Multimodal phenotypic axes of Parkinson’s disease

Abstract

Individuals with Parkinson’s disease present with a complex clinical phenotype, encompassing sleep, motor, cognitive, and affective disturbances. However, characterizations of PD are typically made for the “average” patient, ignoring patient heterogeneity and obscuring important individual differences. Modern large-scale data sharing efforts provide a unique opportunity to precisely investigate individual patient characteristics, but there exists no analytic framework for comprehensively integrating data modalities. Here we apply an unsupervised learning method—similarity network fusion—to objectively integrate MRI morphometry, dopamine active transporter binding, protein assays, and clinical measurements from n = 186 individuals with de novo Parkinson’s disease from the Parkinson’s Progression Markers Initiative. We show that multimodal fusion captures inter-dependencies among data modalities that would otherwise be overlooked by field standard techniques like data concatenation. We then examine how patient subgroups derived from the fused data map onto clinical phenotypes, and how neuroimaging data is critical to this delineation. Finally, we identify a compact set of phenotypic axes that span the patient population, demonstrating that this continuous, low-dimensional projection of individual patients presents a more parsimonious representation of heterogeneity in the sample compared to discrete biotypes. Altogether, these findings showcase the potential of similarity network fusion for combining multimodal data in heterogeneous patient populations.

Immersive Technology for Cognitive-Motor Training in Parkinson’s Disease

“…Interestingly, both the trainers and assessors noted clear phenotypic differences in participants as they performed the assessments and/or training. PD is a heterogenous disease often viewed as a movement disorder with three motor types: Tremor-dominant; akinetic-rigid or postural instability with gait difficulty; or indeterminate ( Luo et al, 2019 ; Wojtala et al, 2019 ; Markello et al, 2021 ). The clinical spectrum of PD encompasses many non-motor domains like cognition and autonomic function.…”

The Gut–Brain Axis and Its Relation to Parkinson’s Disease: A Review

“…or pathological disease progression, or whether they may be indicative of the microbiota being a true contributing factor of PD. Given the complex bidirectional relationship between the microbiome and host health in addition to the heterogeneity in clinical phenotypes of PD (Markello et al, 2021), is possible that microbiota dynamics are both a product PD pathology as well as potential drivers for the onset and progression of the disease.…”

Deep phenotyping for precision medicine in Parkinson's disease

“…demographics), will often be preferred by algorithms simply because of their size and thus larger influence. Markello et al (2021) have proposed creating a similarity network for each data modality separately and then iteratively fusing these together. This similarity network fusion approach has the advantage of overcoming the dimensionality bias, plus it generates a low-dimensional representation of each source that can be interpreted.…”