TY - JOUR
T1 - A multi-layer Gaussian process for motor symptom estimation in people with Parkinson's Disease
AU - Lang, Muriel
AU - Pfister, Franz M. J.
AU - Frohner, Jakob
AU - Abedinpour, Kian
AU - Pichler, Daniel
AU - Fietzek, Urban
AU - Um, Terry Taewoong
AU - Kulic, Dana
AU - Endo, Satoshi
AU - Hirche, Sandra
PY - 2019/11/1
Y1 - 2019/11/1
N2 - The assessment of Parkinson's disease (PD) poses a significant challenge, as it is influenced by various factors that lead to a complex and fluctuating symptom manifestation. Thus, a frequent and objective PD assessment is highly valuable for effective health management of people with Parkinson's disease (PwP). Here, we propose a method for monitoring PwP by stochastically modeling the relationships between wrist movements during unscripted daily activities and corresponding annotations about clinical displays of movement abnormalities. We approach the estimation of PD motor signs by independently modeling and hierarchically stacking Gaussian process models for three classes of commonly observed movement abnormalities in PwP including tremor, (non-tremulous) bradykinesia, and (non-tremulous) dyskinesia. We use clinically adopted severity measures as annotations for training the models, thus allowing our multi-layer Gaussian process prediction models to estimate not only their presence but also their severities. The experimental validation of our approach demonstrates strong agreement of the model predictions with these PD annotations. Our results show that the proposed method produces promising results in objective monitoring of movement abnormalities of PD in the presence of arbitrary and unknown voluntary motions, and makes an important step toward continuous monitoring of PD in the home environment.
AB - The assessment of Parkinson's disease (PD) poses a significant challenge, as it is influenced by various factors that lead to a complex and fluctuating symptom manifestation. Thus, a frequent and objective PD assessment is highly valuable for effective health management of people with Parkinson's disease (PwP). Here, we propose a method for monitoring PwP by stochastically modeling the relationships between wrist movements during unscripted daily activities and corresponding annotations about clinical displays of movement abnormalities. We approach the estimation of PD motor signs by independently modeling and hierarchically stacking Gaussian process models for three classes of commonly observed movement abnormalities in PwP including tremor, (non-tremulous) bradykinesia, and (non-tremulous) dyskinesia. We use clinically adopted severity measures as annotations for training the models, thus allowing our multi-layer Gaussian process prediction models to estimate not only their presence but also their severities. The experimental validation of our approach demonstrates strong agreement of the model predictions with these PD annotations. Our results show that the proposed method produces promising results in objective monitoring of movement abnormalities of PD in the presence of arbitrary and unknown voluntary motions, and makes an important step toward continuous monitoring of PD in the home environment.
KW - Ambient intelligence
KW - Gaussian processes
KW - medical information system
KW - wearable sensors
UR - http://www.scopus.com/inward/record.url?scp=85073655476&partnerID=8YFLogxK
U2 - 10.1109/TBME.2019.2900002
DO - 10.1109/TBME.2019.2900002
M3 - Article
C2 - 30794163
AN - SCOPUS:85073655476
VL - 66
SP - 3038
EP - 3049
JO - IEEE Transactions on Biomedical Engineering
JF - IEEE Transactions on Biomedical Engineering
SN - 0018-9294
IS - 11
ER -