Automatic assessment of Parkinson's Disease from natural hands movements using 3D depth sensor

Abstract

Parkinson's Disease (PD) is a degenerative disease of the central nervous system with a profound effect on the motor system. Symptoms include slowness of movement, rigidity of motion and in some patients, tremor. The severity of the disease is quantified using the Unified Parkinson Disease Rating Scale (UPDRS) which is a subjective scale performed and scored by physicians. In this work, we present an automated, objective quantitative analysis of four UPDRS motor examinations of Hand Movement and Finger Taps.For this purpose, a non-invasive system for recording and analysis of fine motor skills of hands was developed. The system is based on a simple low-cost depth acquisition sensor, similar to the second generation of Microsoft's Kinect sensor, and novel recursive self-correcting hand tracking algorithm. The system allows patients to perform test tasks in a natural and unhindered manner.The evaluation of the system was carried out on PD patients and controls. Machine Learning based classification was performed on the acquired data, followed by a decision making scheme.

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

“…However, only the maximum accuracy for each classifier was included, ranging from 71.4% to 85.7%. Finally, the HvsP binary classification was also addressed in [ 18 ], and the results were reported for each UPDRS task; in this case, the classification accuracies ranged from 87.5% for PS to 100% for FT, but on a very limited number of HC and PD subjects. In conclusion, our results concerning the HvsP binary classification accuracy are overall better than the results of the previous studies mentioned [ 13 , 16 , 18 ] (see Table 6 ).…”

“…Solutions for upper limb task assessment based on hand-worn wireless sensors (i.e., accelerometers, gyroscopes, resistive bands) [ 8 , 9 , 10 , 11 , 12 ] do not suffer from occlusion problems, but are more invasive for motor-impaired people with respect to optical approaches and, more importantly, with an invasiveness that can affect motor performance. Some optical-based approaches for hand tracking in the automated assessment of upper limb tasks of UPDRS have been recently proposed based on video processing [ 13 ], RGB-Depth cameras combined with colored markers [ 14 ], video with the aid of reflective markers [ 15 ], and bare hand tracking by consumer-grade depth-sensing devices [ 16 , 17 , 18 ].…”

Caracterização Da Severidade Do Tremor De Punho Em Indivíduos Com a Doença De Parkinson Por Meio De Sensores Inerciais

“…O tremor pode ser uma função motora humana normal (fisiológico) presente em todos seres humanos ou anormal (patológico) em consequência de distúrbios da saúde ou envelhecimento [2]. Estudos e estatísticas governamentais mostram que a população senil é a mais afetada pelo tremor [3]. Essa manifestação pode causar incapacidade funcional considerável e leva o indivíduo ao afastamento social pela interferência nas atividades de vida diária (AVDs) [3].…”

“…Estudos e estatísticas governamentais mostram que a população senil é a mais afetada pelo tremor [3]. Essa manifestação pode causar incapacidade funcional considerável e leva o indivíduo ao afastamento social pela interferência nas atividades de vida diária (AVDs) [3].…”

“…Estudos e estatísticas governamentais mostram que a população senil é a mais afetada pelo tremor [3]. Essa manifestação pode causar incapacidade funcional considerável e leva o indivíduo ao afastamento social pela interferência nas atividades de vida diária (AVDs) [3].O presente estudo avaliou o tremor advindo da Doença de Parkinson (DP). A DP pode causar tremor patológico, sendo uma desordem crônica, progressiva e neurodegenerativa do sistema nervoso central (SNC), com implicações profundas para o indivíduo, como déficits em funções motoras, diminuição da amplitude de movimento (ADM) e força muscular [5].…”