CARE-PD: A Multi-Site Anonymized Clinical Dataset for Parkinson's Disease Gait Assessment
Authors
Vida Adeli
Ivan Klabucar
Javad Rajabi
Benjamin Filtjens
Soroush Mehraban
Diwei Wang
Hyewon Seo
Trung-Hieu Hoang
Minh N. Do
Candice Muller
Claudia Oliveira
Daniel Boari Coelho
Pieter Ginis
Moran Gilat
Alice Nieuwboer
Joke Spildooren
Lucas Mckay
Hyeokhyen Kwon
Gari Clifford
Christine Esper
Stewart Factor
Imari Genias
Amirhossein Dadashzadeh
Leia Shum
Alan Whone
Majid Mirmehdi
Andrea Iaboni
Babak Taati
Abstract
Objective gait assessment in Parkinson's Disease (PD) is limited by the absence of large, diverse, and clinically annotated motion datasets. We introduce CARE-PD, the largest publicly available archive of 3D mesh gait data for PD, and the first multi-site collection spanning 9 cohorts from 8 clinical centers. All recordings (RGB video or motion capture) are converted into anonymized SMPL meshes via a harmonized preprocessing pipeline. CARE-PD supports two key benchmarks: supervised clinical score prediction (estimating Unified Parkinson's Disease Rating Scale, UPDRS, gait scores) and unsupervised motion pretext tasks (2D-to-3D keypoint lifting and full-body 3D reconstruction). Clinical prediction is evaluated under four generalization protocols: within-dataset, cross-dataset, leave-one-dataset-out, and multi-dataset in-domain adaptation. To assess clinical relevance, we compare state-of-the-art motion encoders with a traditional gait-feature baseline, finding that encoders consistently outperform handcrafted features. Pretraining on CARE-PD reduces MPJPE (from 60.8mm to 7.5mm) and boosts PD severity macro-F1 by 17 percentage points, underscoring the value of clinically curated, diverse training data. CARE-PD and all benchmark code are released for non-commercial research at https://neurips2025.care-pd.ca/.
