< Back to previous page

Project

A data-driven approach to identifying stress response phenotypes based on affective and physiological markers of vulnerability & their added value to stress prediction in daily life

Advances in wearable technology allow for the continuous assessment of physiological data to get a detailed picture of daily-life dynamics associated with the development of mental illness. Specific physiological state transitions may hold prognostic value in the course of development, treatment, and relapse of mental disorders. Computational modelling of the physiological data is a promising approach in predicting this course. Physiological state transitions can be observed in different time-windows. On a momentary level, minute-to-minute changes in physiology, such as in the case of acute stress and recovery from acute stress, may predict specific illness-related behavior and symptoms. On the longer term, more structural alterations in physiology such as chronic stress or patterns in circadian rhythm may signal important phases in illness progression, treatment effects, or relapse. During this PhD, new computational models will be applied to detect daily life markers of state transitions related to mental health. Among the data used are existing datasets that have been collected within IMEC and the Psychiatry Research Group of the KU Leuven in healthy volunteers and individuals with psychiatric complaints.

Date:1 Oct 2022 →  Today
Keywords:ESM, Wearables, Models of mental health, Computational modelling, Machine learning
Disciplines:Human health engineering, Knowledge representation and machine learning, Mathematical psychology, Computational biomodelling and machine learning, Psychopathology, Biological psychology
Project type:PhD project