Objective assessment of upper limb motor symptoms in Parkinson's Disease using body-worn sensors

Abstract

Background There is a need for an objective method of symptom assessment in Parkinson's disease (PD) to enable better treatment decisions and to aid evaluation of new treatments. Current assessment methods; patient-completed symptom diaries and clinical rating scales, have limitations. Accelerometers (sensors capable of capturing data on human movement) and analysis using artificial neural networks (ANNs) have shown potential as a method of motor symptom evaluation in PD. It is unknown whether symptom monitoring with body-worn sensors is acceptable to PD patients due to a lack of previous research. Methods 34 participants with PD wore bilateral wrist-worn accelerometers for 4 hours in a research facility (phase 1) and then for 7 days in their homes (phase 2) whilst also completing symptom diaries. An ANN designed to predict a patient’s motor status, was developed and trained based on accelerometer data during phase 2. ANN performance was evaluated (leave-one-out approach) against patient-completed symptom diaries during phase 2, and against clinician rating of disease state during phase 1 observations. Participants’ views regarding the sensors were obtained via a Likert-style questionnaire completed after each phase. Differences in responses between phases were assessed for using the Wilcoxon rank-sum test. Results ANN-derived values of the proportion of time in each disease state (phase 2), showed strong, significant correlations with values derived from patient-completed symptom diaries. ANN disease state recognition during phase 1 was sub-optimal. High concordance with sensors was seen. Prolonged wearing of the sensors did not adversely affect participants’ opinions on the wearability of the sensors, when compared to their responses following phase 1 Conclusions  Accelerometers and ANNs produced results comparable to those of symptom diaries.  Our findings suggest that long-term monitoring with wrist-worn sensors is acceptable to PD patients.