Aplicación de técnicas de procesamiento de audio para la clasificación de fonocardiogramas

Auscultation has been the most simple, cheap, primary and non-invasive method to diagnose the presence of a Heart pathology associated to a cardiovascular disease (CVD). However, physicians and specialists require special skills for this task, besides the Frequency limitations of the human auditory system.

The new digital stethoscope devices allow the use of digital signal processing techniques which can ve automatized aid by Machine Learning methods.

On the other hand, the pre-processing of the Heart Sound signal (also known as phonocardiogram or PCG) has been a challenging area for the Computer-Aided auscultation Systems. In this talk, we present some skills and strategies for PCG data Engineering in order to improve the Quality of Classification schemes using Machine Learning and Deep Learning classifiers bases on Digital Audio Processing techniques.