Skip to content
Back to outputs

A hybrid spatio-temporal model for detection and severity rating of Parkinson’s Disease from gait data

Research output: Contribution to journalArticlepeer-review

Standard

A hybrid spatio-temporal model for detection and severity rating of Parkinson’s Disease from gait data. / Zhao, Aite; Qi, Lin; Li, Jie; Dong, Junyu; Yu, Hui.

In: Neurocomputing, Vol. 315, 13.11.2018, p. 1-8.

Research output: Contribution to journalArticlepeer-review

Harvard

APA

Vancouver

Author

Zhao, Aite ; Qi, Lin ; Li, Jie ; Dong, Junyu ; Yu, Hui. / A hybrid spatio-temporal model for detection and severity rating of Parkinson’s Disease from gait data. In: Neurocomputing. 2018 ; Vol. 315. pp. 1-8.

Bibtex

@article{35843a08b71d45b094af0fa3585a6605,
title = "A hybrid spatio-temporal model for detection and severity rating of Parkinson{\textquoteright}s Disease from gait data",
abstract = "When diagnosing Parkinson{\textquoteright}s disease (PD), medical specialists normally assess several clinical manifestations of the PD patient and rate a severity level according to established criteria. This rating process is highly depended by doctors{\textquoteright} expertise, which is subjective and inefficient. In this paper, we propose a machine learning based method to automatically rate the PD severity from gait information, in particular, the sequential data of Vertical Ground Reaction Force (VGRF) recorded by foot sensors. We developed a two-channel model that combines Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) to learn the spatio-temporal patterns behind the gait data. The model was trained and tested on three public VGRF datasets. Our proposed method outperforms existing ones in terms of prediction accuracy of PD severity levels. We believe the quantitative evaluation provided by our method will benefit clinical diagnosis of Parkinson{\textquoteright}s disease.",
keywords = "Parkinson's disease, diagnosis, gait, temporal data, LSTM, CNN",
author = "Aite Zhao and Lin Qi and Jie Li and Junyu Dong and Hui Yu",
note = "12 month embargo.",
year = "2018",
month = nov,
day = "13",
doi = "10.1016/j.neucom.2018.03.032",
language = "English",
volume = "315",
pages = "1--8",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier",

}

RIS

TY - JOUR

T1 - A hybrid spatio-temporal model for detection and severity rating of Parkinson’s Disease from gait data

AU - Zhao, Aite

AU - Qi, Lin

AU - Li, Jie

AU - Dong, Junyu

AU - Yu, Hui

N1 - 12 month embargo.

PY - 2018/11/13

Y1 - 2018/11/13

N2 - When diagnosing Parkinson’s disease (PD), medical specialists normally assess several clinical manifestations of the PD patient and rate a severity level according to established criteria. This rating process is highly depended by doctors’ expertise, which is subjective and inefficient. In this paper, we propose a machine learning based method to automatically rate the PD severity from gait information, in particular, the sequential data of Vertical Ground Reaction Force (VGRF) recorded by foot sensors. We developed a two-channel model that combines Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) to learn the spatio-temporal patterns behind the gait data. The model was trained and tested on three public VGRF datasets. Our proposed method outperforms existing ones in terms of prediction accuracy of PD severity levels. We believe the quantitative evaluation provided by our method will benefit clinical diagnosis of Parkinson’s disease.

AB - When diagnosing Parkinson’s disease (PD), medical specialists normally assess several clinical manifestations of the PD patient and rate a severity level according to established criteria. This rating process is highly depended by doctors’ expertise, which is subjective and inefficient. In this paper, we propose a machine learning based method to automatically rate the PD severity from gait information, in particular, the sequential data of Vertical Ground Reaction Force (VGRF) recorded by foot sensors. We developed a two-channel model that combines Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) to learn the spatio-temporal patterns behind the gait data. The model was trained and tested on three public VGRF datasets. Our proposed method outperforms existing ones in terms of prediction accuracy of PD severity levels. We believe the quantitative evaluation provided by our method will benefit clinical diagnosis of Parkinson’s disease.

KW - Parkinson's disease

KW - diagnosis

KW - gait

KW - temporal data

KW - LSTM

KW - CNN

U2 - 10.1016/j.neucom.2018.03.032

DO - 10.1016/j.neucom.2018.03.032

M3 - Article

VL - 315

SP - 1

EP - 8

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

ER -

ID: 10177531