Development of AI tools for automated analysis of sleep EEG recordings and detection of clinically meaningful features
Automatizing sleep analysis for diagnosing and monitoring the effects of diseases and therapeutic interventions on sleep in children
Electroencephalography (EEG) is an essential tool for monitoring brain activity and plays a central role in the diagnosis and management of neurological disorders such as epilepsy. In clinical practice, overnight EEG recordings provide valuable insights into both epileptic activity and sleep-related brain dynamics, generating large and complex datasets that require expert interpretation.
Our work focuses on the development of artificial intelligence tools for automated analysis of EEG recordings in children. These tools are designed to detect clinically relevant features, including epileptic discharges and sleep-related patterns, directly from long-term EEG data.
By integrating AI-assisted analysis into clinical workflows, we aim to support clinicians with faster, more standardized, and more comprehensive evaluation of EEG recordings. In addition to clinical applications, these methods can also facilitate large-scale data processing in clinical research and trials, enabling more efficient and reproducible analysis of EEG data.
Research group
Group Leader: Prof. Dr. Reto Huber
Project Leader: Dr. Jelena Skorucak
Institution:
Child Development Center
University Children's Hospital Zurich
University of Zurich
Funding
- Swiss National Science Foundation (320030_179443)
- University of Zurich Postdoc Grant (FK-21-049)
- University of Zurich Entrepreneur Fellowship (MEDEF22-033)
- Innosuisse Innovation project grant (123.768 IP-LS)