# Benchmarking Skeleton-based Motion Encoder Models for Clinical Applications: Estimating Parkinson's Disease Severity in Walking Sequences

arXiv: https://arxiv.org/abs/2405.17817 · HTML: https://mlsanity.com/paper/2405.17817/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 52 references that are in the map.
- First posted on arXiv 28 May 2024.

## Builds on (most cited first, 14 of 14)

- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [Convolutional Pose Machines](https://mlsanity.com/paper/1602.00134/) (2016)
- [MotionBERT: A Unified Perspective on Learning Human Motion Representations](https://mlsanity.com/paper/2210.06551/) (2022)
- [MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video](https://mlsanity.com/paper/2203.00859/) (2022)
- [PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation](https://mlsanity.com/paper/2303.17472/) (2023)
- [MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Network](https://mlsanity.com/paper/2310.16288/) (2023)
- [Towards a Deeper Understanding of Skeleton-based Gait Recognition](https://mlsanity.com/paper/2204.07855/) (2022)
- [Pose Transformers (POTR): Human Motion Prediction with Non-Autoregressive Transformers](https://mlsanity.com/paper/2109.07531/) (2021)
- [Deep 1D-Convnet for accurate Parkinson disease detection and severity prediction from gait](https://mlsanity.com/paper/1910.11509/) (2019)
- [Vision-based Estimation of MDS-UPDRS Gait Scores for Assessing Parkinson's Disease Motor Severity](https://mlsanity.com/paper/2007.08920/) (2020)
- [Vision-Based Assessment of Parkinsonism and Levodopa-Induced Dyskinesia with Deep Learning Pose Estimation](https://mlsanity.com/paper/1707.09416/) (2017)
- [1D-Convolutional transformer for Parkinson disease diagnosis from gait](https://mlsanity.com/paper/2311.03177/) (2023)
- [Towards Automated and Marker-less Parkinson Disease Assessment: Predicting UPDRS Scores using Sit-stand videos](https://mlsanity.com/paper/2104.04650/) (2021)
- [Pose2Gait: Extracting Gait Features from Monocular Video of Individuals with Dementia](https://mlsanity.com/paper/2308.11484/) (2023)

## Built on by (most cited first, 6 of 6)

- [GAITGen: Disentangled Motion-Pathology Impaired Gait Generative Model -- Bringing Motion Generation to the Clinical Domain](https://mlsanity.com/paper/2503.22397/) (2025)
- [CARE-PD: A Multi-Site Anonymized Clinical Dataset for Parkinson's Disease Gait Assessment](https://mlsanity.com/paper/2510.04312/) (2025)
- [AGIR: Assessing 3D Gait Impairment with Reasoning based on LLMs](https://mlsanity.com/paper/2503.18141/) (2025)
- [SkelMamba: A State Space Model for Efficient Skeleton Action Recognition of Neurological Disorders](https://mlsanity.com/paper/2411.19544/) (2024)
- [REST-HANDS: Rehabilitation with Egocentric Vision Using Smartglasses for Treatment of Hands after Surviving Stroke](https://mlsanity.com/paper/2409.20116/) (2024)
- [An Elastic Shape Variational Autoencoder for Skeleton Pose Trajectories](https://mlsanity.com/paper/2605.09231/) (2026)

## Abstract (arXiv)

This study investigates the application of general human motion encoders trained on large-scale human motion datasets for analyzing gait patterns in PD patients. Although these models have learned a wealth of human biomechanical knowledge, their effectiveness in analyzing pathological movements, such as parkinsonian gait, has yet to be fully validated. We propose a comparative framework and evaluate six pre-trained state-of-the-art human motion encoder models on their ability to predict the Movement Disorder Society - Unified Parkinson's Disease Rating Scale (MDS-UPDRS-III) gait scores from motion capture data. We compare these against a traditional gait feature-based predictive model in a recently released large public PD dataset, including PD patients on and off medication. The feature-based model currently shows higher weighted average accuracy, precision, recall, and F1-score. Motion encoder models with closely comparable results demonstrate promise for scalability and efficiency in clinical settings. This potential is underscored by the enhanced performance of the encoder model upon fine-tuning on PD training set. Four of the six human motion models examined provided prediction scores that were significantly different between on- and off-medication states. This finding reveals the sensitivity of motion encoder models to nuanced clinical changes. It also underscores the necessity for continued customization of these models to better capture disease-specific features, thereby reducing the reliance on labor-intensive feature engineering. Lastly, we establish a benchmark for the analysis of skeleton-based motion encoder models in clinical settings. To the best of our knowledge, this is the first study to provide a benchmark that enables state-of-the-art models to be tested and compete in a clinical context. Codes and benchmark leaderboard are available at code.