Automatic heart activity diagnosis based on Gram polynomials and probabilistic neural networks
10.1007/s13534-017-0046-z
- Author:
Francesco BERITELLI
1
;
Giacomo CAPIZZI
;
Grazia LO SCIUTO
;
Christian NAPOLI
;
Francesco SCAGLIONE
Author Information
1. Department of Electrical, Electronic and Informatics Engineering (DIEEI), University of Catania, Catania, Italy. gcapizzi@diees.unict.it
- Publication Type:Original Article
- Keywords:
Heart sounds;
Phonocardiogram;
Cardiac signal analysis;
Gram polynomials;
Probabilistic neural network
- MeSH:
Classification;
Dataset;
Diagnosis;
Fourier Analysis;
Heart Diseases;
Heart Sounds;
Heart;
Sensitivity and Specificity
- From:
Biomedical Engineering Letters
2018;8(1):77-85
- CountryRepublic of Korea
- Language:English
-
Abstract:
The paper proposes a new approach to heart activity diagnosis based on Gram polynomials and probabilistic neural networks (PNN). Heart disease recognition is based on the analysis of phonocardiogram (PCG) digital sequences. The PNN provides a powerful tool for proper classification of the input data set. The novelty of the proposed approach lies in a powerful feature extraction based on Gram polynomials and the Fourier transform. The proposed system presents good performance obtaining overall sensitivity of 93%, specificity of 91% and accuracy of 94%, using a public database of over 3000 heart beat sound recordings, classified as normal and abnormal heart sounds. Thus, it can be concluded that Gram polynomials and PNN prove to be a very efficient technique using the PCG signal for characterizing heart diseases.
