High accuracy discrimination of Parkinson's disease participants from healthy controls using smartphones

Siddharth Arora, Vinayak Venkataraman, Sean Donohue, Kevin M. Biglan, Earl R. Dorsey, Max A. Little

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The aim of this study is to accurately distinguish Parkinson's disease (PD) participants from healthy controls using self-administered tests of gait and postural sway. Using consumer-grade smartphones with in-built accelerometers, we objectively measure and quantify key movement severity symptoms of Parkinson's disease. Specifically, we record tri-axial accelerations, and extract a range of different features based on the time and frequency-domain properties of the acceleration time series. The features quantify key characteristics of the acceleration time series, and enhance the underlying differences in the gait and postural sway accelerations between PD participants and controls. Using a random forest classifier, we demonstrate an average sensitivity of 98.5% and average specificity of 97.5% in discriminating PD participants from controls.

Original languageEnglish
Title of host publication2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
PublisherIEEE
Pages3641-3644
Number of pages4
ISBN (Print)978-1-4799-2892-7
DOIs
Publication statusPublished - 2014
Event2014 IEEE International Conference on Acoustics, Speech, and Signal Processing - Florence, Italy
Duration: 4 May 20149 May 2014

Conference

Conference2014 IEEE International Conference on Acoustics, Speech, and Signal Processing
Abbreviated titleICASSP 2014
CountryItaly
CityFlorence
Period4/05/149/05/14

Fingerprint

Smartphones
Time series
Accelerometers
Classifiers

Bibliographical note

© 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Keywords

  • Gait
  • Parkinson's disease
  • Postural sway
  • Random forest
  • Smartphones
  • Tri-axial acceleration

Cite this

Arora, S., Venkataraman, V., Donohue, S., Biglan, K. M., Dorsey, E. R., & Little, M. A. (2014). High accuracy discrimination of Parkinson's disease participants from healthy controls using smartphones. In 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 3641-3644). IEEE. https://doi.org/10.1109/ICASSP.2014.6854280
Arora, Siddharth ; Venkataraman, Vinayak ; Donohue, Sean ; Biglan, Kevin M. ; Dorsey, Earl R. ; Little, Max A. / High accuracy discrimination of Parkinson's disease participants from healthy controls using smartphones. 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2014. pp. 3641-3644
@inproceedings{ee53f089e3cd4ef19d7d64f8adfe4b0d,
title = "High accuracy discrimination of Parkinson's disease participants from healthy controls using smartphones",
abstract = "The aim of this study is to accurately distinguish Parkinson's disease (PD) participants from healthy controls using self-administered tests of gait and postural sway. Using consumer-grade smartphones with in-built accelerometers, we objectively measure and quantify key movement severity symptoms of Parkinson's disease. Specifically, we record tri-axial accelerations, and extract a range of different features based on the time and frequency-domain properties of the acceleration time series. The features quantify key characteristics of the acceleration time series, and enhance the underlying differences in the gait and postural sway accelerations between PD participants and controls. Using a random forest classifier, we demonstrate an average sensitivity of 98.5{\%} and average specificity of 97.5{\%} in discriminating PD participants from controls.",
keywords = "Gait, Parkinson's disease, Postural sway, Random forest, Smartphones, Tri-axial acceleration",
author = "Siddharth Arora and Vinayak Venkataraman and Sean Donohue and Biglan, {Kevin M.} and Dorsey, {Earl R.} and Little, {Max A.}",
note = "{\circledC} 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.",
year = "2014",
doi = "10.1109/ICASSP.2014.6854280",
language = "English",
isbn = "978-1-4799-2892-7",
pages = "3641--3644",
booktitle = "2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)",
publisher = "IEEE",
address = "United States",

}

Arora, S, Venkataraman, V, Donohue, S, Biglan, KM, Dorsey, ER & Little, MA 2014, High accuracy discrimination of Parkinson's disease participants from healthy controls using smartphones. in 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp. 3641-3644, 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, Florence, Italy, 4/05/14. https://doi.org/10.1109/ICASSP.2014.6854280

High accuracy discrimination of Parkinson's disease participants from healthy controls using smartphones. / Arora, Siddharth; Venkataraman, Vinayak; Donohue, Sean; Biglan, Kevin M.; Dorsey, Earl R.; Little, Max A.

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2014. p. 3641-3644.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - High accuracy discrimination of Parkinson's disease participants from healthy controls using smartphones

AU - Arora, Siddharth

AU - Venkataraman, Vinayak

AU - Donohue, Sean

AU - Biglan, Kevin M.

AU - Dorsey, Earl R.

AU - Little, Max A.

N1 - © 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2014

Y1 - 2014

N2 - The aim of this study is to accurately distinguish Parkinson's disease (PD) participants from healthy controls using self-administered tests of gait and postural sway. Using consumer-grade smartphones with in-built accelerometers, we objectively measure and quantify key movement severity symptoms of Parkinson's disease. Specifically, we record tri-axial accelerations, and extract a range of different features based on the time and frequency-domain properties of the acceleration time series. The features quantify key characteristics of the acceleration time series, and enhance the underlying differences in the gait and postural sway accelerations between PD participants and controls. Using a random forest classifier, we demonstrate an average sensitivity of 98.5% and average specificity of 97.5% in discriminating PD participants from controls.

AB - The aim of this study is to accurately distinguish Parkinson's disease (PD) participants from healthy controls using self-administered tests of gait and postural sway. Using consumer-grade smartphones with in-built accelerometers, we objectively measure and quantify key movement severity symptoms of Parkinson's disease. Specifically, we record tri-axial accelerations, and extract a range of different features based on the time and frequency-domain properties of the acceleration time series. The features quantify key characteristics of the acceleration time series, and enhance the underlying differences in the gait and postural sway accelerations between PD participants and controls. Using a random forest classifier, we demonstrate an average sensitivity of 98.5% and average specificity of 97.5% in discriminating PD participants from controls.

KW - Gait

KW - Parkinson's disease

KW - Postural sway

KW - Random forest

KW - Smartphones

KW - Tri-axial acceleration

UR - http://www.scopus.com/inward/record.url?scp=84905247586&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2014.6854280

DO - 10.1109/ICASSP.2014.6854280

M3 - Conference contribution

SN - 978-1-4799-2892-7

SP - 3641

EP - 3644

BT - 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

PB - IEEE

ER -

Arora S, Venkataraman V, Donohue S, Biglan KM, Dorsey ER, Little MA. High accuracy discrimination of Parkinson's disease participants from healthy controls using smartphones. In 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE. 2014. p. 3641-3644 https://doi.org/10.1109/ICASSP.2014.6854280