Identification of Patients with Sarcopenia Using Gait Parameters Based on Inertial Sensors

Abstract

Sarcopenia can cause various senile diseases and is a major factor associated with the quality of life in old age. To diagnose, assess, and monitor muscle loss in daily life, 10 sarcopenia and 10 normal subjects were selected using lean mass index and grip strength, and their gait signals obtained from inertial sensor-based gait devices were analyzed. Given that the inertial sensor can measure the acceleration and angular velocity, it is highly useful in the kinematic analysis of walking. This study detected spatial-temporal parameters used in clinical practice and descriptive statistical parameters for all seven gait phases for detailed analyses. To increase the accuracy of sarcopenia identification, we used Shapley Additive explanations to select important parameters that facilitated high classification accuracy. Support vector machines (SVM), random forest, and multilayer perceptron are classification methods that require traditional feature extraction, whereas deep learning methods use raw data as input to identify sarcopenia. As a result, the input that used the descriptive statistical parameters for the seven gait phases obtained higher accuracy. The knowledge-based gait parameter detection was more accurate in identifying sarcopenia than automatic feature selection using deep learning. The highest accuracy of 95% was achieved using an SVM model with 20 descriptive statistical parameters. Our results indicate that sarcopenia can be monitored with a wearable device in daily life.

Wearable Sensor for Assessing Gait and Postural Alterations in Patients with Diabetes: A Scoping Review

“…Thus, they are useful for implementing strategies to reduce the risk of falls which represents a major public health problem [50]. Recent reports suggest that IMUs, besides being useful in evaluating and to monitoring gait alterations in patients with neurodegenerative diseases such as Parkinson's disease [51][52][53], are useful for; patients with osteoarthritis [54], with benign paroxysmal positional vertigo, the most common peripheral vestibular disorder, leading to balance difficulties and increased fall risks [55] and walking disturbances in sarcopenic patients [56], they are also useful for gait event detection and analysis of gait alterations in patients with diabetes secondary to DPN [23,24,[27][28][29]31]. In spatiotemporal gait parameters recorded using a wearable sensor in patients with DPN, Kang et al showed that gait initiation steps and dynamic balance may be more sensitive than gait speed for detecting gait deterioration due to DPN [23], and Najafi et al demonstrated that gait alteration in patients with DPN is most pronounced while walking barefoot over longer distances [31].…”

Predicting Sarcopenia of Female Elderly from Physical Activity Performance Measurement Using Machine Learning Classifiers

“…Kim et al developed a sarcopenia classification model by performing SVM algorithm from data collected by 2 IMU during walking (Accuracy: 95%). 30 The sarcopenia classification model showed a higher performance than that of the sarcopenia classification model developed in this study. However, the reason for such performance difference is that more IMUs were used for measuring physical activity.…”

Sarcopenia: Technological Advances in Measurement and Rehabilitation

“…Lastly, a very recent article [14] aimed at identifying and elaborating parameters from gait signals produced by the sensors in order to develop a screening and classification method for sarcopenia. In the study were used specific parameters that they interpreted through an artificial intelligence (AI) model called SHAP (Shapley Additive Explanations).…”

“…In the study were used specific parameters that they interpreted through an artificial intelligence (AI) model called SHAP (Shapley Additive Explanations). The features obtained through the inertial signals were not exhaustive; for this reason, further data and greater cohorts, respectively, with additional clinical evaluations should be collected and studied [14].…”