Differentiating cardiac and non-cardiac chest pain using deep learning with magnetocardiography: A novel diagnostic approach

Key Points

• The aim is to develop a deep learning model to distinguish between cardiac and non-cardiac chest pain using magnetocardiography data.
• Utilized magnetocardiography to collect data from patients presenting with chest pain.
• Applied deep learning algorithms to analyze the collected magnetocardiography signals.
• Conducted a randomized trial to assess the performance of the diagnostic model.
• Achieved an accuracy of 87% in distinguishing cardiac from non-cardiac chest pain.
• The model demonstrated a sensitivity of 85% and specificity of 90% in the validation cohort.
• P<0.001 for the difference in diagnostic accuracy compared to traditional methods.