What question did this study set out to answer?

The study aims to evaluate Parkinson’s disease severity using real-world gait data via federated learning while addressing privacy concerns.

March 12, 2026Open Access

Privacy and personalisation: predicting Parkinson’s disease severity from real-world gait with federated learning

Key Points

The study aims to evaluate Parkinson’s disease severity using real-world gait data via federated learning while addressing privacy concerns.
Simulated a federated learning system for gait analysis in Parkinson's disease.
Collected retrospective data from 89 participants using accelerometers over 6 years.
Analyzed the Movement Disorder Society Unified Parkinson’s Disease Rating Scale (MDS-UPDRS)-Part III scores as an outcome measure.
Compared the accuracy of federated learning models to traditional machine learning approaches.
The local models from federated learning demonstrated a mean absolute error (MAE) of 4.83, indicating high accuracy.
The global federated learning model achieved a MAE of 9.26 after optimizing training data without sharing any participant data.
Traditional machine learning showed a MAE of 10.43, highlighting the efficacy of the federated approach in preserving privacy.

Abstract

Introduction Cloud-based artificial intelligence (AI) combined with smart-health technology presents a powerful tool to passively monitor disease severity. However, current methods raise privacy concerns as they require transmitting patient data to the cloud. A potential solution is Federated Learning (FL), which only shares the weights of locally trained neural networks (NNs) instead of user data. Here, we simulated an FL system to demonstrate its application for evaluating Parkinson’s disease (PD) severity in a smart-home scenario. Methods Retrospective data including 89 people with PD wore an accelerometer on the lower-back at home for 7 days at 18-month intervals over 6 years. Patient characteristics (age, sex, and body mass index) and clinical measures of PD were additionally collected, including the Movement Disorder Society Unified Parkinson’s Disease Rating Scale (MDS-UPDRS)-Part III. Real-world daily gait measures along with these patient characteristics were used to predict the MDS-UPDRS-III score. For FL, a local model was trained for each participant, and a global model (an aggregation of these local models) was tested on unseen participants. Results The performance of a simulated FL system was compared with that of a traditional Machine Learning (ML) approach in which patient data were shared. The traditional ML approach had a mean absolute error (MAE) of 10.43. The global FL model had a similar MAE of 10.22 but was underfitted, and the mean MAE of the local, personalised models was 4.83. Shapley Additive exPlanations (SHAP) analysis showed that while the participants’ age and sex were very important in traditional ML, this was not the case for the local FL models, leading to a decrease in global model performance. Here, we show that reserving a small number of participants from the system and including them in training data for all local models restored the importance of these features and improved global FL performance (MAE = 9.26) but reduced local performance (MAE = 6.83). Conclusion This exploratory study shows that our proposed approach enables FL to achieve similar accuracy to traditional Machine Learning without sharing any patient data but with costs to the local performance, leading towards a smart-home system that prioritises personalisation and patient privacy.

Bookmark

View Full Paper

Bookmark

View Full Paper

Privacy and personalisation: predicting Parkinson’s disease severity from real-world gait with federated learning

Key Points

Abstract

Cite This Study