PhD Position: AI-assisted EEG Monitoring in the ICU

Continuous EEG (cEEG) monitoring is essential for managing patients in the intensive care unit (ICU), especially after cardiac arrest or severe brain injury. Yet, clinical use is hampered by limited local expertise and the time-intensive nature of EEG interpretation.

This project aims to develop advanced EEG sensing technology integrated with a cloud-based platform for real-time data analysis and remote expert consultation. The goal is to create an explainable AI-assisted monitoring system that improves decision-making in the ICU and ultimately patient outcomes. The system will be piloted at Medisch Spectrum Twente (MST), with the ambition to scale to (inter)national hospitals.

As PhD candidate, you will contribute to the full development pipeline: from algorithm design and implementation to clinical integration and evaluation. You will also work on improving prognostic models using (neuro-symbolic) AI and develop intuitive, explainable tools for clinicians.

Your RoleYou will work at the interface of signal processing, AI, and clinical neurophysiology. The project involves close collaboration with MST, the University of Twente TechMed-CNPH and BMS-CodE groups , and industry partners Artinis Medical Systems and Clinical Science Systems.

We are looking for a highly motivated candidate with:

• A Master’s degree in Technical Medicine, Biomedical Engineering, or a related field;
• Interest in translational research bridging technology and clinical care;
• Affinity with signal processing, machine learning, and/or physiological monitoring;
• Strong teamwork and communication skills in multidisciplinary environments;
• Strong programming skills and experience with implementing machine learning algorithms
• Proficiency in English and Dutch (spoken and written);
• German language skills are a plus.

Mission statement and research lines Clinical Neurophysiology group (CNPH)

Research in the Clinical Neurophysiology group is at the interface of neuroscience, neurophysiology, and clinical neurology, focusing on cerebral ischemia and epilepsy. In addition, to improve understanding of pathophysiology, we aim to develop novel diagnostic tools and treatments. Our research is truly translational: from the UT to the clinic and back.

The EEG is a key clinical and research tool. EEG signal analysis includes various machine learning techniques to improve diagnostic values and (bedside) application. Applied EEG studies are complemented by biophysical modeling and simulation for improved understanding of underlying neuronal dynamics and prediction of treatment effects. In addition, we use in vitro models consisting of cultured neurons (from rodent or human induced pluripotent stem cells) on multi-electrode arrays to study basic neuronal and synaptic functioning, identify treatment targets, and screen treatments.