Login
Search
Search
0 Dates
2026
2025
2024
2023
2022
2021
2020
2019
2018
0 Events
CPC 2018
CPC 2019
Curso de Atualização em Medicina Cardiovascular 2019
Reunião Anual Conjunta dos Grupos de Estudo de Cirurgia Cardíaca, Doenças Valvulares e Ecocardiografia da SPC
CPC 2020
CPC 2021
CPC 2022
CPC 2023
CPC 2024
CPC 2025
CPC 2026
0 Topics
A. Basics
B. Imaging
C. Arrhythmias and Device Therapy
D. Heart Failure
E. Coronary Artery Disease, Acute Coronary Syndromes, Acute Cardiac Care
F. Valvular, Myocardial, Pericardial, Pulmonary, Congenital Heart Disease
G. Aortic Disease, Peripheral Vascular Disease, Stroke
H. Interventional Cardiology and Cardiovascular Surgery
I. Hypertension
J. Preventive Cardiology
K. Cardiovascular Disease In Special Populations
L. Cardiovascular Pharmacology
M. Cardiovascular Nursing
N. E-Cardiology / Digital Health, Public Health, Health Economics, Research Methodology
O. Basic Science
P. Other
0 Themes
01. History of Cardiology
02. Clinical Skills
03. Imaging
04. Arrhythmias, General
05. Atrial Fibrillation
06. Supraventricular Tachycardia (non-AF)
07. Syncope and Bradycardia
08. Ventricular Arrhythmias and Sudden Cardiac Death (SCD)
09. Device Therapy
10. Chronic Heart Failure
11. Acute Heart Failure
12. Coronary Artery Disease (Chronic)
13. Acute Coronary Syndromes
14. Acute Cardiac Care
15. Valvular Heart Disease
16. Infective Endocarditis
17. Myocardial Disease
18. Pericardial Disease
19. Tumors of the Heart
20. Congenital Heart Disease and Pediatric Cardiology
21. Pulmonary Circulation, Pulmonary Embolism, Right Heart Failure
22. Aortic Disease
23. Peripheral Vascular and Cerebrovascular Disease
24. Stroke
25. Interventional Cardiology
26. Cardiovascular Surgery
27. Hypertension
28. Risk Factors and Prevention
29. Rehabilitation and Sports Cardiology
30. Cardiovascular Disease in Special Populations
31. Pharmacology and Pharmacotherapy
32. Cardiovascular Nursing
33. e-Cardiology / Digital Health
34. Public Health and Health Economics
35. Research Methodology
36. Basic Science
37. Miscellanea
0 Resources
Abstract
Slides
Vídeo
Report
CLEAR FILTERS
External validation of an AI-ECG Model for Left Ventricular Systolic Dysfunction Detection - Comparison with Transthoracic Echocardiography and Cardiac Magnetic Resonance.
Session:
Sessão de Posters 47 - Dos dados às decisões: a revolução da IA em cardiologia
Speaker:
Erivaldo Figueiredo Pires Andrade
Congress:
CPC 2026
Topic:
N. E-Cardiology / Digital Health, Public Health, Health Economics, Research Methodology
Theme:
33. e-Cardiology / Digital Health
Subtheme:
33.3 Computer Modeling and Simulation
Session Type:
Posters Eletrónicos
FP Number:
---
Authors:
Erivaldo Figueiredo
Abstract
<p style="text-align:justify"><strong>Background:</strong><br /> Left ventricular (LV) systolic dysfunction is associated with adverse outcomes but often remains unrecognized. Artificial intelligence (AI) applied to electrocardiography offers a scalable approach for early detection. PMcardio® is a commercially available AI-ECG platform capable of automated LV function estimation, yet its performance relative to transthoracic echocardiography (TTE) and cardiac magnetic resonance (CMR) remains insufficiently established in real-world cohorts.</p> <p style="text-align:justify"><strong>Objectives:</strong><br /> To evaluate the diagnostic performance of the PMcardio® AI-ECG model compared with TTE for detecting LV systolic dysfunction using CMR as reference, and to directly compare AI-ECG classification with CMR-defined dysfunction.</p> <p style="text-align:justify"><strong>Methods:</strong><br /> This retrospective study included 384 patients who underwent ECG, TTE, and CMR within ≤30 days. The AI-ECG model classified LV function as reduced (≤40%), mildly reduced (41–49%), or preserved (≥50%). For validation, AI-ECG and TTE were dichotomized as dysfunction (<50%) or no dysfunction (≥50%), using CMR as reference. Diagnostic metrics included sensitivity, specificity, predictive values, accuracy, and AUC. Concordance between TTE and CMR was assessed using Lin’s concordance correlation coefficient and Cohen’s κ. A subgroup of heart failure (HF) patients was analysed separately. Logistic regression evaluated predictors of AI-ECG misclassification and the association between AI-ECG output and CMR-defined dysfunction.</p> <p style="text-align:justify"><strong>Results:</strong><br /> LV dysfunction was present in 112 patients (29.2%). AI-ECG sensitivity was 85.7% (95% CI 77.5–91.1), specificity 85.3% (95% CI 80.5–89.1), accuracy 85.4%, and AUC 0.86 (95% CI 0.80–0.90). TTE showed sensitivity 92.9% (95% CI 86.8–96.4), specificity 88.6% (95% CI 84.2–91.8), accuracy 89.6%, and AUC 0.97 (95% CI 0.94–0.99). Concordance with CMR was substantial for categorical dysfunction (κ 0.765) and high for continuous LVEF (CCC 0.884). In HF patients (n = 78), AI-ECG performance improved, with sensitivity 92.3%, specificity 75.0%, accuracy 88.5%, and AUC 0.89 (95% CI 0.83–0.94). In multivariable analysis, AI-ECG classification was strongly associated with CMR-defined dysfunction (OR 22.2; 95% CI 10.6–46.5), while age and sex did not predict misclassification.</p> <p style="text-align:justify"><strong>Conclusions:</strong><br /> The PMcardio® AI-ECG model demonstrated high diagnostic accuracy for detecting LV systolic dysfunction when benchmarked against CMR, with satisfactory performance even in a cohort with high prevalence of dysfunction, supporting its potential role as an accessible screening tool to guide referral for advanced cardiac imaging.</p>
Slides
Our mission: To reduce the burden of cardiovascular disease
Visit our site