Contact information
Research groups
Colleges
Alexander Tashevski-Beckwith
Graph-based Causal Machine Learning for Investigating the Aetiology of Alzheimer’s Disease
I am a DPhil student and member of the bioinformatics team in the Translational Neuroscience and Dementia Research Group, specialising in causal machine learning methods to study disease mechanisms in Alzheimer’s disease. After working as a support worker within Australia’s National Disability Insurance Scheme (NDIS), I completed my training as a Clinical Psychologist at the University of Sydney. I then moved into machine learning and quantitative policy work within the Department of the Prime Minister and Cabinet, including serving as a principal advisor for mental health on the Australian Government’s COVID-19 Review and conducting prospective analyses of new medical treatments for the public healthcare system within the Behavioural Economics Team (BETA).
My current research examines the use and development of causal machine learning and graph-based models to understand how different biological and clinical factors contribute to the development and progression of Alzheimer’s disease. These methods facilitate predictions that are both accurate and interpretable to clinicians and researchers.
More broadly, I am interested in how complex patterns in psychiatry and psychology arise from many interacting factors, such as genes, brain changes, life experiences, and symptoms over time. By building models that can represent this high-dimensional structure in a transparent way, I aim to identify new, robust patterns that help explain human behaviour and the mechanisms underlying mental and neurological disorders.