01
Biosignal Intelligence
Continuous ECG, PPG, EEG, EDA and heart-rate variability as windows into physiological adaptation, stress and human performance.
Biosignals · Artificial Intelligence · Medical Education
Building the infrastructure between physiological signals and meaningful AI.
I develop transparent, context-aware approaches for transforming continuous physiological data into reproducible and inference-ready information for research, clinical environments and medical education.
Morris Gellisch
Researcher · B-AI Lab · Ruhr University Bochum
Institutional affiliation
Ruhr University Bochum
Medical Faculty
Medical Faculty
01 · Research Vision
From physiological signals to meaningful context.
My research explores how continuous physiological data can be transformed into transparent, contextualized and inference-ready information — creating reproducible foundations for artificial intelligence in medicine and medical education.
02
AI-ready Health Data Infrastructure
Transparent pipelines for synchronized acquisition, preprocessing, contextualization and transformation of physiological streams into machine-readable data objects.
03
Stress, Learning & Medical Education
Physiological and computational approaches to understanding stress, performance, simulation and learning in medical education.
Research architecture
Sensors
→
Signals
→
Synchronization
→
Context
→
Data Objects
→
AI & Inference
02 · Current Projects
Research in motion.
Selected projects connecting physiological measurement, computational infrastructure and real-world clinical or educational environments.
Infrastructure
Real-time physiological data infrastructure
A software architecture for transforming continuous physiological streams into synchronized, contextualized and machine-readable objects for downstream analysis and AI.
Ongoing
Clinical AI
Multimodal physiological monitoring
Integrating ECG, PPG, EEG, EDA and contextual information to investigate computational approaches to physiological state recognition in clinical environments.
Ongoing
Medical Education
Stress physiology in learning and assessment
Studying autonomic responses during simulation, problem-based learning and assessment to understand how educational environments shape physiological stress and performance.
Ongoing
Software
Infrastructure before inference.
Reliable artificial intelligence starts before model training. The B-AI software framework is designed around transparent acquisition, preprocessing, synchronization and contextualization of continuous physiological data.
The aim is to create auditable and reproducible data pathways that remain interpretable from the original signal to downstream computational inference.
Real-time biosignal streaming
Transparent signal processing
Event and context synchronization
Machine-readable data objects
AI and ML integration
03 · Publications
Selected work.
Research spanning physiological computing, stress physiology, digital health and medical education.
2026
Selected publication title will appear here.
Physiological computing · Digital health
2026
Selected publication title will appear here.
Medical education · Stress physiology
2025
Selected publication title will appear here.
Heart-rate variability · Real-time infrastructure
04 · Media & Press
Research beyond the paper.
Selected features, institutional coverage and public-facing communication around ongoing research.
Research feature
Institutional coverage will appear here.
Invited talks & scientific communication
Selected talks and presentations.
Public engagement
Interviews, podcasts and other formats.
05 · Collaborate
Good research becomes more interesting when disciplines meet.
I am interested in collaborations involving continuous biosignal acquisition, multimodal physiological data, transparent AI, digital health infrastructure and medical education research.
Get in touch