Log In

Forgot Password?
Create New Account

Loading... please wait

Abstract Details

Establishing Reproducibility of Clinical Clusters Across Parkinson’s Disease Cohorts
Movement Disorders
P11 - Poster Session 11 (5:30 PM-6:30 PM)
PD is a heterogeneous disorder that is likely composed of several subgroups with distinct clinical features and patterns of disease progression. Cluster analysis is a valuable tool for characterizing phenotypic variability in clinical cohorts and for correlating phenotypes with biomarkers. However, data collection methods often differ between clinical and research settings, limiting the ability to obtain statistically significant results from smaller or less characterized cohorts and to compare results across studies. Establishing reproducibility of cluster analysis across sites would allow for greater generalizability. 
To establish reproducibility of phenotype-based clustering in two independent datasets of patients with Parkinson’s disease (PD).

Non-hierarchical k-means clustering by phenotype of subjects in the large Parkinson’s Progressive Marker Initiative (PPMI) Validation Cohort (n=368) and a smaller, independent Discovery Cohort (n=179) was performed via Principal Component Analysis (cohort-based clusters). Eigenvectors of clustering of the Validation Cohort were used to re-cluster the Discovery Cohort (PPMI-based clusters). Overlap in cluster membership between cohort-based and PPMI-based clusters of the Discovery Cohort was assessed.

We identified two clusters in the Discovery Cohort and three clusters in the Validation Cohort. The first four principal components for clustering of the Validation Cohort, accounting for 43% of the variability, were driven by depression, anxiety, age at symptom onset, gender, and tremor-dominance. After re-clustering the Discovery Cohort based on these traits, 77% of subjects remained in their original cluster.  
We successfully validated reproducibility of clustering in our Discovery Cohort. We propose a combination of non-hierarchical cluster analysis and cross-validation with re-clustering to establishing clustering reproducibility. This method can be adapted for use in a range of clinical scenarios to validate cohorts that are less extensively characterized or have low intrinsic power secondary to low sample size.
Kristen Watkins, MD (NYU Langone)
Dr. Watkins has nothing to disclose.
Julia H. Greenberg, MD Dr. Greenberg has a non-compensated relationship as a Editorial Board Member with Neurology Resident and Fellow Section that is relevant to AAN interests or activities.
Kelly Astudillo (NYU Langone Health) No disclosure on file
Charalambos Argyrou No disclosure on file
John Crary No disclosure on file
Steven Frucht, MD (New York University Medical Center) Dr. Frucht has nothing to disclose.
Towfique Raj No disclosure on file
Giulietta Riboldi, MD (New York University) The institution of Dr. Riboldi has received research support from Prevail Therapeutics.