Prediction of reported sleep quality based on physiological markers as measured with PSG

Abstract

In sleep research, the relationship between objective and subjective scores of sleep quality is still an open question. In particular, sleep patterns change naturally during pregnancy. In this study, we analyze sixty three nocturnal sleep data from 39 women, pregnant in their second and third trimester, collected in an earlier study at Philips. The data consists of various polysomnographic measures as well as Groningen Sleep Quality Scale (GSQS) questionnaire evaluation. A combination of two sets of hand-crafted and EEG features directly extracted by convolutional neural network (CNN) has been used to find subjective relevant features in the data.