A preliminary study of the causality of Freezing of Gait for Parkinson\'s disease patients: Bayesian Belief Network approach
Parkinson Disease (PD) patients suffer from a disabling phenomenon called Freezing of Gait (FoG), which can be described as if their feet were ‘frozen or stuck, but that the top half of their body was still able to move. In this paper, we make a graphical probabilistic modeling study, \Bayesian Belief Network (BBN) approach\ of a previously collected dataset that represents the measurements of acceleration sensors placed on the ankle, knee and hip of PD patients during their walk. In order to know if this is a traditional BBN model or a causal one, we built a FoG Model and tested its causality behavior, first by forming an Epidemiological Approach, and then, by inferring causal relations based on Additive Noise Models (ANM). Consequently, we built a Bayesian Naive Classifier Model related to FoG. The Bayesian belief Network classifier has the ability to identify the onset of freezing of PD patients, during walking using the extracted features. Promising results appeared when testing the BNC classifier models.
Keywords: Parkinson Disease, Freezing of Gait, Bayesian Network, Causality, Data Mining, Epidemiology, Classification.
Download Full-Text
ABOUT THE AUTHORS
Ali Saad
Biomedical Department, Faculty of Engineering, Islamic University of Lebanon Beirut-Lebanon Laboratoire GREAH -Groupe de Recherche en Electrotechnique et Automatique du Havre, Université du Havre Le Havre-France
Iyad Zaarour
Laboratoire d\'Informatique, de traitement de l\'Information et des Systèmes (LITIS- EA 4108) -Université de Rouen Rouen-France Faculty of business and economical sciences, Doctoral school of Science and technology, Lebanese University Beirut-Lebanon
Abbas Zeinedine
Faculty of business and economical sciences, Doctoral school of Science and technology, Lebanese University Beirut-Lebanon
Mohammad Ayache
Biomedical Department, Faculty of Engineering, Islamic University of Lebanon Beirut-Lebanon
François Guerin
Laboratoire GREAH -Groupe de Recherche en Electrotechnique et Automatique du Havre, Université du Havre Le Havre-France
Dimitri Lefebvre
Laboratoire GREAH -Groupe de Recherche en Electrotechnique et Automatique du Havre, Université du Havre Le Havre-France
Ali Saad
Biomedical Department, Faculty of Engineering, Islamic University of Lebanon Beirut-Lebanon Laboratoire GREAH -Groupe de Recherche en Electrotechnique et Automatique du Havre, Université du Havre Le Havre-France
Iyad Zaarour
Laboratoire d\'Informatique, de traitement de l\'Information et des Systèmes (LITIS- EA 4108) -Université de Rouen Rouen-France Faculty of business and economical sciences, Doctoral school of Science and technology, Lebanese University Beirut-Lebanon
Abbas Zeinedine
Faculty of business and economical sciences, Doctoral school of Science and technology, Lebanese University Beirut-Lebanon
Mohammad Ayache
Biomedical Department, Faculty of Engineering, Islamic University of Lebanon Beirut-Lebanon
François Guerin
Laboratoire GREAH -Groupe de Recherche en Electrotechnique et Automatique du Havre, Université du Havre Le Havre-France
Dimitri Lefebvre
Laboratoire GREAH -Groupe de Recherche en Electrotechnique et Automatique du Havre, Université du Havre Le Havre-France
