Rest tremor quantification based on fuzzy inference systems and wearable sensors

Abstract

Background: Currently the most consistent, widely accepted and detailed instrument to rate Parkinson's disease (PD) is the Movement Disorder Society sponsored Unified Parkinson Disease Rating Scale (MDS-UPDRS). However, the motor examination is based upon subjective human interpretation trying to capture a snapshot of PD status. Wearable sensors and machine learning have been broadly used to analyze PD motor disorder, but still most ratings and examinations lay outside MDS-UPDRS standards. Moreover, logical connections between features and output ratings are not clear and complex to derive from the model, thus limiting the understanding of the structure in the data.

Methods: Fifty-seven PD patients underwent a full motor examination in accordance to the MDS-UPDRS on twelve different sessions, gathering 123 measurements. Overall, 446 different combinations of limb features correlated to rest tremors amplitude are extracted from gyroscopes, accelerometers, and magnetometers and feed into a fuzzy inference system to yield severity estimations.

Results: A method to perform rest tremor quantification fully adhered to the MDS-UPDRS based on wearable sensors and fuzzy inference system is proposed, which enables a reliable and repeatable assessment while still computing features suggested by clinicians in the scale. This quantification is straightforward and scalable allowing clinicians to improve inference by means of new linguistic statements. In addition, the method is immediately accessible to clinical environments and provides rest tremor amplitude data with respect to the timeline. A better resolution is also achieved in tremors rating by adding a continuous range.

Keywords: Continuous scale; Fuzzy inference; Rest tremor; Tremor quantification; Wearable sensors.