Login
Search
Search
0 Dates
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
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
Phenotyping Heart Failure with Reduced Ejection Fraction: A Machine Learning Approach to Patient Stratification
Session:
SESSÃO DE COMUNICAÇÕES ORAIS 15 - INTELIGÊNCIA ARTIFICIAL EM CARDIOLOGIA: APROVEITAR O POTENCIAL!
Speaker:
Diogo Ferreira
Congress:
CPC 2025
Topic:
D. Heart Failure
Theme:
10. Chronic Heart Failure
Subtheme:
10.2 Chronic Heart Failure – Epidemiology, Prognosis, Outcome
Session Type:
Comunicações Orais
FP Number:
---
Authors:
Diogo Rosa Ferreira; Sofia Morgado; Fátima Salazar; Ana Francês; Rafael Santos; Joana Rigueira; Doroteia Silva; Nuno Lousada; Fausto Pinto; Dulce Brito; João Agostinho
Abstract
<p style="text-align:justify"><strong>Introduction:</strong><br /> Left ventricular ejection fraction (LVEF) is a key marker in heart failure with reduced ejection fraction (HFrEF). However, relying solely on LVEF oversimplifies HFrEF, especially in terms of treatment response and comorbidities. This study used a machine learning approach to identify subgroups of HFrEF patients, aiming to improve treatment strategies and guide personalized decision-making.<br /> </p> <p style="text-align:justify"><strong>Methods:</strong><br /> We conducted a prospective cohort study including patients with newly diagnosed HFrEF followed at a tertiary clinic from 2020-24. Clinical data underwent preprocessing (outlier correction, imputation of missing values, normalization). Dimensionality reduction was done using Principal Component Analysis, retaining components based on the Kaiser criterion. Agglomerative hierarchical clustering with Ward's linkage identified subgroups. Statistical comparisons between clusters utilized Mann-Whitney U, Kruskal-Wallis, Kaplan-Meier survival analysis, and log-rank tests. The primary outcome was a composite of heart failure hospitalizations (HHF) or cardiovascular (CV) death at 2 years.<br /> <br /> <strong>Results: </strong><br /> The study included 213 patients, with a mean age of 64 years and baseline LVEF of 28.5%. Follow-up averaged 2.4 years. Clustering revealed three subgroups: Responders, Frail, and Resilient.<br /> The Responders group, mostly non-ischemic, had the lowest LVEF and elevated left atrial volume index, NTproBNP, and GGT, reflecting a congestive phenotype. Despite pronounced adverse remodeling, this group experienced the greatest LVEF recovery following optimized medical therapy (OMT).<br /> The Frail group, the oldest cohort, had balanced ischemic and non-ischemic etiologies, with low hemoglobin, estimated glomerular filtration rate (eGFR), ferritin, transferrin saturation (TSAT), LDL, and uric acid, suggesting undernutrition. It had the highest baseline LVEF but the poorest outcomes.<br /> The Resilient group, similar in age to the Responders, had higher baseline LVEF, lower NTproBNP and LAVI, better hemoglobin, eGFR, ferritin, and TSAT, and a higher body mass index compared to the Frail group.<br /> LVEF improved across all groups with OMT, but prognosis varied significantly. The Frail group had an eightfold higher risk of HHF or CV death compared to the Resilient group (HR: 8.2; 95% CI: 2.7–24.3; p<0.001) and nearly twice the risk compared to Responders (HR: 1.9; 95% CI: 1.1–3.4; p=0.019). Responders had 2.2 times the risk of the composite outcome compared to Resilient patients (HR: 2.2; 95% CI: 1.1–4.5; p=0.036).<br /> A user-friendly software was developed to classify any HFrEF patient into these clusters.<br /> </p> <p style="text-align:justify"><strong>Conclusion:</strong><br /> This study demonstrates that machine learning can identify distinct HFrEF subgroups with unique characteristics and outcomes. Phenotypic stratification goes beyond LVEF, enabling personalized treatment strategies to improve outcomes, particularly for high-risk groups.</p> <p> </p>
Slides
Our mission: To reduce the burden of cardiovascular disease
Visit our site