NCT04996381
Lead sponsor
Yonsei University
Responsible party
SungA Bae (MD. PhD., Yonsei University) — Principal investigator
First posted
Aug 9, 2021
Start date
Mar 1, 2022
Primary completion
Jun 30, 2022
Completion
Sep 1, 2022
Last update
Sep 14, 2022

Study contacts

In Hyun Jung, MD, PhD
study chair · Yongin Severance Hospital, Yonsei University College of Medicine

Oversight

Data monitoring committee
Yes
FDA-regulated drug
No
FDA-regulated device
No
View the source record on ClinicalTrials.gov ↗

Not currently enrolling

This study is completed, as verified in Sep 2022. You cannot join it, but the record below documents what was studied.

Follow this study

Get an email when the registry record changes — status, dates, results — or when someone posts here.

Sign in to follow

Discussion

Questions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.

Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.

Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.

Start the discussion