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
Unlocking Hidden Prognostic Signals Using Machine-Learning – Squeezing the orange
Session:
Sessão de Posters 47 - Dos dados às decisões: a revolução da IA em cardiologia
Speaker:
Inês Gomes Campos
Congress:
CPC 2026
Topic:
N. E-Cardiology / Digital Health, Public Health, Health Economics, Research Methodology
Theme:
35. Research Methodology
Subtheme:
35.2 Research Methodology: Big Data Analysis
Session Type:
Posters Eletrónicos
FP Number:
---
Authors:
Inês Gomes Campos; Ana Rodrigo Costa; Mauro Moreira; José Luís Ferraro; Inês Bastos Castro; Rafaela G. Lopes; Aurora Andrade; Joel Monteiro
Abstract
<p style="text-align:start"><span style="font-size:medium"><span style="font-family:"Times New Roman",serif"><span style="color:#000000"><strong>Background:</strong><br /> Traditional statistical tools used in clinical research, such as logistic regression in SPSS, rely on linearity and binary endpoints and often struggle with complex relationships and censoring in survival data. Machine-learning survival models might handle these issues better, but are limited to be used in advanced statistics programs, such as R, and are still not commonly applied in common practice.</span></span></span></p> <p style="text-align:start"><span style="font-size:medium"><span style="font-family:"Times New Roman",serif"><span style="color:#000000"><strong>Methods:</strong><br /> To compare the predictive capabilities of classical and modern approaches, we applied three modeling strategies to a cardiac stress-test cohort. After cleaning and excluding post-outcome variables, the dataset was split into <strong>70% training </strong>and <strong>30% testing</strong>. Three models were developed: (1) <strong>Random Survival Forests (RSF)</strong>, a machine-learning method that uses decision trees to find complex patterns and predict survival more accurately than traditional models; (2) <strong>Penalized LASSO Cox regression (LASSO)</strong>, a refined version of the Cox model that automatically selects the most important predictors while preventing overfitting; (3) <strong>Binary logistic regression</strong>, predicting 5-year mortality to reflect SPSS-type analysis. Performance was evaluated on the test set using Harrell’s C-index and time-dependent ROC curves.</span></span></span></p> <p style="text-align:start"><span style="font-size:medium"><span style="font-family:"Times New Roman",serif"><span style="color:#000000"><strong>Results:</strong><br /> We included <strong>497 patients</strong> (mean age <strong>59.2±9.6</strong>; <strong>12.5%</strong> female; <strong>73.4%</strong> prior MI; <strong>9.8%</strong> HF; <strong>31.4%</strong> diabetes; <strong>19.1% </strong>positive stress tests), collected between 2009 and 2019. Over a mean follow-up of <strong>3543±1005 days</strong>, <strong>14.7%</strong> patients died.<br /> <strong>RSF</strong> achieved <strong>C-index 0.961</strong>, with AUCs: <strong>0.809 (3 yr)</strong>, <strong>0.732 (5 yr)</strong> and <strong>0.642 (10 yr)</strong>. <strong>LASSO Cox</strong> achieved <strong>C-index 0.703</strong>, with AUCs: <strong>0.305 (3 yr)</strong>, <strong>0.520 (5 yr)</strong> and <strong>0.661 (10 yr)</strong>. <strong>Binary logistic regression</strong> showed limited performance (<strong>C-index 0.536</strong>), consistent with loss of time-to-event information.</span></span></span></p> <p style="text-align:start"><span style="font-size:medium"><span style="font-family:"Times New Roman",serif"><span style="color:#000000"><strong>Conclusion:</strong><br /> This study works as a “proof of concept” that machine-learning survival analysis is not only feasible but gives clear advantages for cardiovascular risk prediction, especially for long-term follow-up data, where interactions between variables become more relevant. In this real-world stress-test cohort, <strong>Random Survival Forest </strong>clearly outperformed both penalized Cox regression and the more traditional SPSS-type logistic regression.</span></span></span></p>
Slides
Our mission: To reduce the burden of cardiovascular disease
Visit our site