Accelerometer data of individuals with Huntington's disease and healthy controls from in-clinic assessment

Participants with Huntington's Disease (HD) and age-matched healthy controls (HC) were recruited as part of a study designed to evaluate the feasibility, acceptability, and utility of wearable activity monitors in people with early-mid stage HD. Tri-axial accelerometer signals were collected using wrist-worn devices (GENEActiv, Activinsights; 43 × 40 × 13 mm; weight: 16 g; 100 Hz sampling rate) during an in-clinic assessment. Participants completed a set of standardized laboratory-based functional activities, reflecting independent activities of daily living. The in-clinic assessment lasted 60-90 minutes per participant. The in-clinic assessments were video-recorded, and these videos were subsequently used in the labeling procedure of the accelerometer signals. The dataset contains a csv file for each participant with the 3 axis accelerometer recording, as well as labels for walking detection. An anonymized metadata table is also provided with demographic information and clinical scores. 

Files description:
Each csv file is named with a serial number representing a participant. 
Each file contains 3 axis of accelerometer recordings (i.e., X, Y, Z) that was recorded in a sample rate of 100 Hz.
The forth column contains labels for each sample according to the following: 1=walking , 0=non-walking, -1 = cannot be marked (due to the patients being obscured from the camera). 
Additional metadata file is provided that include the following information regarding each participant in the columns: 

• Huntington's Disease patient/healthy control (HD=1, HC=2)
• Sex (Male=1, Female=2)
• Age
• Birthday
• Height
• Weight
• TMS (Total Motor Score)
• FA (Functional Assessment)
• TFC (Total functional capacity)

Additional relevant information is available in the paper. 

Kindly cite of the following paper when using this data:

D. Schwartz, L. Quinn, N. E. Fritz, L. M. Muratori, J. M. Hausdorff, and R. G. Bachrach, Detecting daily living gait amid huntington’s disease chorea using a foundation deep learning model, 2024. arXiv:2412.11286 [cs.CV]. url: https://arxiv.org/abs/2412.11286.