Sleep/wake classification with pulse oximeter signals using recurrent neural networks

CASAL, RAMIRO; SCHLOTTHAUER, GASTÓN; DI PERSIA, LEANDRO E.

Long Beach

Conferencia; International Conference on Machine Learning; 2019

LatinX in AI research

The regulation of the autonomic nervous system changes with the sleep stages causing fluctuation in the physiological variables. We exploit this changes with the aim of classify the sleep stages in awake or asleep using pulse oximeter signals. We applied a recurrent neural network to heart rate and peripheral oxygen saturation signals to classify every 30 seconds the sleep state. The network architecture consists of two stacked layers of bidirectional GRU and a softmax layer to classify the output. The best result obtained was 90.13% accuracy, 94.13% sensitivity, 80.26% specificity, 92.05% precision, and 84.68.3% negative predictive value. Further, the Cohen?s Kappa coefficient was 0.74 and the average absolute error percentage to the actual sleep time was 8.9%.