An Artificial Intelligence-Enabled Electrocardiogram to Evaluate Patients With Dyspnea in the Emergency Department

Objective: To evaluate whether an Artificial Intelligence-Enabled Electrocardiogram (AI-ECG) for diastolic function/filling pressure can determine whether dyspnea in emergency department (ED) patients is cardiac in origin. Patients and Methods: We identified 2412 patients aged 18 years or older pres...

Full description

Saved in:
Bibliographic Details
Main Authors: Hee Tae Yu, MD, PhD, Laura E. Walker, MD, Eunjung Lee, PhD, Muhannad Abbasi, MBBCh, Samuel Wopperer, MD, Gal Tsaban, MD, PhD, Kathleen Kopecky, MD, Francisco Lopez-Jimenez, MD, Paul Friedman, MD, Zachi Attia, PhD, Jae K. Oh, MD
Format: Article
Language:English
Published: Elsevier 2025-10-01
Series:Mayo Clinic Proceedings: Innovations, Quality & Outcomes
Online Access:http://www.sciencedirect.com/science/article/pii/S2542454825000633
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849229294106050560
author Hee Tae Yu, MD, PhD
Laura E. Walker, MD
Eunjung Lee, PhD
Muhannad Abbasi, MBBCh
Samuel Wopperer, MD
Gal Tsaban, MD, PhD
Kathleen Kopecky, MD
Francisco Lopez-Jimenez, MD
Paul Friedman, MD
Zachi Attia, PhD
Jae K. Oh, MD
author_facet Hee Tae Yu, MD, PhD
Laura E. Walker, MD
Eunjung Lee, PhD
Muhannad Abbasi, MBBCh
Samuel Wopperer, MD
Gal Tsaban, MD, PhD
Kathleen Kopecky, MD
Francisco Lopez-Jimenez, MD
Paul Friedman, MD
Zachi Attia, PhD
Jae K. Oh, MD
author_sort Hee Tae Yu, MD, PhD
collection DOAJ
description Objective: To evaluate whether an Artificial Intelligence-Enabled Electrocardiogram (AI-ECG) for diastolic function/filling pressure can determine whether dyspnea in emergency department (ED) patients is cardiac in origin. Patients and Methods: We identified 2412 patients aged 18 years or older presented with dyspnea/shortness of breath to the ED who had an ECG performed at the time of evaluation from January 2020 to December 2022. The AI-ECG for determining left ventricular diastolic function to identify the patients with cardiac cause of dyspnea was assessed, using the final diagnosis based on subsequent evaluation. Results: Of the 2412 patients, 966 (40%) were found to have cardiac dyspnea, and the remaining 1446 (60%) were noncardiac. The AI-ECG-estimated diastolic function was divided into 4 groups: 922 (38.2%) were normal, 245 (10.2%) grade 1, 1192 (49.4%) grade 2, and 53 (2.2%) grade 3. The probability of cardiac dyspnea was considerably higher in patients with grade 2 (62.2%±48.5%) and 3 (83%±37.9%) diastolic function compared with normal (14.1%±34.8%) and grade 1 (20.8%±40.7%). The incidence of cardiac dyspnea increased as the probability of increasing filling pressure increased on AI-ECG. Conclusion: Patients often present to the ED with undifferentiated dyspnea. It is important to promptly determine whether the symptoms have cardiac origin. Cardiac dyspnea often reflects elevated left ventricular filling pressures. Artificial intelligence-enhanced 12-lead electrocardiograms can precisely assess diastolic function and filling pressures. Among patients who presented to the ED with dyspnea/shortness of breath, AI-ECG assessing diastolic function strongly distinguished whether the cause was cardiac.
format Article
id doaj-art-350ffcdb741e4467abdbdfffa199af78
institution Kabale University
issn 2542-4548
language English
publishDate 2025-10-01
publisher Elsevier
record_format Article
series Mayo Clinic Proceedings: Innovations, Quality & Outcomes
spelling doaj-art-350ffcdb741e4467abdbdfffa199af782025-08-22T04:57:06ZengElsevierMayo Clinic Proceedings: Innovations, Quality & Outcomes2542-45482025-10-019510065210.1016/j.mayocpiqo.2025.100652An Artificial Intelligence-Enabled Electrocardiogram to Evaluate Patients With Dyspnea in the Emergency DepartmentHee Tae Yu, MD, PhD0Laura E. Walker, MD1Eunjung Lee, PhD2Muhannad Abbasi, MBBCh3Samuel Wopperer, MD4Gal Tsaban, MD, PhD5Kathleen Kopecky, MD6Francisco Lopez-Jimenez, MD7Paul Friedman, MD8Zachi Attia, PhD9Jae K. Oh, MD10Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN; Division of Cardiology, Department of Internal Medicine, Yonsei University College of Medicine, Seoul, Republic of KoreaDepartment of Emergency Medicine, Mayo Clinic, Rochester, MN; Correspondence: Address to Laura E Walker, MD, Department of Emergency Medicine, Mayo Clinic, 200 First St SW, Rochester, MN 55905.Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MNDepartment of Cardiovascular Medicine, Mayo Clinic, Rochester, MNDepartment of Cardiovascular Medicine, Mayo Clinic, Rochester, MNDepartment of Cardiovascular Medicine, Mayo Clinic, Rochester, MNDepartment of Cardiovascular Medicine, Mayo Clinic, Rochester, MNDepartment of Cardiovascular Medicine, Mayo Clinic, Rochester, MNDepartment of Cardiovascular Medicine, Mayo Clinic, Rochester, MNDepartment of Cardiovascular Medicine, Mayo Clinic, Rochester, MNDepartment of Cardiovascular Medicine, Mayo Clinic, Rochester, MNObjective: To evaluate whether an Artificial Intelligence-Enabled Electrocardiogram (AI-ECG) for diastolic function/filling pressure can determine whether dyspnea in emergency department (ED) patients is cardiac in origin. Patients and Methods: We identified 2412 patients aged 18 years or older presented with dyspnea/shortness of breath to the ED who had an ECG performed at the time of evaluation from January 2020 to December 2022. The AI-ECG for determining left ventricular diastolic function to identify the patients with cardiac cause of dyspnea was assessed, using the final diagnosis based on subsequent evaluation. Results: Of the 2412 patients, 966 (40%) were found to have cardiac dyspnea, and the remaining 1446 (60%) were noncardiac. The AI-ECG-estimated diastolic function was divided into 4 groups: 922 (38.2%) were normal, 245 (10.2%) grade 1, 1192 (49.4%) grade 2, and 53 (2.2%) grade 3. The probability of cardiac dyspnea was considerably higher in patients with grade 2 (62.2%±48.5%) and 3 (83%±37.9%) diastolic function compared with normal (14.1%±34.8%) and grade 1 (20.8%±40.7%). The incidence of cardiac dyspnea increased as the probability of increasing filling pressure increased on AI-ECG. Conclusion: Patients often present to the ED with undifferentiated dyspnea. It is important to promptly determine whether the symptoms have cardiac origin. Cardiac dyspnea often reflects elevated left ventricular filling pressures. Artificial intelligence-enhanced 12-lead electrocardiograms can precisely assess diastolic function and filling pressures. Among patients who presented to the ED with dyspnea/shortness of breath, AI-ECG assessing diastolic function strongly distinguished whether the cause was cardiac.http://www.sciencedirect.com/science/article/pii/S2542454825000633
spellingShingle Hee Tae Yu, MD, PhD
Laura E. Walker, MD
Eunjung Lee, PhD
Muhannad Abbasi, MBBCh
Samuel Wopperer, MD
Gal Tsaban, MD, PhD
Kathleen Kopecky, MD
Francisco Lopez-Jimenez, MD
Paul Friedman, MD
Zachi Attia, PhD
Jae K. Oh, MD
An Artificial Intelligence-Enabled Electrocardiogram to Evaluate Patients With Dyspnea in the Emergency Department
Mayo Clinic Proceedings: Innovations, Quality & Outcomes
title An Artificial Intelligence-Enabled Electrocardiogram to Evaluate Patients With Dyspnea in the Emergency Department
title_full An Artificial Intelligence-Enabled Electrocardiogram to Evaluate Patients With Dyspnea in the Emergency Department
title_fullStr An Artificial Intelligence-Enabled Electrocardiogram to Evaluate Patients With Dyspnea in the Emergency Department
title_full_unstemmed An Artificial Intelligence-Enabled Electrocardiogram to Evaluate Patients With Dyspnea in the Emergency Department
title_short An Artificial Intelligence-Enabled Electrocardiogram to Evaluate Patients With Dyspnea in the Emergency Department
title_sort artificial intelligence enabled electrocardiogram to evaluate patients with dyspnea in the emergency department
url http://www.sciencedirect.com/science/article/pii/S2542454825000633
work_keys_str_mv AT heetaeyumdphd anartificialintelligenceenabledelectrocardiogramtoevaluatepatientswithdyspneaintheemergencydepartment
AT lauraewalkermd anartificialintelligenceenabledelectrocardiogramtoevaluatepatientswithdyspneaintheemergencydepartment
AT eunjungleephd anartificialintelligenceenabledelectrocardiogramtoevaluatepatientswithdyspneaintheemergencydepartment
AT muhannadabbasimbbch anartificialintelligenceenabledelectrocardiogramtoevaluatepatientswithdyspneaintheemergencydepartment
AT samuelwopperermd anartificialintelligenceenabledelectrocardiogramtoevaluatepatientswithdyspneaintheemergencydepartment
AT galtsabanmdphd anartificialintelligenceenabledelectrocardiogramtoevaluatepatientswithdyspneaintheemergencydepartment
AT kathleenkopeckymd anartificialintelligenceenabledelectrocardiogramtoevaluatepatientswithdyspneaintheemergencydepartment
AT franciscolopezjimenezmd anartificialintelligenceenabledelectrocardiogramtoevaluatepatientswithdyspneaintheemergencydepartment
AT paulfriedmanmd anartificialintelligenceenabledelectrocardiogramtoevaluatepatientswithdyspneaintheemergencydepartment
AT zachiattiaphd anartificialintelligenceenabledelectrocardiogramtoevaluatepatientswithdyspneaintheemergencydepartment
AT jaekohmd anartificialintelligenceenabledelectrocardiogramtoevaluatepatientswithdyspneaintheemergencydepartment
AT heetaeyumdphd artificialintelligenceenabledelectrocardiogramtoevaluatepatientswithdyspneaintheemergencydepartment
AT lauraewalkermd artificialintelligenceenabledelectrocardiogramtoevaluatepatientswithdyspneaintheemergencydepartment
AT eunjungleephd artificialintelligenceenabledelectrocardiogramtoevaluatepatientswithdyspneaintheemergencydepartment
AT muhannadabbasimbbch artificialintelligenceenabledelectrocardiogramtoevaluatepatientswithdyspneaintheemergencydepartment
AT samuelwopperermd artificialintelligenceenabledelectrocardiogramtoevaluatepatientswithdyspneaintheemergencydepartment
AT galtsabanmdphd artificialintelligenceenabledelectrocardiogramtoevaluatepatientswithdyspneaintheemergencydepartment
AT kathleenkopeckymd artificialintelligenceenabledelectrocardiogramtoevaluatepatientswithdyspneaintheemergencydepartment
AT franciscolopezjimenezmd artificialintelligenceenabledelectrocardiogramtoevaluatepatientswithdyspneaintheemergencydepartment
AT paulfriedmanmd artificialintelligenceenabledelectrocardiogramtoevaluatepatientswithdyspneaintheemergencydepartment
AT zachiattiaphd artificialintelligenceenabledelectrocardiogramtoevaluatepatientswithdyspneaintheemergencydepartment
AT jaekohmd artificialintelligenceenabledelectrocardiogramtoevaluatepatientswithdyspneaintheemergencydepartment