TY - JOUR
T1 - Deep learning for freezing of gait detection in Parkinson's disease patients in their homes using a waist-worn inertial measurement unit
AU - Camps, Julià
AU - Samà, Albert
AU - Martín, Mario
AU - Rodríguez-Martín, Daniel
AU - Pérez-López, Carlos
AU - Moreno Arostegui, Joan M.
AU - Cabestany, Joan
AU - Català, Andreu
AU - Alcaine, Sheila
AU - Mestre, Berta
AU - Prats, Anna
AU - Crespo-Maraver, Maria C.
AU - Counihan, Timothy J.
AU - Browne, Patrick
AU - Quinlan, Leo R.
AU - Laighin, Gearóid
AU - Sweeney, Dean
AU - Lewy, Hadas
AU - Vainstein, Gabriel
AU - Costa, Alberto
AU - Annicchiarico, Roberta
AU - Bayés, Àngels
AU - Rodríguez-Molinero, Alejandro
PY - 2017/10/16
Y1 - 2017/10/16
N2 - Among Parkinson's disease (PD) motor symptoms, freezing of gait (FOG) may be the most incapacitating. FOG episodes may result in falls and reduce patients’ quality of life. Accurate assessment of FOG would provide objective information to neurologists about the patient's condition and the symptom's characteristics, while it could enable non-pharmacologic support based on rhythmic cues. This paper is, to the best of our knowledge, the first study to propose a deep learning method for detecting FOG episodes in PD patients. This model is trained using a novel spectral data representation strategy which considers information from both the previous and current signal windows. Our approach was evaluated using data collected by a waist-placed inertial measurement unit from 21 PD patients who manifested FOG episodes. These data were also employed to reproduce the state-of-the-art methodologies, which served to perform a comparative study to our FOG monitoring system. The results of this study demonstrate that our approach successfully outperforms the state-of-the-art methods for automatic FOG detection. Precisely, the deep learning model achieved 90% for the geometric mean between sensitivity and specificity, whereas the state-of-the-art methods were unable to surpass the 83% for the same metric.
AB - Among Parkinson's disease (PD) motor symptoms, freezing of gait (FOG) may be the most incapacitating. FOG episodes may result in falls and reduce patients’ quality of life. Accurate assessment of FOG would provide objective information to neurologists about the patient's condition and the symptom's characteristics, while it could enable non-pharmacologic support based on rhythmic cues. This paper is, to the best of our knowledge, the first study to propose a deep learning method for detecting FOG episodes in PD patients. This model is trained using a novel spectral data representation strategy which considers information from both the previous and current signal windows. Our approach was evaluated using data collected by a waist-placed inertial measurement unit from 21 PD patients who manifested FOG episodes. These data were also employed to reproduce the state-of-the-art methodologies, which served to perform a comparative study to our FOG monitoring system. The results of this study demonstrate that our approach successfully outperforms the state-of-the-art methods for automatic FOG detection. Precisely, the deep learning model achieved 90% for the geometric mean between sensitivity and specificity, whereas the state-of-the-art methods were unable to surpass the 83% for the same metric.
KW - Deep learning
KW - Freezing of gait
KW - Parkinson's disease
KW - Signal processing
KW - Wearable device
UR - http://www.scopus.com/inward/record.url?scp=85033499782&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85033499782&partnerID=8YFLogxK
U2 - 10.1016/j.knosys.2017.10.017
DO - 10.1016/j.knosys.2017.10.017
M3 - Article
AN - SCOPUS:85033499782
VL - 139
SP - 119
EP - 131
JO - Knowledge-Based Systems
JF - Knowledge-Based Systems
SN - 0950-7051
ER -