Convolutional neural network reveals frequency content of medio-lateral COM body sway to be highly predictive of Parkinson’s disease

Postural instability as a symptom of progressing Parkinson’s disease (PD) greatly reduces quality of life. Hence, early detection of postural impairments is crucial to facilitate interventions. Our aim was to use a convolutional neural network (CNN) to differentiate people with early to mid-stage PD from healthy age-matched individuals based on spectrogram images obtained from their body movement. We hypothesized the time-frequency content of body sway to be predictive of PD, even when impairments are not yet manifested in day-to-day postural control. We tracked their center of pressure (COP) using a Wii Balance Board and their full-body motion using a Microsoft Kinect, out of which we calculated the trajectory of their center of mass (COM). We used 30 s-snippets of motion data from which we acquired wavelet-based time-frequency spectrograms that were fed into a custom-built CNN as labeled images. We used binary classification to have the network differentiate between individuals with PD and controls (n=15, respectively). Classification performance was best when the medio-lateral motion of the COM was considered. Here, our network reached an average predictive accuracy of 98.45 % with a receiver operating characteristic area under the curve of 1.0. Moreover, an explainable AI approach revealed high frequencies in the postural sway data to be most distinct between both groups. Our findings suggest a CNN classifier based on cost-effective and conveniently obtainable posturographic data to be a promising approach to detect postural impairments in early to mid-stage PD and to gain novel insight into the subtle characteristics of impairments at this stage of the disease.