Parkinson's Disease Motor Assessment Dataset: In-Clinic and At-Home IMU Recordings

Read full text Summarise with VIRAT
Authors: Wireless Sensor Networks Group - Tyndall National Institute
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This dataset contains wearable IMU recordings from 24 Parkinson’s disease patients during in-clinic motor tasks and at-home monitoring. In-clinic data were collected using XSens MTw Awinda IMUs at 100 Hz on the most affected wrist and ankle during a battery of 12 scripted tasks, with simultaneous video recordings rated by a clinician for tremor, bradykinesia, and dyskinesia. At-home data were collected using off-the-shelf IMUs (ActiGraph GT3X+, 100 Hz) worn for 24 hours, alongside patient-reported motor diaries. A prototype WESAA wearable system (40 Hz) was also used on 6 participants for continuous home monitoring. Purpose:The dataset was collected to develop and validate models for detecting tremor, bradykinesia, and dyskinesia in both scripted and unsupervised settings. Study Details:- Location: Tyndall National Institute, Cork, Ireland- Cohort: 24 PD participants (16 males, 8 females), average age 70.7 ± 8.5 years- Data: Inertial Measurement Unit (IMU), accelerometer and gyroscope, 40 Hz and 100 Hz This study received approval by the Clinical Research Ethics Committee (CREC) of the Cork Teaching Hospitals at the University College Cork (Reference Number: ECM 4 (r) 11/02/2020 & ECM 3 (q) 09/08/2022). Access:This is a metadata-only record. Data are not publicly available. The full dataset is stored on a private SharePoint drive at the Tyndall National Institute for 10 years (until 13 February 2030) from date of ethics application (13 February 2020). Access to the data is subject to approval by the relevant Research Ethics Committee and Data Sharing Agreement. Please note the underlying data for this specific record cannot be shared, as it originates from an industry-funded project with associated restrictions on data distribution. However, in line with open science practices, we have made the metadata publicly available to support transparency and facilitate broader research engagement.Contact: colum.crowe@tyndall.ie, salvatore.tedesco@tyndall.ie

Fields of Study & Subjects

Context-Aware Activity Recognition Systems Balance Gait and Falls Prevention Parkinson's Disease Mechanisms and Treatments

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
19 March 2026
Language
EN
Document type
Dataset