Developing Digital Tools for Diagnosing and Monitoring Parkinsons Disease Using Eye and Gait Data

What this Trial Is About

Researchers are evaluating digital tools to improve diagnosis and monitoring of Parkinsons disease PD, a common neurodegenerative disorder affecting many older adults. The study focuses on collecting eye movement, pupil response, and walking pattern data from people with PD to develop machine learning models. These models aim to provide earlier and more precise diagnosis and track disease progression better than current methods that rely on subjective assessments. Participants will undergo several phases including laboratory testing and home monitoring. Eye and pupil data will be collected using standard clinical exams and a medical device called Neos. Gait data will be gathered through wearable sensors including an IMU sensor and the GaitQ senti device, which allows continuous remote monitoring. Some participants will also experience a two-week home intervention using a vibration-based cueing device to assess its potential effects on gait. During the study, participants will complete various walking and motor tests such as the Timed Up and Go test and Sit to Stand test across two lab visits spaced up to three weeks apart. Researchers will monitor safety and usability of the devices over up to six weeks. Data collected will be analyzed against clinical assessments to develop and compare machine learning models, contributing to better understanding and personalized care for people with Parkinsons disease.

Development of Digital Services for Parkinson's Disease