Peer-Reviewed Journal Details
Mandatory Fields
Claas Ahlrichs · Albert Samŕ · Michael Lawo · Joan Cabestany · Daniel Rodríguez-Martín · Carlos Pérez-López · Dean Sweeney · Leo R. Quinlan · Gearňid Ň Laighin · Timothy Counihan · Patrick Browne · Lewy Hadas · Gabriel Vainstein · Alberto Costa · Roberta Annicchiarico · Sheila Alcaine · Berta Mestre · Paola Quispe · Ŕngels Bayes · Alejandro Rodríguez-Molinero
Medical & Biological Engineering & Computing
Detecting freezing of gait with a tri-axial accelerometer in Parkinson’s disease patients
Optional Fields
Freezing of Gait; Machine learning; Parkinson’s disease; Support vector machines
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.
Grant Details
Publication Themes
Biomedical Science and Engineering