An autonomous medical monitoring system: Validation on arrhythmia detection

No Thumbnail Available
Lemkaddem, Alia
Proenca, Martin
Delgado-Gonzalo, Ricard
Renevey, Philippe
Oei, Ing
Montano, Giuseppe
Martinez-Heras, Jose-Antonio
Donati, Alessandro
Bertschi, Mattia
Lemay, Mathieu
In this paper, we present a generic platform for autonomous medical monitoring and diagnostics. We validated the platform in the context of arrhythmia detection with publicly available databases. The big advantage of this platform is its capacity to deal with any type of physiological signal. Many preprocessing steps are performed to bring the input information into a uniform state that will be explored by a machine learning algorithm. Since this block plays a crucial role in the entire processing pipeline, three different methods were evaluated for detection and classification of anomalies. The results presented in this work are validated on cardiac beats, where the highest accuracy was obtained on the classification of normal beats (94%). While, atrial fibrillation and premature ventricular contraction beats were classified with an accuracy of 78%.
Publication Reference
2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Seogwipo (KOR), pp. 4553-4556