Author: Andre Marquand
Affiliation(s): Radboudumc/ Donders Center for Cognitive Neuroimaging
Keywords: smartphone monitoring, neuroimaging, digital phenotyping
Research question(s):
In this study we will link neurobiological measures (structural connectivity, functional connectivity
and brain structure) with real-time smartphone monitoring in order to predict the symptoms of
psychiatric disorders
Abstract:
In many areas of medicine, biomarkers have improved diagnosis and personalised treatment allocation (‘precision medicine’). Psychiatry lags behind: disorders are still diagnosed by symptoms and no biomarkers have been found. However, addressing this is a formidable task because of a lack of analysis tools to understand the complex disruptions of mental disorders at multiple levels – from neurobiology to behaviour – and to tackle their heterogeneity at every level.
In this proposal we aim to overcome this problem by linking biological markers derived from neuroimaging, with quantitative measures of behaviour derived from passive smartphone monitoring. For the neurobiological measures we will leverage large scale normative models estimated on tens of thousands of individuals to derive a set of deviation scores that permit inference at the level of the individual. At the same time, the behavioural measures we have acquired monitor behaviour quantitatively in the real world. These measures have been acquired from individuals from the HBS who have also participated in our study. We will also apply these
measures to the clinical MIND-Set study for whom we have comparable measures available, thereby aiming to derive associations that are valid in healthy individuals and in individuals with a clinical diagnosis.
This project therefore aims to take the first steps in understanding how the interaction between biological risk and real-world behaviour gives rise to risk or resilience for mental disorders.
In the spirit of open science, we will also disseminate all outputs from this project widely, for example using github. We will also feed all derived measures back into the HBS platform for further use by other researchers.