Among Parkinson’s disease (PD) motor symptoms, freezing of gait (FOG) may\ud be the most incapacitating. FOG episodes may result in falls and reduce patients’\ud quality of life. Accurate assessment of FOG would provide objective information\ud to neurologists about the patient’s condition and the symptom’s characteristics,\ud while it could enable non-pharmacologic support based on rhythmic\ud cues.\ud This paper is, to the best of our knowledge, the first study to propose a\ud deep learning method for detecting FOG episodes in PD patients. This model\ud is trained using a novel spectral data representation strategy which considers information from both the previous and current signal windows. Our approach\ud was evaluated using data collected by a waist-placed inertial measurement unit\ud from 21 PD patients who manifested FOG episodes. These data were also employed\ud to reproduce the state-of-the-art methodologies, which served to perform\ud a comparative study to our FOG monitoring system.\ud The results of this study demonstrate that our approach successfully outperforms\ud the state-of-the-art methods for automatic FOG detection. Precisely, the\ud deep learning model achieved 90% for the geometric mean between sensitivity\ud and specificity, whereas the state-of-the-art methods were unable to surpass the\ud 83% for the same metric.Peer ReviewedPostprint (published version

Bradykinesia is a cardinal symptom of Parkinson's disease (PD) and describes the slowness of movement revealed in patients. Current PD therapies are based on dopamine replacement, and given that bradykinesia is the symptom that best correlates with the dopaminergic deficiency, the knowledge of its fluctuations may be useful in the diagnosis, treatment and better understanding of the disease progression. This paper evaluates a machine learning method that analyses the signals provided by a triaxial accelerometer placed on the waist of PD patients in order to automatically assess bradykinetic gait unobtrusively. This method employs Support Vector Machines to determine those parts of the signals corresponding to gait. The frequency content of strides is then used to determine bradykinetic walking bouts and to estimate bradykinesia severity based on an epsilon-Support Vector Regression model. The method is validated in 12 PD patients, which leads to two main conclusions. Firstly, the frequency content of the strides allows for the dichotomic detection of bradykinesia with an accuracy higher than 90%. This process requires the use of a patient-dependant threshold that is estimated based on a leave-one-patient-out regression model. Secondly, bradykinesia severity measured through UPDRS scores is approximated by means of a regression model with errors below 10%. Although the method has to be further validated in more patients, results obtained suggest that the presented approach can be successfully used to rate bradykinesia in the daily life of PD patients unobtrusively.