09/02/2026
September's paper of the month is: "Frequency-based deep learning to identify subtle postural instability in early, untreated Parkinson’s disease" by David Engel, Pablo Burgos, Patty Carlson-Kutha, Lauran Talman, Joe Quinn, Kaleb Vinehout, R. Stefan Greulich, Fay Horak, and Martina Mancini.
This study investigated whether subtle changes in postural control could be detected in people with early Parkinson’s disease, even before clear postural instability is apparent clinically. The researchers compared 40 newly diagnosed, untreated people with PD with 79 age-matched healthy controls using a 30-second quiet-standing test while an accelerometer attached to the lower back recorded their body movements. They analyzed the frequency characteristics of these postural sway signals using a convolutional neural network and found that the model could distinguish people with PD from healthy controls with very high accuracy, particularly when analyzing medio-lateral movements. The findings suggest that frequency-based analysis of postural sway may reveal subtle motor abnormalities in early PD and could potentially provide an objective tool for detecting and assessing these changes.
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 ...
