Finger Tapping Clinimetric Score Prediction in Parkinson's Disease Using Low-Cost Accelerometers

The motor clinical hallmarks of Parkinson's disease (PD) are usually quantified by physicians using validated clinimetric scales such as the Unified Parkinson's Disease Rating Scale (MDS-UPDRS). However, clinical ratings are prone to subjectivity and inter-rater variability. The PD medical community is therefore looking for a simple, inexpensive, and objective rating method. As a first step towards this goal, a triaxial accelerometer-based system was used in a sample of 36 PD patients and 10 age-matched controls as they performed the MDS-UPDRS finger tapping (FT) task. First, raw signals were epoched to isolate the successive single FT movements. Next, eighteen FT task movement features were extracted, depicting MDS-UPDRS features and accelerometer specific features. An ordinal logistic regression model and a greedy backward algorithm were used to identify the most relevant features in the prediction of MDS-UPDRS FT scores, given by 3 specialists in movement disorders (SMDs). The Goodman-Kruskal Gamma index obtained (0.961), depicting the predictive performance of the model, is similar to those obtained between the individual scores given by the SMD (0.870 to 0.970). The automatic prediction of MDS-UPDRS scores using the proposed system may be valuable in clinical trials designed to evaluate and modify motor disability in PD patients. 1. Introduction The most important functional disturbance in patients with Parkinson's disease (PD), a chronic neurodegenerative condition, is a disorder of voluntary movement prominently characterized by slowness. This phenomenon is generally called bradykinesia [1]. Tremor and muscle rigidity are also part of the motor phenotypic spectrum [2]. Although it has not been possible to define a single underlying pathophysiologic mechanism that explains everything, bradykinesia and other motor symptoms seem to be related to a progressive loss of dopaminergic neurons in the substantia nigra [2, 3]. Since decades, the medical community has been developing clinical tools such as rating scales to quantify the severity of motor and other symptoms in PD. Despite the various attempts to use instruments and devices for quantification, clinical scales remain the preferred method because they are easy to administer and widely available. In the late eighties, the Unified Parkinson's Disease Rating Scale (UPDRS) was proposed as the primary international rating scale for PD clinical care and research and is still anchored in the daily practice of MDs. The motor examination part of the UPDRS requires the Specialists in Movement Disorders