The paper addresses the problem of detecting one of the most common cardiac arrhythmias atrial fibrillation with artificial intelligence. The arrhythmia increases the risk of suffering from a stroke massively. Because of this, it is essential to detect atrial fibrillation early. As the arrhythmia occurs in short sequences, it is only possible to detect the disease in long-term measurements for example with electrocardiography. All common current detection techniques are calculating the R-R intervals with variations of the root mean square of successive differences. Because this approach is inflexible and expensive, a major hospital in Germany suggests the implementation of an artificial intelligence solution for atrial fibrillation detection. The aim of the paper is to study the feasibility of atrial fibrillation detection with artificial intelligence in the clinical setting of the hospital.
Schneider, Simone; Gau, Thorsten; Grosse, Annika; Hennig,, Holger; and Winter,, Carmen, "Transformation of Medical Diagnostics with Machine Learning by Considering the Example of Atrial Fibrillation Identification" (2019). BLED 2019 Proceedings. 44.