A Self-Managed System for Automated Assessment of UPDRS Upper Limb Tasks in Parkinson’s Disease

Abstract

A home-based, reliable, objective and automated assessment of motor performance of patients affected by Parkinson’s Disease (PD) is important in disease management, both to monitor therapy efficacy and to reduce costs and discomforts. In this context, we have developed a self-managed system for the automated assessment of the PD upper limb motor tasks as specified by the Unified Parkinson’s Disease Rating Scale (UPDRS). The system is built around a Human Computer Interface (HCI) based on an optical RGB-Depth device and a replicable software. The HCI accuracy and reliability of the hand tracking compares favorably against consumer hand tracking devices as verified by an optoelectronic system as reference. The interface allows gestural interactions with visual feedback, providing a system management suitable for motor impaired users. The system software characterizes hand movements by kinematic parameters of their trajectories. The correlation between selected parameters and clinical UPDRS scores of patient performance is used to assess new task instances by a machine learning approach based on supervised classifiers. The classifiers have been trained by an experimental campaign on cohorts of PD patients. Experimental results show that automated assessments of the system replicate clinical ones, demonstrating its effectiveness in home monitoring of PD.

An Integrated Multi-Sensor Approach for the Remote Monitoring of Parkinson’s Disease

“…A low-cost tracking system has been developed for the accurate acquisition of fine hand movements [29,30] (Figure 1a): it consists of an RGB-depth camera (Intel RealSense ® SR300 [26]), a computer (notebook or mini-PC), a monitor (for visual feedback of the hand movement) and easy-to-wear gloves with colored markers imprinted on specific parts of the hand.…”

“…The dedicated tracking algorithms, based on computer vision techniques, detect the colored markers in the scene and calculate the three-dimensional (3D) trajectories of each colored blob centroid, thus capturing the movements of hand and fingers (Figure 1b). The fusion of color and depth information performed by the tracking algorithms ensures greater robustness compared to the different commercial trackers based only on depth information, as shown by comparison with gold reference systems for motion analysis [29]. This approach also acts as a gesture-based HMI, making the interaction with the system friendly, self-manageable and natural [30].…”

“…The first component is an active vision system dedicated to the analysis of the motor tasks related to upper limbs; the second applies a body sensor network (BSN) approach with wireless wearable sensors for the analysis of the lower limb tasks. The technical details of both and the validation of their accuracy as UPDRS automatic scoring systems have been already presented in previous works [27,28,29,30] and will be briefly summarized in the Materials and Methods section.…”

The Existing of Supportive Technology Tools for Hand Motor-impaired User: A systematic Literature Review

“…From the reviews, most studies had been conducted in Europe which is 15 studies [3][4][5][8][9][10][11][12][13][14][15][16][17][18][19] followed by USA which is nine studies [2], [20][21][22][23][24][25][26][27], Korea [28,29], and South East Asia [30][31][32][33] had been handled 3 studies respectively, while China has 2 studies [34,35] and Turkey [36] and Brazil [37] and Japan [38] had one paper respectively. The papers had been published in the early 2000s until the present.…”

An Expert System for Quantification of Bradykinesia Based on Wearable Inertial Sensors

“…The introduced methodologies differ in terms of applied instrumentation, analysed movements, measurement protocols, the size and composition of patients’ groups, and implemented signal processing and learning techniques. Some studies implement RGB or infrared camera systems for measuring clinically important repetitive hand and leg movements [5,11,12]. Although such systems can provide high-precision measurements, they have some limitations.…”