Automated sleep analysis from wearable monitoring devices.

Sleep-wake disturbances are widespread across the disease spectrum. They are among the earliest and most disruptive symptoms in Alzheimer’s disease (AD), which is the number one neurodegenerative disease and represents a huge burden in our aging society. Sleep-wake disturbances are also associated with epilepsy, which in turn interacts with AD. While there is plenty of evidence for the interplay between AD, epilepsy and sleep, the nature of the interactions is not well understood yet.

Potential causalities between the disorders can be unravelled by studying their long-term evolution and trends. This requires access to longitudinal sleep data outside of the hospital environment and automated approaches to analyse those data. The recent emergence of wearable brain monitoring devices has enabled the recording of longitudinal data. In this PhD project, algorithms will be devised for automated sleep-wake quantification from data collected with these wearables. The PhD student will develop deep learning models for sleep scoring, optimized for selected patient populations. The ideal model will allow to be trained on small amounts of labeled data, augmented with unlabeled data, and will be personalized for individual patients. The models will be validated on AD and epilepsy patients.

The developed algorithms will be fundamental to efficiently track sleep longitudinally in AD and epilepsy patients, and ultimately, to unravel its impact on these diseases.