Quantification assessment of bradykinesia in Parkinson's disease based on a wearable device

Abstract

Bradykinesia is one of the primary characteristic symptoms of Parkinson's disease (PD). Ten-second whole-hand-grasps action was chosen to assess bradykinesia severity in this study. A quantification assessment system based on a self-developed wearable device was proposed to assess the severity of the parkinsonian bradykinesia. The proposed assessment method used an attitude-estimation algorithm to extract the parkinsonian bradykinesia parameters. A regression model was adopted to fit the characteristic parameters with the clinical UPDRS ratings judged by neurologists. Clinical experiment with 15 PD patients and 5 age-matched healthy controls demonstrated that the predicted bradykinesia scores by proposed model correlated well with the judgments of neurologists (r=0.99). The proposed quantification model demonstrated the greater goodness-of-fit compared with the related works.

A Heterogeneous Sensing Suite for Multisymptom Quantification of Parkinson’s Disease

“…The results also show promise to adapt to improved (e.g., higher resolution, multi-dimensional) rating scales proposed for more precise disease assessment. Past studies have targeted only one or two main PD symptoms [39], [40]. This is the first investigation introducing a sensor system with the capacity to measure all three cardinal symptoms on a significantly sized PD cohort.…”

“…This is then used as a basis for correlation to the UPDRS scores [35], [36]. The second approach is to extract sensor features and implement a regression/ classification model to minimise the prediction errors to the UPDRS scores [37]- [40]. Since there exists no single model that has been explicitly defined to correlate UPDRS scores across all motor symptoms, machine learning algorithms are typically used as tools of analysis [41], [42].…”

SnapKi—An Inertial Easy-to-Adapt Wearable Textile Device for Movement Quantification of Neurological Patients

“…The non-linearity, the ceiling and floor effects and the inter-observation variability of clinical rating scales makes them highly subjective and with a low level of reliability [ 8 ]. For this reason, several research centers and companies have been recently working in body motion tracking with wearable devices of patients suffering from Parkinson’s Disease (PD) [ 9 , 10 , 11 , 12 , 13 , 14 , 15 ], Epilepsy [ 11 , 15 , 16 ], Stroke [ 11 , 17 ], Multiple Sclerosis [ 15 , 18 ], among others. However, these body motion tracking systems oriented-development for a specific disease or symptom(s) reveals limitation in their user, such as the ones discussed in the two next sub-sections.…”

“…The work presented in this paper focused on the development of a versatile textile embedded wearable device which provides inertial and analog raw data that can be used for the quantification of neurological motor symptoms, such as rigidity, tremor, bradykinesia and gait analysis. As example, rigidity quantification is achieved in Reference [ 19 ] by collecting angular velocity data from the wrist, tremor and bradykinesia are quantified in References [ 9 ] and [ 14 ], respectively, through the acquisition of accelerometer and gyroscope data from the finger. Gait analysis is performed by obtaining and processing accelerometer, gyroscope and analog data from the ankle [ 20 ].…”

“…Micro electromechanical systems inertial measurement units (MEMS IMUs), which are miniaturized components comprising a 3-axis accelerometer, gyroscope and often magnetometer, are the most implemented sensors for motion tracking [ 7 , 9 , 10 , 11 , 12 , 13 , 14 , 15 , 16 , 17 , 18 , 20 ]. They are preferred amongst developers for their small size, light weight and high precision.…”