One of the main physiopathologic mechanisms of chronic heart failure symptoms is pulmonary congestion, characterized by the accumulation of fluid in the lungs, often detected on physical examination by pulmonary auscultation. Crackles, crepitations or rales are characteristic noises that may be present in one or both lungs, frequently heard during inspiration or expiration.
Assessment of the presence of pulmonary congestion is done by auscultation of the patient’s respiratory sounds using a stethoscope connected to the smartphone, which records the sounds through the microphone input and stores it in a digital audio file. The aim of such solution falls within a remote health monitoring system, where patients are able to self-auscultate and use mobile devices to send relevant data to a physician.
Early results with this approach revealed a large amount of external noise in the audio files obtained through auscultation. This issue induces the need for applying noise suppression techniques in order to obtain a clearer signal of the auscultation. The goal of this master thesis is to research on a range of possible techniques to mitigate the described issue, implement a prototype of the most balanced solution and test its effectiveness against a set of collected samples. This prototype should be integrated with an Android application connected to the stethoscope, so a real usage scenario can be tested.
Author: Gabriel Damaso
Type: MSc thesis
Partner: Faculdade de Engenharia da Universidade do Porto