Detecting freezing of gait with a tri-axial accelerometer in Parkinson’s disease patients

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 th...

Descripción completa

Detalles Bibliográficos
Autores: Ahlrichs, Claas, Samà Monsonís, Albert|||0000-0003-3185-0799, Lawo, Michael, Cabestany Moncusí, Joan|||0000-0002-6926-3322, Rodríguez Martín, Daniel Manuel|||0000-0002-2598-6772, Pérez López, Carlos|||0000-0001-7400-4360, Quinlan, Leo R., ÓLaighin, Gearóid, Counihan, Timothy, Lewy, Hadas, Annicchiarico, Roberta, Bayés, Àngels, Rodríguez Molinero, Alejandro|||0000-0002-9678-2654
Tipo de recurso: artículo
Fecha de publicación:2015
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/86472
Acceso en línea:https://hdl.handle.net/2117/86472
https://dx.doi.org/10.1007/s11517-015-1395-3
Access Level:acceso abierto
Palabra clave:Parkinson's disease
Parkinson’s disease Freezing of Gait Machine learning Support vector machines
Parkinson, Malaltia de
Enginyeria biomèdica
Àrees temàtiques de la UPC::Enginyeria biomèdica
Descripción
Sumario: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 provides 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.

Similares en LA Referencia