Towards personalized prevention of stress-related disorders with computational phenotyping.
Stress-related disorders, like depression and anxiety, are very common, difficult to treat despite years or research, and have a dramatic impact on quality of life and participation in society. Early detection of vulnerability, before escalating into a full blow disorder, is urgently needed, to enable timely preventative intervention. I propose a new method to identify individuals at-risk for stress-related disorders, and track for each individual which aspect requires intervention.
To this end, I will leverage the rich multi-dimensional data available in the Healthy Brain Study dataset, integrating behavior of multiple cognitive tasks in the lab to predict people’s mental well-being in real life (measured with ecological momentary assessment and physiology). This method combines computational modeling with smartphone/ smartwatch real-life measurements, laying the grounds for personalized cost-effective prevention.