Sarcopenia Evaluation by using surface EMG-Based Platform with Supervised Classification

Loss of strength and muscle mass, known as sarcopenia, has a high impact on the health status, quality of life and independence of the older population. The use of smart wearable devices is becoming increasingly relevant for the diagnosis and prevention of the disease. For this purpose, surface electromyography is becoming more popular thanks to its minimally invasive characteristics. A hardware/software platform was designed and implemented, based on the processing of the electromyographic signal derived from the Gastrocnemius Lateralis and Tibialis Anterior muscles. These signals are used to analyze the strength of the muscles in order to identify three different confidence levels of sarcopenia. Subsequently, the effectiveness of three state of the art supervised classifiers in the evaluation of sarcopenia was compared. To validate the proposed approach, a series of experiments were performed to verify the effectiveness and its operation in real-time. A total of 32 patients were recruited from Casa Sollievo della Sofferenza Hospital in San Giovanni Rotondo (Foggia, Italy). All patients were considered at risk or suffering from sarcopenia. The obtained results demonstrated the ability of the proposed platform to classify the three confidence levels of sarcopenia, with the Support Vector Machine classifier outperforming the other classifiers in terms of accuracy.