Clustering and prediction of disease progression trajectories in Huntington's disease: An analysis of Enroll-HD data using a machine learning approach

Abstract

IntroductionHuntington's disease (HD) is a rare neurodegenerative disease characterized by cognitive, behavioral and motor symptoms that progressively worsen with time. Cognitive and behavioral signs of HD are generally present in the years prior to a diagnosis; however, manifest HD is typically assessed by genetic confirmation and/or the presence of unequivocal motor symptoms. Nevertheless, there is a large variation in symptom severity and rate of progression among individuals with HD.MethodsIn this retrospective study, longitudinal natural history of disease progression was modeled in individuals with manifest HD from the global, observational Enroll-HD study (NCT01574053). Unsupervised machine learning (k-means; km3d) was used to jointly model clinical and functional disease measures simultaneously over time, based on one-dimensional clustering concordance such that individuals with manifest HD (N = 4,961) were grouped into three clusters: rapid (Cluster A; 25.3%), moderate (Cluster B; 45.5%) and slow (Cluster C; 29.2%) progressors. Features that were considered predictive of disease trajectory were then identified using a supervised machine learning method (XGBoost).ResultsThe cytosine adenine guanine-age product score (a product of age and polyglutamine repeat length) at enrollment was the top predicting feature for cluster assignment, followed by years since symptom onset, medical history of apathy, body mass index at enrollment and age at enrollment.ConclusionsThese results are useful for understanding factors that affect the global rate of decline in HD. Further work is needed to develop prognostic models of HD progression as these could help clinicians with individualized clinical care planning and disease management.