/You-snooze-You-win

Deep learning on multi-channel time series classification (medical data)

Primary LanguagePython

PhysioNet

Automatic signal inspection to detect sleep apnea

About the project:

This project is to help detection of SleepApnea. People with this disease can't sleep at night because their breathing stops repeatedly and starts again. Lack of sleep at night will cause daytime sleepness. As a result, the person can't sleep enough and can't stay awake either.

When this situation lasts for weeks or months, you can imagine how painful this can be. In fact, sleep apnea can reportedly cause depression, heart problem, High blood pressure ..etc. learn more

Furthermore, While apneas are arguably the best understood of sleep disturbances, they are not the only cause of disturbance. Sleep arousals can also be spontaneous, result from teeth grinding, partial airway obstructions, or even snoring. In this year's PhysioNet Challenge we will use a variety of physiological signals, collected during polysomnographic sleep studies, to detect these other sources of arousal (non-apnea) during sleep.

Data for this challenge [...] includes 1,985 subjects which were monitored at an MGH sleep laboratory for the diagnosis of sleep disorders. The data were partitioned into balanced training (n = 994), and test sets (n = 989).

The objective is to automatically detect arousal regions in the signals. Traditionally, this task required visual inspection by scientists and doctors which can be a time-consuming task.

The detection automation of sleep arousals regions will allow faster evaluation of sleep disorder for each subject.

Data repo :

https://www.physionet.org/challenge/2018/