sEMG-based Sarcopenia Risk Classification using Empirical Mode Decomposition and Machine Learning Algorithms

Abstract

Sarcopenia is the age-related loss of muscle mass, strength and function, it is associated with various adverse health outcomes in older adults. Therefore, early detection of sarcopenia risk at younger ages is crucial for implementing preventive strategies, fostering healthy muscle development, and minimizing the negative impact of sarcopenia on health and aging. In this study, we propose a novel sarcopenia risk detection technique that combines surface electromyography (sEMG) signals and empirical mode decomposition with machine learning algorithms. We first recorded and preprocessed sEMG data from both healthy and individuals with a risk of sarcopenia during various physical activities, including normal walking, fast walking, standard squat, and wide squat. Next, EMG features were extracted from normalized EMG and its IMFs obtained through empirical mode decomposition (EMD) decomposition. Subsequently, a mRMR feature selection method was employed to identify the most influential subset of features. Finally, the performance of state-of-the-art machine learning classifiers was evaluated using a leave-one-subject-out cross-validation technique and the effectiveness of the classifiers for sarcopenia risk classification was assessed through various performance metrics. The proposed method shows high accuracy, with accuracy rates of 88% for normal walking, 89% for fast walking, 81% for standard squat, and 80% for wide squat, providing reliable identification of sarcopenia risk during physical activities. This study showcases the potential of combining sEMG and EMD with machine learning algorithms to design an accurate and efficient technique for sarcopenia risk classification, ultimately improving healthcare outcomes and enhancing the quality of life.