• Select the area you would like to search.
  • ACTIVE INVESTIGATIONS Search for current projects using the investigator's name, institution, or keywords.
  • EXPERTS KNOWLEDGE BASE Enter keywords to search a list of questions and answers received and processed by the ADNI team.
  • ADNI PDFS Search any ADNI publication pdf by author, keyword, or PMID. Use an asterisk only to view all pdfs.
Principal Investigator  
Principal Investigator's Name: Bahaaldin Helal
Institution: Western University
Department: Biomedical Engineering
Proposed Analysis: Hypothesis: If PD is indeed a heterogeneous syndrome, we hypothesize that patients will ‘cluster’ into distinct phenotypes characterized by multifactor longitudinal trajectories of neurodegeneration, cognitive and motor changes and pathology. Research objectives: We will test this hypothesis in two primary objectives. First, we will integrate within-subjects measures of multifactor longitudinal data from the Parkinson’s Progression Markers Initiative (PPMI), a large study consisting of longitudinal structural magnetic resonance imaging (sMRI), cerebrospinal fluid (CSF) biomarkers of protein pathology, and comprehensive clinical evaluation of motor and cognitive functions. We will then employ quantitative multimodal data fusion using joint independent components (jIC) analysis techniques (Qi et al. 2019) which leverages multiple data types to uncover the latent relationships that might be missed from single modality analysis. Each jIC might therefore reveal a distinct combination of degeneration of a specific brain structure (e.g. substantia nigra, basal forebrain, cortex), increase in a specific pathology (e.g. amyloid-ꞵ, tau, α-synuclein), and decline in a subset of cognitive or motor functions (e.g. memory, executive function, gait, tremor). Next we will employ machine learning techniques to see if identified jICs cluster into distinct subgroups of individuals. If we detect clustering of individuals according to distinct jICs, this will support our hypothesis that distinct phenotypes of PD are characterized by multifactor longitudinal trajectories of disease progression. The second objective is an exploratory analysis. Here we will integrate a harmonized subset of multifactor longitudinal data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset and compute jICA on these data, using the same techniques as those in the first objective. We will then pool the PPMI and ADNI datasets to determine whether clustering identifies both distinct and overlapping clusters of individuals from each consortia. Evidence in favor of mixed clustering would support a multifactor phenotypic axis spanning AD and PD.
Additional Investigators