Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Apr 26, 2026

Evaluation of Left Ventricular Structure and Function using 3D Echocardiography
06:34

Evaluation of Left Ventricular Structure and Function using 3D Echocardiography

Published on: October 28, 2020

4.1K

Deep Learning Model Using Transfer Learning for Detecting Left Ventricular Systolic Dysfunction: Retrospective

Sungjae Lee1, Jung-Woo Son2, Sung-Ai Kim3

  • 1VUNO Inc, Seoul, Republic of Korea.

JMIR Medical Informatics
|April 24, 2026
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Periprocedural Factor Xa Inhibitor Interruption and Resumption for Patients With Atrial Fibrillation Undergoing Dental Procedures.

Korean circulation journal·2026
Same author

Effectiveness of an Intervention to Improve Guideline-Directed Medications for Patients With Acute Heart Failure: A Randomized Clinical Trial.

Journal of the American Heart Association·2026
Same author

Long-term mortality and treatment outcomes in pacemaker-associated heart failure: insights from a nationwide propensity-matched study.

European heart journal open·2026
Same author

Evaluation of guideline adherence to hypertension-mediated organ damage screening in Korean patients with hypertension: results from the Korean Registry of Target Organ Damage in Hypertension (KorHR).

Clinical hypertension·2026
Same author

Clinical Effectiveness of an Artificial Intelligence-Based Prediction Model for Cardiac Arrest in General Ward-Admitted Patients: A Non-Randomized Controlled Trial.

Diagnostics (Basel, Switzerland)·2026
Same author

Erratum: Correction of Funding in the Article "Prognostic Significance of Fatty Liver Index for the Development of Hypertension and Cardiovascular Events in Populations With Suboptimal Blood Pressure".

Journal of Korean medical science·2026
Same journal

Clinician Perspectives on Ambient AI Scribes in the Intensive Care Unit: Qualitative Interview Study.

JMIR medical informatics·2026
Same journal

IdeaDistiller-AI Support for Idea Synthesis in Concept Mapping: Algorithm Development and Validation Study.

JMIR medical informatics·2026
Same journal

Pregnancy-Related Clinical Codes in Unlikely Populations in Primary Care.

JMIR medical informatics·2026
Same journal

Selecting, Scaling, and Measuring the Value of Ambient AI in a Nonacademic Health System: Multiphase Pilot Study.

JMIR medical informatics·2026
Same journal

Prediction of Early Hospital Admission (≤24 Hours) After Stroke Using Machine Learning and Deep Learning: Multicenter Study From China.

JMIR medical informatics·2026
Same journal

Assessing the Feasibility and Acceptability of Implementing a Preclinic Vital Signs Assessment in Primary Care: Cross-Sectional Pilot Study.

JMIR medical informatics·2026
See all related articles
This summary is machine-generated.

A new recalibration method significantly improves artificial intelligence-electrocardiogram (AI-ECG) models for detecting left ventricular systolic dysfunction (LVSD). This enhances accuracy and consistency in patients with comorbidities, enabling reliable longitudinal monitoring.

Area of Science:

  • Cardiology
  • Artificial Intelligence
  • Medical Diagnostics

Background:

  • Artificial intelligence-augmented electrocardiogram (AI-ECG) models for left ventricular systolic dysfunction (LVSD) detection often show reduced performance in patients with comorbidities.
  • This performance degradation necessitates improved AI-ECG methodologies for accurate clinical application.

Purpose of the Study:

  • To introduce and validate a novel recalibration method using longitudinal patient data to enhance AI-ECG prediction accuracy for LVSD.
  • To simulate the clinical utility of this recalibration method for ongoing patient monitoring.

Main Methods:

  • A multicenter, retrospective cohort study utilizing paired transthoracic echocardiogram (TTE) and electrocardiogram (ECG) data from two Korean hospitals.
  • Development of a patient-wise recalibration strategy incorporating historical left ventricular ejection fraction and prior AI-ECG outputs to adjust predictions and mitigate confounding effects.
Keywords:
artificial intelligencedeep learningechocardiographyelectrocardiogramleft ventricular systolic dysfunction

More Related Videos

Transthoracic Echocardiography to Assess Post-Resuscitation Left Ventricular Dysfunction After Acute Myocardial Infarction and Cardiac Arrest in Pigs
08:19

Transthoracic Echocardiography to Assess Post-Resuscitation Left Ventricular Dysfunction After Acute Myocardial Infarction and Cardiac Arrest in Pigs

Published on: July 12, 2022

3.3K

Related Experiment Videos

Last Updated: Apr 26, 2026

Evaluation of Left Ventricular Structure and Function using 3D Echocardiography
06:34

Evaluation of Left Ventricular Structure and Function using 3D Echocardiography

Published on: October 28, 2020

4.1K
Transthoracic Echocardiography to Assess Post-Resuscitation Left Ventricular Dysfunction After Acute Myocardial Infarction and Cardiac Arrest in Pigs
08:19

Transthoracic Echocardiography to Assess Post-Resuscitation Left Ventricular Dysfunction After Acute Myocardial Infarction and Cardiac Arrest in Pigs

Published on: July 12, 2022

3.3K
  • Implementation of pretraining to further enhance model performance.

    • Main Results:

    • The recalibrated 12-lead DeepECG LVSD model achieved high areas under the receiver operating curve (AUC) of 0.956 (internal) and 0.940 (external validation).
    • Recalibration resulted in statistically significant improvements (P<.001) in model performance across all clinical subgroups compared to the uncalibrated model.
    • The recalibrated model demonstrated enhanced and more balanced performance, particularly in patients with comorbidities.

    Conclusions:

    • Patient-wise recalibration effectively improves the accuracy and consistency of AI-ECG for LVSD detection, mitigating performance degradation and bias.
    • This method broadens the application of AI-ECG from screening to high-risk longitudinal monitoring.
    • The validated recalibration strategy supports the reliable use of AI-ECG in diverse patient populations.