Dream or reality? Studies and research on sleep to enhance well-being and quality of life

SUPSI Article Header

On Friday, March 14, the World Sleep Day, promoted by the World Association of Sleep Medicine, aims to raise awareness about the benefits of quality sleep and encourage healthy habits. Researchers at the Department of Innovative Technologies are actively studying sleep to prevent and treat disorders, ultimately improving quality of life.

On average, a person spends about one-third of their life sleeping. For an adult who sleeps approximately eight hours per night, this amounts to an estimated 121 days of sleep per year.

With its various stages and dreams, sleep has long fascinated artists, philosophers, psychologists, and researchers. Today, it is the focus of numerous studies aimed at understanding its mechanisms, preventing disorders that may affect its quality, and addressing related complications.

Sleep is a fundamental aspect of our lives, with its routine and quality playing a crucial role in physical, mental, and emotional well-being. Along with physical exercise and a balanced diet, it is a key pillar of health and disease prevention.

In this context, several research projects are underway at the Department of Innovative Technologies, particularly at the Institute of Digital Technologies for Personalized Healthcare (MeDiTech) and the Dalle Molle Institute for Artificial Intelligence (IDSIA USI-SUPSI), in collaboration with national and international research centers and clinics. Below are some examples.

SUPSI Image Focus

During wakefulness and sleep, synaptic strength is regulated by homeostatic processes that work in balance with each other. Specifically, during wakefulness, synaptic potentiation (upscaling) occurs, a process that enhances the strength of neural connections, preparing the brain for new information and stimuli. Later, during slow-wave sleep, selective reduction mechanisms (downscaling) are activated, helping to balance and optimize synaptic connections, improving learning quality and memory consolidation.

The project Disabling Levodopa-induced Dyskinesia in Parkinson’s Disease: The Role of Sleep, funded by the Swiss National Science Foundation (SNSF) and conducted in collaboration with the Institute of Clinical Neurosciences of the Ente ospedaliero cantonale (EOC), investigates the role of sleep in Parkinson's disease.

The project focuses on the potential connections between dyskinesias—uncontrolled, involuntary, and abnormal movements typical of the disease—and synaptic downscaling and upscaling mechanisms.

This research aims to better understand how the regulation of synaptic strength during sleep can influence the manifestation of dyskinesias in patients treated with levodopa, a medication used to treat Parkinson’s disease and other movement disorders caused by dopamine deficiency in the brain, potentially offering insights for new therapeutic approaches.

SUPSI Image Focus

Caption test
 

The classification of sleep stages is a crucial process for understanding the quality and structure of nightly rest. During sleep, our body cycles through different stages: light sleep, deep sleep, and REM (Rapid Eye Movement) sleep, each of which plays a vital role in physical and mental recovery.

The SleePyLand project (A Python library to analyze the large amount of NSRR sleep data), funded by the Swiss Open Research Data Grants (CHORD) program of swissuniversities, aims to create a platform for the fair evaluation of advanced deep learning algorithms for large-scale sleep classification. The goal is to promote transparency and reproducibility, strengthening both research and medical practice in the field of sleep.

The project fosters collaboration with international institutions, such as the National Sleep Research Resource (NSRR) at Harvard University, as well as with Swiss institutes and hospitals, including Inselspital Bern, for data exchange and the sharing of potential innovative clinical solutions.

SUPSI Image Focus

Caption test
Sleep scoring, performed by doctors or artificial intelligence algorithms, is essential for identifying standardized clinical markers—indicators that reflect and monitor health status.
 

The study Enhancing Sleep Medicine with Quantitative and AI-Driven Methods, conducted in collaboration with the University of Bern, Inselspital Bern, and the Imperial College of Tokyo, aims to develop new markers based on the dynamics of sleep stages, with the goal of improving the assessment of sleep disorders, such as sleep apnea, and predicting the long-term development of cardiovascular diseases.

Additionally, the work introduces a general framework to quantify and mitigate biases in AI algorithms applied to automated sleep scoring. This helps avoid disparities in results, ensuring fairness and transparency.

SUPSI Image Focus

Caption test

Sleep disorders, particularly those related to non-REM parasomnia—episodes characterized by abnormal behaviors, movements, or experiences that occur while a person is asleep but are not related to dreams (as in REM sleep)—are often underestimated, despite their potential to cause serious consequences such as injuries, cognitive impairments, and psycho-physical complications.

The At-home monitoring of abnormal sleep behaviors project aims to develop and test the effectiveness of a new wearable device for monitoring sleep behavior at home. By combining video-polysomnographic recordings and electroencephalographic data, the system uses deep learning algorithms to detect parasomnia episodes in real time. The introduction of this technology could mark a true revolution in the treatment of sleep disorders, offering continuous and non-invasive monitoring directly at home.

Funded by Innosuisse, the project is carried out in collaboration with the Institute of Clinical Neurosciences of the Ente ospedaliero cantonale (EOC).

SUPSI Image Focus

Caption test

Pregnancy is a physiological condition marked by profound anatomical, metabolic, hormonal, and psychological changes. Sleep and pregnancy are also closely interconnected: on one hand, pregnancy can disrupt sleep and cause disorders, while on the other, sleep disorders can affect the course of pregnancy and its outcome.

Sleep and sleep disorders during pregnancy and postpartum: the Life-ON study (Sleep medicine) and A machine learning model to predict the risk of perinatal depression: Psychosocial and sleep-related factors in the Life-ON study cohort (Psychiatry research) are two publications derived from the analysis of data collected during the Life-ON study, which monitored approximately 400 women during pregnancy and the postpartum period.

The goal was to analyze the sleep characteristics of pregnant women and their association with perinatal depression, a mood disorder that can occur during pregnancy or in the immediate postpartum period, with significant consequences for the mother’s mental health, the baby’s well-being, and the overall family dynamic. The study was conducted in collaboration with the Ente ospedaliero cantonale (EOC).

SUPSI Image Focus

Caption test

Hidden Widget