Brain Charts and Normative Modeling for Dementia Stratification

Last updated on Nov 5, 2025 Neuroimaging, AI, Dementia

Validating data-driven population-reference models (Braincharts, Bethlehem et al., Nature, 2022) with neuroimaging and clinical records for disease stratification and prognosis in neurodegenerative cohorts.

This work involves analyzing neuroimaging and clinical data from memory clinics at Addenbrooke’s Hospital and other NHS trusts around the UK, using artificial intelligence (AI) and normative models to develop individualized tools for patient stratification and prognostication in dementia.

The project aims to:

  • Apply normative modeling approaches to identify individual-level deviations from healthy brain aging trajectories
  • Integrate multimodal neuroimaging data (structural MRI, diffusion, functional) with clinical and cognitive assessments
  • Develop AI-driven tools for early dementia detection and prognosis
  • Validate models across large-scale memory clinic cohorts (QMIN-MC, NACC)
Neuroimaging AI Dementia Normative Modeling
Marcella Montagnese
Marcella Montagnese
Junior Research Fellow & Research Associate in Neuroinformatics

My research interests include the application of neuroimaging (fMRI, DWI, EEG) and graph theory to the study of psychopathology and dementia. I mainly work on psychosis both in neurodegenerative disorders such as Parkinson’s Disease, as well as in schizophrenia. My recent work focuses on using Artificial Intelligence for early dementia detection and prognosis.

Related