Early detection of Parkinson’s disease based on IMU and machine learning

Zhixu Zhao; Hairong Yu; Feng Wang; Huifen Zheng

doi:10.1117/12.2674576

23 May 2023 Early detection of Parkinson’s disease based on IMU and machine learning

Zhixu Zhao, Hairong Yu, Feng Wang, Huifen Zheng

Proceedings Volume 12604, International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2022); 126044D (2023) https://doi.org/10.1117/12.2674576
Event: 2nd International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2022), 2022, Guangzhou, China

Abstract

Parkinson’s disease (PD) is the second most neurodegenerative disease, which results in gradual loss of movement. Early diagnosis helps to control the disease in advance and prevent the disease from getting worse. The diagnosis of Parkinson’s disease in hospitals is cumbersome and expensive. IMU which is widely used in gait analysis is much cheaper and suitable for early detection. But pure gait analysis has limitations in detecting PD. In this paper, we selected a representative 10- meter folding task and a stationary standing task reflecting the gait domain, balance domain, and tremor domain from a scale commonly used in clinical Parkinson's examinations, and collected a total of 127 data from early PD patients and healthy individuals using IMU sensors. Fifteen valid features were selected using MRMR and a support vector machine was used to discriminate between early-stage patients and healthy individuals. Due to the introduction of balance and tremor features, the accuracy is improved from 88% to 96%, and reduced likelihood of healthy individuals being misclassified as PD patients.

Citation Download Citation

Zhixu Zhao, Hairong Yu, Feng Wang, and Huifen Zheng "Early detection of Parkinson’s disease based on IMU and machine learning", Proc. SPIE 12604, International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2022), 126044D (23 May 2023); https://doi.org/10.1117/12.2674576

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available