Â鶹´«Ã½Ó³»­

Â鶹´«Ã½Ó³»­

Explore the latest content from across our publications
Join The Â鶹´«Ã½Ó³»­

Log In

Forgot Password?
Create New Account

Loading... please wait

Abstract Details

Clustering and Prediction of Disease Progression Trajectories in Huntington’s Disease: an Analysis of the Enroll-HD and REGISTRY Database Using a Machine Learning Approach
Movement Disorders
Movement Disorders Posters (7:00 AM-5:00 PM)
147
Describe joint longitudinal trajectories of several manifest Huntington’s disease (HD) clinical variables and determine which genetic/medical/family history variables are predictive of trajectory pattern.

HD is a rare, genetic, neurodegenerative disease caused by a cytosine adenine guanine (CAG) expansion and characterized by a triad of cognitive, behavioral and motor symptoms. A thorough characterization of manifest HD progression, and identification of patient profiles related to different progression patterns are needed.

Data from participants with manifest HD and ≥2 annual visits in the longitudinal, global observational Enroll-HD study were included (NCT01574053; N=4,514). Demographics at enrollment were considered as at visit because baseline from Enroll-HD is not a true baseline for manifest HD. A K-means method for joint longitudinal trajectories was used to cluster participants based on similarities in progression trajectories in motor, cognitive and behavioral domains. Impactful variables that predicted trajectory assignment were identified using the eXtreme Gradient Boosting machine learning algorithm (XGBoost) from pre-selected demographic, genetic/medical/family history, social, symptom and medication-use variables.
Participants were grouped as rapid, moderate or slow progressors based on joint longitudinal trajectories of Total Motor Score, Symbol Digit Modalities Test and Apathy scores. The top 10 predictors of trajectory pattern were CAG-age product (CAP) score at visit, years since rater’s diagnosis to visit, body mass index (BMI) at visit, no medical history of apathy, age at visit, father’s age of onset if has HD, mother’s age of onset if has HD, no prior tetrabenazine use, without companion at visit and no medical history of cognitive impairment.
CAP score at visit was the strongest predictor of trajectory pattern, followed by years since rater’s diagnosis to visit and BMI at visit. The clustering and prediction provide a profile for different rates of manifest HD progression, which may be useful for guiding future personalized clinical care and management plans.
Authors/Disclosures
Jinnie Ko (Genentech Inc)
PRESENTER 		Jinnie Ko has received personal compensation for serving as an employee of Genentech.
No disclosure on file
Xiaoye Ma Xiaoye Ma has received personal compensation for serving as an employee of Genentech.
Jeffrey D. Long Jeffrey Long has received personal compensation in the range of $5,000-$9,999 for serving as a Consultant for Triplet. Jeffrey Long has received personal compensation in the range of $10,000-$49,999 for serving as a Consultant for Vacinnex. Jeffrey Long has received personal compensation in the range of $500-$4,999 for serving as a Consultant for Wave. Jeffrey Long has received personal compensation in the range of $0-$499 for serving as a Consultant for PTC. Jeffrey Long has received personal compensation in the range of $500-$4,999 for serving as a Consultant for Genentech. Jeffrey Long has received personal compensation in the range of $10,000-$49,999 for serving on a Scientific Advisory or Data Safety Monitoring board for Roche. Jeffrey Long has received personal compensation in the range of $500-$4,999 for serving on a Scientific Advisory or Data Safety Monitoring board for uniQure. Jeffrey Long has received research support from NIH DSMB.
Xiao-Yu Lu Xiao-Yu Lu has received personal compensation for serving as an employee of Genentech.
Diana Slowiejko Diana Slowiejko has received personal compensation for serving as an employee of Genentech Inc.
Rita Gandhy, MD Dr. Gandhy has received personal compensation for serving as an employee of Genentech.