A Density-Based Clustering Approach to Motor Unit Potential Characterizations to Support Diagnosis of Neuromuscular Disorders

• Published in: IEEE transactions on neural systems and rehabilitation engineering 2017-07, Vol.25 (7), p.956-966
• Main Authors: Kamali, Tahereh, Stashuk, Daniel W.
• Format: Article
• Language: English
• Subjects: Action Potentials; Adult; Aged; Aged, 80 and over; Chameleon; Classification algorithms; Clustering algorithms; Computer Simulation; Data Interpretation, Statistical; DBSCAN; density based clustering algorithm; Diagnosis, Computer-Assisted - methods; Diagnostic Techniques, Neurological; Diseases; Electromyography - methods; ensemble of SVM classifiers; Female; Heuristic algorithms; Humans; k-means; Male; Middle Aged; Models, Neurological; Models, Statistical; Motor Neurons; Muscle Fibers, Skeletal; needle electrodiagnostic examination; Neuromuscular; Neuromuscular Diseases - diagnosis; Neuromuscular Diseases - physiopathology; Pattern Recognition, Automated - methods; quantitative electromyographic muscle classification; Shape; spectral clustering; Support Vector Machine; Young Adult
• ISSN: 1534-4320; 1558-0210
• DOI: 10.1109/TNSRE.2017.2673664

Electrophysiological muscle classification involves characterization of extracted motor unit potentials (MUPs) followed by the aggregation of these MUP characterizations. Existing techniques consider three classes (i.e., myopathic, neurogenic, and normal) for both MUP characterization and electrophysiological muscle classification. However, diseased-induced MUP changes are continuous in nature, which make it difficult to find distinct boundaries between normal, myopathic, and neurogenic MUPs. Hence, MUP characterization based on more than three classes is better able to represent the various effects of disease. Here, a novel, electrophysio- logical muscle classification system is proposed, which considers a dynamic number of classes for characterizing MUPs. To this end, a clustering algorithm called neighbor- hood distances entropy consistency is proposed to find clusters with arbitrary shapes and densities in an MUP feature space. These clusters represent several concepts of MUP normality and abnormality and are used for MUP characterization instead of the conventional three classes. An examined muscle is then classified by embedding its MUP characterizations in a feature vector fed to an ensemble of support vector machine and nearest neighbor classifiers. For 103 sets of MUPs recorded in tibialis anterior muscles, the proposed system had a 97% electro-physiological muscle classification accuracy, which is significantly higher than in previous works.