Care-PD: A Multi-Site Anonymized Clinical Dataset for Parkinson’s Disease Gait Assessment

Vida Adeli, Ivan Klabučar, Javad Rajabi, Benjamin Filtjens, Soroush Mehraban, Diwei Wang, Trung-Hieu Hoang, Minh N. Do, Hyewon Seo, Candice MULLER, Daniel Boari Coelho, Claudia Eunice Neves de Oliveira, Pieter Ginis, Moran Gilat, Alice Nieuwboer, Joke Spildooren, J. Lucas Mckay, Hyeokhyen Kwon, Gari Clifford, Christine D Esper et al. (8 additional authors not shown)

Keywords: Parkinson’s Disease, Gait Assesment, Clinical Severity Prediction, Multi-site Dataset, Human Motion Encoder, Healthcare AI

TL;DR: We introduce Care-PD a multi-site dataset and benchmark for Parkinson’s gait analysis, enabling robust clinical severity prediction and improving motion representation learning through diverse, anonymized pathological gait data.

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\%, underscoring the value of clinically curated, diverse training data. Care-PD and all benchmark code are released for non-commercial research (Code, Data).

Dataset URL: https://doi.org/10.5683/SP3/TWIKMK

Code URL: https://github.com/TaatiTeam/CARE-PD

Primary Area: AL/ML Datasets & Benchmarks for health sciences (e.g. climate, health, life sciences, physics, social sciences)

Submission Number: 718