Publications by authors named "L Baecker"

In the context of climate change, the impacts of extreme weather events are increasingly recognised as a significant threat to mental health in the UK. As clinicians and researchers with an interest in mental health, we have a collective responsibility to help understand and mitigate these impacts. To achieve this, however, it is vital to have an appreciation of the relevant policy and regulatory frameworks.

View Article and Find Full Text PDF

Mapping brain-behaviour associations is paramount to understand and treat psychiatric disorders. Standard approaches involve investigating the association between one brain and one behavioural variable (univariate) or multiple variables against one brain/behaviour feature ('single' multivariate). Recently, large multimodal datasets have propelled a new wave of studies that leverage on 'doubly' multivariate approaches capable of parsing the multifaceted nature of both brain and behaviour simultaneously.

View Article and Find Full Text PDF
Article Synopsis
  • Machine learning is being used to analyze structural neuroimaging data for brain age prediction, which helps assess changes in brain anatomy with age.
  • This process involves creating a regression model based on healthy individuals' brain data and applying it to new subjects, leading to a comparison between predicted brain age and actual chronological age.
  • The resulting 'brain-age gap' may indicate neuroanatomical issues and has potential clinical applications, including early detection and better management of brain disorders.
View Article and Find Full Text PDF

Normative modelling is an emerging method for quantifying how individuals deviate from the healthy populational pattern. Several machine learning models have been implemented to develop normative models to investigate brain disorders, including regression, support vector machines and Gaussian process models. With the advance of deep learning technology, the use of deep neural networks has also been proposed.

View Article and Find Full Text PDF
Article Synopsis
  • Brain morphology changes with age, and predicting a person's brain age can help identify age-related abnormalities.
  • This study analyzed UK Biobank data (10,824 participants, ages 47-73) to compare different machine learning models for brain age prediction using structural MRI data.
  • The best results showed mean absolute errors of 3.7 to 4.7 years, with models using voxel-level data and principal component analysis performing the best, highlighting that input data type is more crucial than the model choice itself.
View Article and Find Full Text PDF