Joint modeling to predict the probability of progression from mild cognitive impairment to Alzheimer's disease
Joint modeling to predict the probability of progression from mild cognitive impairment to Alzheimer's disease
Joint longitudinal-survival models are useful when repeated measurements and event times are available and possibly associated.
Different types of data for each subject at multiple timepoints leading up to a conversion event, such as the conversion from Mild Cognitive Impairment (MCI) to Alzheimer's Disease (AD). These data, obtained from the ADNI (Alzheimer's Disease Neuroimaging Initiative) datasets, include known biomarkers related to amyloidosis and neurodegeneration such as CSF ABeta 1-42, CSF tau, FDG-PET, hippocampal volumes (HV) measured through MRI, as well as neuropsychological test scores like ADAS-Cog and MMSE.
The goal of this thesis is to investigate the association between longitudinal biomarker (eg. HV) and event of interest (eg. Conversion to AD), and subsequently employ this association to predict the time of conversion for new subjects.
Many published articles have demonstrated this association, but not explicitly indicate the risk probability of progression. Separate analysis of longitudinal biomarkers and time-to-conversion may lead to inefficient or biased results. Joint models for longitudinal and survival data trait information simultaneously and provide valid and efficient inferences (L. Wu et al., 2011).
Candidates with a Master's/engineering degree (or equivalent) in artificial intelligence, statistics, biostatistics, computational biology or computer science (big data analysis) with mastery of R and/or Python software and having experience in statistical modeling in the health field (considered an asset). Additionally, the candidate must be good in English.
Registration procedure
- Application file: Curriculum vitae, cover letter, end-of-studies project, diplomas and transcripts
- Working conditions: The doctoral student will carry out full-time research work at the Euromed University of Fez
File to be sent to a.mouiha@ueuromed.org before November 10, 2023