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
Can ChatGPT-Assisted ECG Interpretation help in the STEMI Activation pathway?
Session:
Sessão de Posters 13 - Intervenção coronária avançada: fisiologia, bifurcações e complicações
Speaker:
Inês Pereira De Miranda
Congress:
CPC 2026
Topic:
H. Interventional Cardiology and Cardiovascular Surgery
Theme:
25. Interventional Cardiology
Subtheme:
25.2 Coronary Intervention
Session Type:
Posters Eletrónicos
FP Number:
---
Authors:
Inês Pereira de Miranda; Filipa Gerardo; Yara Alvarenga; Carolina Pereira Mateus; Rodrigo Brandão; Tiago Dias Mesquita; Luís Cotrim; Inês Madeira Santos; Miguel Santos; Sérgio Bravo Baptista; Carlos Morais
Abstract
<p style="text-align:justify"><span style="font-size:12pt"><span style="font-family:"Times New Roman",serif"><strong><span style="font-family:"Calibri",sans-serif">Background:</span></strong><span style="font-family:"Calibri",sans-serif"> Rapid and accurate interpretation of the ECG is critical for early activation of the coronary team in patients with suspected ST-segment-elevation myocardial infarction (STEMI). However, conventional workflows often face delays and diagnostic variability. Recent advances in generative AI, such as ChatGPT, offer potential to streamline ECG interpretation and trigger timely and accurately STEMI activation.</span></span></span></p> <p style="text-align:justify"><span style="font-size:12pt"><span style="font-family:"Times New Roman",serif"><strong><span style="font-family:"Calibri",sans-serif">Objective:</span></strong><span style="font-family:"Calibri",sans-serif"> To assess ChatGPT-assisted ECG analysis diagnostic accuracy. </span></span></span></p> <p style="text-align:justify"><span style="font-size:12pt"><span style="font-family:Calibri,sans-serif"><strong>Methods:</strong> We conducted a single-center retrospective study including all coronary team (“Via Verde Coronária”) STEMI activations from January to November 2025. ECGs were analyzed using ChatGPT version 5.0, prompted with: <em><span style="font-family:"Calibri",sans-serif">“Based on this ECG, is there an occluded coronary artery?”.</span></em> ChatGPT’s output was then compared with the invasive coronary angiography reports. Significant coronary artery disease was defined as a <u>></u>90% stenosis requiring urgent revascularization.</span></span></p> <p style="text-align:justify"><span style="font-size:12pt"><span style="font-family:Calibri,sans-serif"><strong>Results:</strong> We reviewed a total of 220 STEMI activations (mean age 64 ± 14 years, 30.9% female, 21.8% diabetes, 42.7% dyslipidemia, 63.2% hypertension, 40.5% smokers and 11.4% previous smokers). There were 176 (80%) ECGs available for analysis; 20% were unavailable due to external acquisition or technical issues. Among the available ECGs, 152 patients (86%) had significant coronary stenosis. ChatGPT correctly predicted a significant stenosis in 126 cases (83%), and failed in 26 (17%). Missed occlusions most frequently involved the LAD (10), followed by LCx (5), RCA (5), diagonal (2) and OM (2) branches, and one case of three-vessel disease. Among the 24 patients without significant stenosis, ChatGPT correctly classified 20 (83%) and generated four false positives (normal coronaries [2], vasospasm [1], or repeat angiography [1]). Diagnostic performance had a sensitivity of 82.9%, specificity 83.3%, positive likelihood ratio 4.97, and a high positive predictive value of 96.9% (vs 84.4% human positive predictive value), confirming excellent rule-in ability. The negative likelihood ratio was 0.21 and the negative predictive value 43.5%, indicating limited rule-out capability. Overall accuracy was 83%.</span></span></p> <p style="text-align:justify"><span style="font-size:12pt"><span style="font-family:Calibri,sans-serif"><strong>Conclusion:</strong> These results indicate a good overall performance, driven mainly by ChatGPT excellent rule-in ability, with a high positive predictive value, providing practical reassurance for clinicians uncertain about activating the interventional team or even the on-duty cardiologist. The negative predictive value was low (although limited by the high disease prevalence), and ChatGPT should not be used to exclude a coronary occlusion. The high positive predictive value suggests further investigations are in order to explore ChatGPT’s capability in similar settings, such as identifying NSTEMI patients with an acutely occluded artery.</span></span></p>
Slides
Our mission: To reduce the burden of cardiovascular disease
Visit our site