Forecasting gait freezing event in Parkinson's patients utilizing machine learning approach from accelerometer signals

Abstract

Neurological illnesses are one of the most common medical conditions affecting human races and societies worldwide. Parkinson's disease is a neurological ailment caused by absence of dopamine in the human brain and has an impact on the afflicted person's daily routine. Gait freezing event is the most concerning symptom of Parkinson's disease, and it affects around half of people with severe Parkinson's. Machine learning methods are used in this study to detect and forecast gait freezing events. Two hundred thirty seven gait freezing instances from eight patients were collected from tri-axial accelerometer data set and used to train four machine learning classification models. After comparing different performance measures of the four classification models it was found that the Random forest classification model was the most suitable one for predicting gait freezing events in Parkinson disease as it had the best accuracy, sensitivity ,selectivity and least error among the four models. Keywords: Parkinson’s disease , Gait freezing , machine learning , tri-axial accelerometer , Random forest classification model.