logo
ResearchBunny Logo
Enhancing the diagnosis of functionally relevant coronary artery disease with machine learning

Medicine and Health

Enhancing the diagnosis of functionally relevant coronary artery disease with machine learning

C. Bock, J. E. Walter, et al.

This paper reveals how machine learning (ML) can enhance the diagnosis of functionally relevant coronary artery disease (fCAD), outperforming cardiologists and potentially reducing unnecessary imaging procedures. The innovative approaches presented by Christian Bock, Joan Elias Walter, Bastian Rieck, and colleagues could shape the future of cardiac healthcare.

00:00
00:00
Playback language: English
Abstract
This paper investigates the use of machine learning (ML) to improve the diagnosis of functionally relevant coronary artery disease (fCAD). Two ML approaches are presented: one using eight static clinical variables and the other leveraging electrocardiogram (ECG) signals from exercise stress testing. Results show that ML outperforms cardiologists in predicting fCAD (AUROC: 0.71 vs. 0.64, p = 4.0E-13), potentially reducing imaging procedures by 15–17%. Combining ML with cardiologist judgment further improves performance (AUROC: 0.74).
Publisher
Nature Communications
Published On
Jun 12, 2024
Authors
Christian Bock, Joan Elias Walter, Bastian Rieck, Ivo Strebel, Klara Rumora, Ibrahim Schaefer, Michael J. Zellweger, Karsten Borgwardt, Christian Müller
Tags
machine learning
coronary artery disease
diagnosis
electrocardiogram
cardiology
healthcare
Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny