PsyAgent AI Agent Psychological Research Platform
We are developing PsyAgent - a research platform to model mental health in virtual environments using LLM-based generative agents.
Kambeitz Lab · University Hospital Cologne
AI and computational research in mental health
We combine clinical expertise with artificial intelligence and computational modelling to understand mental illness and improve how we predict its course. Our goal is to translate these insights into earlier recognition, more personalised treatment and better prevention.
Research themes
All researchPrediction & precision psychiatry
Machine-learning models that forecast individual outcomes in people at clinical high risk.
4 projects
Language & digital markers
Speech, language and smartphone data as scalable markers of mental health.
2 projects
Computational modeling & generative agents
Brain-network simulations, symptom networks, digital twins and LLM-based agents.
3 projects
Clinical interventions
Trials and cohorts that turn insights into better treatment for young people.
2 projects
Latest news
All news
“Normaler als du denkst”
In this video, Priv.-Doz. Dr. Lana Kambeitz-Ilankovic explains severe mental disorders such as psychosis in an accessible and stigma-free way.
New paper! Can AI minds help understand mental health?
Can artificial minds help us understand what shapes mental health?
Selected publications
All publicationsIntegrated Youth Mental Health Services – niederschwellige, integrierte Angebote für junge Menschen in psychischen Krisen: Internationale Erfahrungen und die aktuelle Situation in Deutschland
Nervenarzt · 2025
Computational modelling reveals neurobiological contributions to static and dynamic functional connectivity patterns
Front Comput Neurosci 19, 1525785 · 2025
Modelling the impact of environmental and social determinants on mental health using generative agents
NPJ Digit Med 8, 36 · 2025
Join us
We welcome PhD, MD and MSc students and visiting researchers who want to work at the meeting point of clinic and computation.