Principal component analysis biplot visualization of electromyogram features for submaximal muscle strength grading

• Published in: Computers in biology and medicine 2024-11, Vol.182, p.109142, Article 109142
• Main Authors: Saranya, S., Poonguzhali, S.
• Format: Article
• Language: English
• Subjects: Accuracy; Adult; Artificial intelligence; Back injuries; Back pain; Classification; Clustering; Electromyogram; Electromyography; Electromyography - methods; Female; Gaussian mixture model; Humans; Injury analysis; K-means; Male; Medical research; Methods; Muscle strength; Muscle Strength - physiology; Muscle, Skeletal - diagnostic imaging; Muscle, Skeletal - physiology; Muscle, Skeletal - physiopathology; Muscles; PCA biplots; Principal Component Analysis; Principal components analysis; Probabilistic models; Signal Processing, Computer-Assisted; Spinal cord injuries; Sports training; Strength training; Submaximal muscle strength; Visualization; Waveforms
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2024.109142

Submaximal muscle strength grading is clinically significant to monitor the progress of rehabilitation. Especially muscle strength grading of core back muscles is challenging using the conventional manual muscle testing (MMT) methods. The muscles are crucial to recovery from back pain, spinal cord injury, stroke and other related diseases. The subjective nature of MMT, adds more ambiguity to grade fine progressions in submaximal strength levels involving 4-, 4 and 4+ grades. Electromyogram (EMG) has been widely used as a quantitative measure to provide insight into the progress of muscle strength. However, several EMG features have been reported in previous studies, and the selection of suitable features pertaining to the problem has remained a challenge. Principal Component Analysis (PCA) biplot visualization is employed in this study to select EMG features that highlight fine changes in muscle strength spanning the submaximal range. Features that offer maximum loading in the principal component subspace, as observed in the PCA biplot, are selected for grading submaximal strength. The performance of the proposed feature set is compared with conventional Principal Component (PC) scores. Submaximal muscle strength grades of 4-, 4, 4+ or 5 are assigned using K-means and Gaussian mixture model clustering methods. Clustering performance of the two feature selection methods is compared using the silhouette score metric. The proposed feature set from biplot visualization involving Root Mean Square (RMS) EMG and Waveform Length in combination with Gaussian Mixture Model (GMM) clustering method was observed to offer maximum accuracy. Muscle-wise mean Silhouette Index (SI) scores (p