Attention Makers

CATEGORY: HEALTH & SAFETY

GyroRing - Wearable Ring for Parkinson's disease Diagnosis

MAKERS: Muhammad Asad COUNTRY: Pakistan

Parkinson's disease is the second most common movement disorder with no diagnostic test. We created a ring that analyses movement patterns and diagnoses using Machine Learning.

 

The Purpose

Tremor is involuntary shaking of body parts and around 281 million people around the world suffer from it. One such disorder is Parkinson?s disease which is hard to diagnose correctly because of lack of any biomarkers. Doctors use subjective tests for its diagnosis and usually misdiagnose it initially with other tremor related disorders. We are trying to solve this problem by using state of the art wearable sensors and machine learning algorithms. With treatment costs of Parkinson?s disease around $25 Billion in the US. GyroRing will reduce the time required to diagnose Parkinson?s disease to minutes.

The Technology

We acquire the tremor data from a wearable ring and then apply different signal processing and machine learning algorithms to compare the patterns with the tremor data of known patients already in our database. We compute different features and use these as inputs for our Machine learning algorithm. We were able to achieve the Sensitivity and specificity of more than 95% which is way more than the accuracy of current standard of 76%.

Additional Details

The goal of this work is to accurately distinguish between finger tremors of Parkinson?s disease and other movement disorders using a tri-axial gyroscope. Finger tremor is specifically studied here as compared to hand tremor since farther distance from radio-carpal joint results in better acquisition of tremor signal. We designed the hardware to acquire angular rate from tri-axial gyroscope and apply a series of techniques to extract different features in time and frequency domains. Both resting and postural tremor is studied for analysis.

Home Previous Next

Vote Share Comment