Bartlomiej Chybowski

Research Associate in EEG signal analysis

  • Institute for Imaging, Data and Communications

Contact details

Address

Street

Usher Building, The University of Edinburgh
5-7 Little France Road
Edinburgh BioQuarter - Gate 3

City
Edinburgh
Post code
EH16 4UX

Background

I recently passed my PhD at the University of Edinburgh as part of the Epilepsy Research Institute UK Doctoral Training Centre, where my research focused on computational models of seizure activity and brain state dynamics in epilepsy. Prior to this, I obtained an MSc in Computer Science with Distinction from Robert Gordon University and a BEng-equivalent in Computer Science from Silesian University of Technology.

Before my PhD, I worked as a software developer and data scientist in Poland and the United Kingdom and completed a research internship at the Czech Academy of Sciences, where I worked on machine learning approaches for epileptic foci localisation.

During my PhD, I took research interruptions to work on collaborative projects at the University of Edinburgh on automated seizure detection and clinical EEG analysis, where I developed a machine learning pipeline for processing clinical EEG recordings.

Research summary

My research interests lie at the intersection of neuroscience and machine learning, with a particular focus on the analysis of brain signals in humans and rodents. I am interested in developing robust and generalisable data-driven methods for understanding neural activity and identifying physiological and behavioural states from electrophysiological recordings. My work combines computational modelling, signal processing, and machine learning to support both scientific discovery and translational applications in neuroscience and healthcare.

Current research interests

My current research focuses on the development of machine learning frameworks for the detection of epileptic seizures from EEG recordings. I work on creating robust and generalisable models that can operate across different datasets and recording conditions, with the aim of improving automated seizure detection and supporting future clinical decision-making. I am particularly interested in translational approaches that bridge methodological advances in machine learning with practical applications in epilepsy research and clinical neuroscience.