Project description
Personalised intervention for psychiatry
Psychiatry lags in many areas of medicine that use biomarkers to assist with diagnosis and personalised treatment (precision medicine). The EU-funded MENTALPRECISION project will bring precision medicine within reach for psychiatry. It will develop a set of principled, next generation analysis tools to stratify mental disorders. This will be done using biomarkers derived from population-scale neuroimaging and quantitative measures of behaviour from smartphone-based digital phenotyping. A universal platform to understand shared and distinct mechanisms of mental disorders – at the level of the individual – will be created based on neuroimaging samples from tens of thousands of people. These will be based on a novel ‘brain growth charting’ methodology.
Objective
In many areas of medicine, biomarkers have revolutionised 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 extreme heterogeneity at every level.
My vision is to provide a set of principled, next generation analysis tools to stratify mental disorders on the basis of biomarkers derived from population-scale neuroimaging and quantitative measures of behaviour from smartphone-based digital phenotyping.
I will build generative models to chart variation in brain organisation across massive neuroimaging samples from more than 40,000 individuals based on ‘brain growth charting’ methodology I have pioneered. This will provide a universal platform to understand shared and distinct mechanisms of mental disorders at the level of the individual, simulate clinical brain states and test putative interventions using synthetic data.
I will develop innovative machine learning tools to: (1) learn latent dynamics of digital phenotyping measures; (2) parse the dynamic interplay between brain systems and the behaviours they underpin; (3) integrate complementary information from distinct data modalities and (4) stratify mental disorders in a way that cuts across diagnostic classifications and accommodates different mechanisms converging on the same symptoms.
These innovations will have far-reaching impact; here, I will showcase them by predicting trajectories of resilience and risk in major depression and bipolar disorder which are a leading cause of worldwide disease burden. This will bring precision medicine within reach for psychiatry allowing early, personalized intervention, preventative treatments and a better understanding of disorder entities.
Fields of science
- natural sciencesbiological sciencesneurobiology
- medical and health sciencesclinical medicinepsychiatry
- natural sciencescomputer and information sciencesartificial intelligencegenerative artificial intelligence
- medical and health scienceshealth sciencespersonalized medicine
- natural sciencescomputer and information sciencesartificial intelligencemachine learning
Programme(s)
Funding Scheme
ERC-COG - Consolidator GrantHost institution
6525 GA Nijmegen
Netherlands