Freezing of gait (FOG) is a common motor symptom of Parkinson's Disease (PD), which presents itself as an inability to initiate or continue gait. This paper presents a method to monitor FOG episodes based only on acceleration measurements obtained from a waist-worn device. Three approximations of this method are tested. Initially, FOG is directly detected by a support vector machine (SVM). Then, classifier's outputs are aggregated over time to determine a confidence value, which is used for the final classification of freezing (i.e. second and third approach). All variations are trained with signals of 15 patients and evaluated with signals from another 5 patients. Using a linear SVM kernel, the third approach outperforms results in the literature with 98.7% accuracy and a geometric mean of 96.1%. Moreover, it is investigated whether frequency features are enough to reliably detect FOG. Results show that these features allow the method to detect FOG with accuracies above 90% and that frequency features enable a reliable monitoring of FOG by using simply a waist sensor.

This paper reviews related work and state-of-the-art publications for recognizing motor symptoms of Parkinson's Disease (PD). It presents research efforts that were undertaken to inform on how well traditional machine learning algorithms can handle this task. In particular, four PD related motor symptoms are highlighted (i.e. tremor, bradykinesia, freezing of gait and dyskinesia) and their details summarized. Thus the primary objective of this research is to provide a literary foundation for development and improvement of algorithms for detecting PD related motor symptoms.

This paper presents a novel health monitoring system for Parkinson's disease (pd) patients called help (Home-based Empowered Living for Parkinson's disease patients). The help system has been specifically designed and implemented as a health monitoring system in order to optimize treatment and improve quality of life of people with Parkinson's. This is a challenging goal due to the difficulty in establishing a closed-loop system that is able to detect the outcomes of treatment and react accordingly. In a similar way to diabetes treatment where the plasma glucose level can be measured and can be used to regulate drug doses, the help system's approach aims to estimate pd symptoms and to adjust the dose of medication in order to reduce symptoms. The proposed health monitoring system is composed of several components: a body sensor & actuator network managed by a smartphone, a remote monitoring platform for doctors and clinical professionals as well as a telecommunication and service infrastructure. The real advantage derives from having constant medical control without dramatically modifying daily life. The help system is going to be evaluated in several cities during the first part of 2012 under daily living conditions with pd patients.Keywords: Parkinson's Disease, Body Sensor and Actuator Network, Health Monitoring System, Ambient Assisted Living ResumenEn este trabajo se presenta un nuevo sistema de vigilancia de la salud para pacientes con la enfermedad de Parkinson (ep), pacientes llamados help (Fortaleciendo la vida en el hogar de pacientes con la enfermedad Parkinson). El sistema de ayuda ha sido específicamente diseñado e implementado como un sistema de vigilancia de la salud con el fin de optimizar el tratamiento y mejorar la calidad de vida de las personas con Parkinson. Este es un objetivo difícil debido a la dificultad del establecimiento de un sistema de circuito cerrado que es capaz de detectar los resultados del tratamiento y reaccionar en consecuencia. Es una manera similar al tratamiento de la diabetes donde el nivel de glucosa en plasma se puede medir y se puede utilizar para regular las dosis de medicamentos; el enfoque del sistema

This paper presents two approaches on detecting tremor in patients with Parkinson's Disease by means of a wrist-worn accelerometer. Both approaches are evaluated in terms of specificity and sensitivity as well as their applicability for a real-time implementation. One approach is solely based on the frequency distribution of a windowed time series, while the second approach utilizes commonly employed features found in the literature (e.g. FFT, entropy, peak frequency, correlation). The two algorithms detect tremor at rest in windowed time series. The effects of varying window lengths and detection thresholds are studied. The results indicate that an SVM with a linear kernel, in combination with the frequency distribution, may already be enough to accurately and reliably detect tremor in windowed time series. The approach, after being trained with a first dataset of signals obtained from 12 patients, achieved a sensitivity of 88.4% and specificity of 89.4% in a second dataset from 64 PD patients.

No abstract