Multiscale Bowel Sound Event Spotting in Highly Imbalanced Wearable Monitoring Data: Algorithm Development and Validation Study.

Annalisa Baronetto Luisa Graf Sarah Fischer Markus Friedrich Neurath Oliver Amft

Published in: JMIR AI (2024)

The EffUNet spotter is robust against background noise and can retrieve BSs with varying duration. EffUNet outperforms previous BS detection approaches in unmodified audio data, containing highly sparse BS events.

Keyphrases

electronic health record
big data
machine learning
deep learning
heart rate
neural network
loop mediated isothermal amplification
data analysis
sensitive detection