Parkinson's disease Assessment using Fuzzy Expert System and Nonlinear Dynamics

Abstract

This paper proposes a new screening system for quantitative evaluation and analysis, designed for the early stage detection of Parkinson disease. This has been carried out in the view of improving the diagnosis currently established upon a basis of subjective scores. Parkinson?s disease (PD) appears as a result of dopamine loss, a chemical mediator that is responsible for the body?s ability to control movements. The symptoms reflect the loss of nerve cells, due to an unknown. The input parameters of the system are represented by amplitude, frequency, the spectral characteristic and trembling localization. The main symptoms include trembling of hand, arms, movement difficulties, postural instability, disturbance of coordination and equilibrium, sleep disturbance, difficulties in speaking, reducing of voice volume. The medical knowledge in PD field is characterized by imprecision, uncertainty and vagueness. The proposed system (fuzzy expert systems) is non-invasive and, easy to use by both physicians and patients at home

Deep brain stimulation efficiency and Parkinson's disease stage prediction using Markov models

“…Positive Lyapunov exponent is the main indicator of chaotic dynamics. Using the program developed in C language for tremor signals from the database, we found that the value Lyapunov exponent varies between 0.078 and 0.68 for normal subjects [12]. The database also contains processed Parkinsonian tremor signals collected at 30, 45 and 60 minutes after stopping the DBS and medication.…”

A Mobile Application for Smart Computer-Aided Self-Administered Testing of Cognition, Speech, and Motor Impairment

“…Previous works on the neural impairment symptom diagnostics have employed a variety of methods, such as an artificial neural network (ANN) [18], radial basis function neural network (RBFNN) [19], dynamic neural network (DNN) [20], decision tree, ID3 [21], adaptive neuro-fuzzy [22], neuro-fuzzy system [23], fusion of classifiers (Bayesian, k-nearest neighbor (KNN), support vector machine (SVM)) [24], and neuro-fuzzy network [25]. Speech analysis has been used, including OpenSMILE features, Essentia descriptors, MPEG7 descriptors, KTU, jAudio, YAAFE, Tsanas audio features, and a random forest (RF) classifier to detect PD and to fuse features obtained from separate input modalities [26].…”

From Fuzzy Expert System to Artificial Neural Network: Application to Assisted Speech Therapy

“…Also, it provides a powerful framework for the combination of evidence and deduction of consequences based on knowledge stored in the knowledge base [9]. Therefore, fuzzy expert system (FES) can be used in applications for diagnosis, patient monitoring and therapy, image analysis, differential diagnosis, pattern recognition, medical data analysis [10][11][12][13][14].…”