Combining Spectral Analysis with Artificial Intelligence in Heart Sound Study
Dariusz Kucharski 1  
,  
Marcin Kajor 1  
,  
Dominik Grochala 1  
,  
Marek Iwaniec 2  
,  
 
 
Więcej
Ukryj
1
Faculty of Electrical Engineering, Automatics, Computer Science and Biomedical Engineering, AGH Univeristy of Science and Technology, Al. Mickiewicza 30, 30-059 Kraków, Poland
2
Faculty of Mechanical Engineering and Robotics AGH Univeristy of Science and Technology, Al. Mickiewicza 30, 30-059 Kraków Poland
AUTOR DO KORESPONDENCJI
Joanna Iwaniec   

Faculty of Mechanical Engineering and Robotics AGH Univeristy of Science and Technology, Al. Mickiewicza 30, 30-059 Kraków Poland
Data publikacji: 01-06-2019
 
Adv. Sci. Technol. Res. J. 2019; 13(2):112–118
SŁOWA KLUCZOWE
DZIEDZINY
 
STRESZCZENIE ARTYKUŁU
An auscultation technique has been widely used in medicine as a screening examination for ages. Nowadays, advanced electronics and effective computational methods aim to support healthcare sector by providing dedicated solutions which facilitate physicians and support diagnostic process. In this paper we propose machine learning approach for analysis of heart sounds. We used acoustic signal spectral analysis to calculate feature vectors and tested a set of machine learning approaches to provide the most effective detection of cardiac disorders. Finally we achieved 91% of sensitivity and 99% of positive predictivity for a designed algorithm based on convolutional neural network.