Frequency-based deep learning to identify subtle postural instability in early, untreated Parkinson's disease.
Frequency-based deep learning to identify subtle postural instability in early, untreated Parkinson's disease.
Where did the research take place?
The study site has not been established. Author addresses may differ from where the research occurred.
Oregon, US · Author affiliation
Department of Neurology, Oregon Health & Science University, Portland, OR, USA. david.engel@uni-bonn.de.Location evidence
Bonn, DE · Author affiliation
Department of Neurology, Clinic for Parkinson's Disease, Sleep Disorders, and Movement Disorders, University of Bonn, University Hospital Bonn, Bonn, Germany. david.engel@uni-bonn.de.Location evidence
Newberg, US · Author affiliation
Doctor of Physical Therapy Program, George Fox University, Newberg, OR, USA.Location evidence
Spring, US · Author affiliation
Cold Spring Harbor Laboratory (CSHL), Cold Spring Harbor, NY, USA.Location evidence
Dresden, DE · Author affiliation
Chair of Business Information Systems, Esp. Intelligent Systems and Services, TUD Dresden University of Technology, Dresden, Germany.Location evidence
Oldenburg, DE · Author affiliation
Assistive Technologies, Jade University of Applied Sciences, Oldenburg, Germany.Location evidence
US · Author affiliation · country only
APDM Precision Motion, Clario, Portland, OR, USA.Location evidence
A plain-language reading has not been prepared for this paper yet.
Original abstract
Despite evidence of early neurodegeneration, postural instability is commonly associated with later stages of Parkinson's disease (PD), mainly due to a lack of sensitive measures. Here, we aim to provide a sensitive, easily obtainable objective measure of postural instability for earlier clinical detection. We assessed postural sway in 40 newly diagnosed, untreated individuals with PD and 79 age-matched healthy controls while they stood quietly for 30 seconds with their eyes open and feet together. Body sway was recorded with a single accelerometer placed at the lumbar spine. We trained a convolutional neural network (CNN) to distinguish between the groups based on the frequency information of their sway signals. Our models reached an average accuracy, sensitivity, and specificity of 98.9%, 97.7%, and 98.9%, respectively. This suggests that characteristic frequency features of postural sway reflect subtle postural impairments in early PD, with great potential to translate into clinical applications.