TY - JOUR
T1 - High-resolution motor state detection in Parkinson's disease using convolutional neural networks
AU - Pfister, Franz M.J.
AU - Um, Terry Taewoong
AU - Pichler, Daniel C.
AU - Goschenhofer, Jann
AU - Abedinpour, Kian
AU - Lang, Muriel
AU - Endo, Satoshi
AU - Ceballos-Baumann, Andres O.
AU - Hirche, Sandra
AU - Bischl, Bernd
AU - Kulić, Dana
AU - Fietzek, Urban M.
PY - 2020/4/3
Y1 - 2020/4/3
N2 - Patients with advanced Parkinson's disease regularly experience unstable motor states. Objective and reliable monitoring of these fluctuations is an unmet need. We used deep learning to classify motion data from a single wrist-worn IMU sensor recording in unscripted environments. For validation purposes, patients were accompanied by a movement disorder expert, and their motor state was passively evaluated every minute. We acquired a dataset of 8,661 minutes of IMU data from 30 patients, with annotations about the motor state (OFF,ON, DYSKINETIC) based on MDS-UPDRS global bradykinesia item and the AIMS upper limb dyskinesia item. Using a 1-minute window size as an input for a convolutional neural network trained on data from a subset of patients, we achieved a three-class balanced accuracy of 0.654 on data from previously unseen subjects. This corresponds to detecting the OFF, ON, or DYSKINETIC motor state at a sensitivity/specificity of 0.64/0.89, 0.67/0.67 and 0.64/0.89, respectively. On average, the model outputs were highly correlated with the annotation on a per subject scale (r = 0.83/0.84; p < 0.0001), and sustained so for the highly resolved time windows of 1 minute (r = 0.64/0.70; p < 0.0001). Thus, we demonstrate the feasibility of long-term motor-state detection in a free-living setting with deep learning using motion data from a single IMU.
AB - Patients with advanced Parkinson's disease regularly experience unstable motor states. Objective and reliable monitoring of these fluctuations is an unmet need. We used deep learning to classify motion data from a single wrist-worn IMU sensor recording in unscripted environments. For validation purposes, patients were accompanied by a movement disorder expert, and their motor state was passively evaluated every minute. We acquired a dataset of 8,661 minutes of IMU data from 30 patients, with annotations about the motor state (OFF,ON, DYSKINETIC) based on MDS-UPDRS global bradykinesia item and the AIMS upper limb dyskinesia item. Using a 1-minute window size as an input for a convolutional neural network trained on data from a subset of patients, we achieved a three-class balanced accuracy of 0.654 on data from previously unseen subjects. This corresponds to detecting the OFF, ON, or DYSKINETIC motor state at a sensitivity/specificity of 0.64/0.89, 0.67/0.67 and 0.64/0.89, respectively. On average, the model outputs were highly correlated with the annotation on a per subject scale (r = 0.83/0.84; p < 0.0001), and sustained so for the highly resolved time windows of 1 minute (r = 0.64/0.70; p < 0.0001). Thus, we demonstrate the feasibility of long-term motor-state detection in a free-living setting with deep learning using motion data from a single IMU.
UR - https://www.scopus.com/pages/publications/85083041211
U2 - 10.1038/s41598-020-61789-3
DO - 10.1038/s41598-020-61789-3
M3 - Article
C2 - 32246097
SN - 2045-2322
VL - 10
JO - Scientific Reports
JF - Scientific Reports
IS - 1
M1 - 5860
ER -