Join us for a PhD thesis defence of Luka Biedebach on her thesis New Pathways for Unsupervised Machine Learning in Digital Health: Applications and Future Potentials for Sleep.

Defence committee:

Main Supervisor: Anna Sigríður Islind, Associate Professor, Department of Computer Science, Reykjavik University, Iceland.

Co-Supervisor: Erna Sif Arnardóttir, Associate Professor, Department of Computer Science & Department of Engineering, Reykjavik University, Iceland.

Examiner: Aleksandre Asatiani, Associate Professor, Department of Applied IT, Gothenburg University, Sweden.

Committee members: 

• Samu Kainulainen, Senior Researcher, Department of Medical Physics, University of Eastern Finland, Finland.
• Alexander Kempton, Associate Professor, Department of Informatics, University of Oslo, Norway.
• María Óskarsdóttir, Associate Professor, Department of Computer Science, Reykjavik University, Iceland & School of Mathematical Sciences, University of Southampton, United Kingdom.

Master of Ceremony: Luca Aceto

Abstract

The strength of unsupervised machine learning -to extract patterns from large unlabeled data sets- has recently led to big steps in natural language processing and computer vision. This thesis aims to explore the existing applications and future potentials of unsupervised machine learning in digital health. There are vast amounts of unlabeled data in digital health, and there is a growing need for digital solutions to tackle health challenges in a growing and aging population. These technologies play a key role in the paradigm shift of medicine towards predictive, preventative, personalized, and participatory healthcare. This research aims to investigate the different ways unsupervised machine learning can contribute to digital health and contemporary medicine. Sleep, as one of the pillars of health, has a substantial contribution to various mechanisms in our body, including the brain, hormonal balance, and the cardiovascular and immune system. Good sleep can help to improve overall physical and mental health, while poor sleep is associated with chronic diseases, decreased cognitive function, and a shortened lifespan. Even though it is common knowledge that sleep is important, it can be difficult to maintain good sleep. There can be physical, psychological, and lifestyle factors impacting the quality of sleep. Digital health and machine learning can address this issue from various perspectives, such as the efficient diagnosis and provision of treatment options for people with sleep disorders, the collection of longitudinal sleep data, and the analysis of sleep recordings. This research first maps all existing publications on unsupervised machine learning in sleep research and then conducts four case studies with selected unsupervised machine learning methods on different forms of sleep data. The cases use (i) anomaly detection, (ii) dimensionality reduction, (iii) clustering, and (iv) association rules with data on respiration and brain during sleep, as well as objective and subjective sleep quality assessment and engagement with a digital health application. Each case aims to represent a novel approach, illustrating a range and diversity of contributions of unsupervised machine learning for sleep to curate new pathways for unsupervised learning in digital health.