Android mobile app for digital stethoscope and heart sound audio classification. It can listen to heart sound in real time, record to WAV file and also play the file. It can also classify heart sound into two groups: abnormal and normal sound. HeartSound is standalone machine learning app that uses Physionet Challenge Dataset 2016 for model training. The app can achieve 82.77% in accuracy.
Screening abnormal heart sound by lay persons may help detecting heart diseases earlier. Machine learning can be used to develop mobile device for helping them doing this screening easily. Fortunately, there is The Physionet Challenge Dataset 2016 that contains of 3,240 heart sound files consisting of 665 abnormal sound files and 2,575 normal sound files. With Tensorflow technology and this data set makes it possible to develop machine learning model for heart sound audio classification.
This app can :
listen to heart sound in real time as a replacement for classical stethoscope.
record heart sound to WAV file.
classify heart sound by using machine learning.
setup microphone and speaker devices.
HeartSound app is tested with test group data. The statistics are as follow:
Test group characteristics:
Total 325 cases
Prevalence of abnormal sound: 20.62%
Negative Predictive Value: 92.08%
Heart sound file specification
Hardware devices needed
To get good quality of heart sound, you need electronic stethoscope that can be connected to your android device. It can be commercial product or you can make it by yourself. The following picture is DIY electronic stethoscope that connects condenser microphone with the head of stethoscope.
DIY electronic stethoscope
2. 4 Pole 3.5mm Audio Splitter Cable
4. Full assembly
Where to listen for Heart Sounds by Medzcool
version 3.0 released ( 29 April 2022)
version 1.0.1 released ( 19 August 2021)
version 1.0 released