Explainable Artificial Intelligence and Wearable Sensor-Based Gait Analysis to Identify Patients with Osteopenia and Sarcopenia in Daily Life.

Osteopenia and sarcopenia can cause various senile diseases and are key factors related to the quality of life in old age. There is need for portable tools and methods that can analyze osteopenia and sarcopenia risks during daily life, rather than requiring a specialized hospital setting. Gait is a suitable indicator of musculoskeletal diseases; therefore, we analyzed the gait signal obtained from an inertial-sensor-based wearable gait device as a tool to manage bone loss and muscle loss in daily life. To analyze the inertial-sensor-based gait, the inertial signal was classified into seven gait phases, and descriptive statistical parameters were obtained for each gait phase. Subsequently, explainable artificial intelligence was utilized to analyze the contribution and importance of descriptive statistical parameters on osteopenia and sarcopenia. It was found that XGBoost yielded a high accuracy of 88.69% for osteopenia, whereas the random forest approach showed a high accuracy of 93.75% for sarcopenia. Transfer learning with a ResNet backbone exhibited appropriate performance but showed lower accuracy than the descriptive statistical parameter-based identification result. The proposed gait analysis method confirmed high classification accuracy and the statistical significance of gait factors that can be used for osteopenia and sarcopenia management.

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

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.

Current/Voltage Dual-Mode Single-Wire Simultaneous Bidirectional Interface Architecture for Sensor System.

This paper presents a simultaneous bidirectional asymmetrical serial interface architecture for sensor systems. The proposed current/voltage dual-mode signaling scheme provides system synchronous clock and continuous data transmission between sensor integrated circuit (IC) and system-on-a-chip (SoC) using a single wire, which minimizes pin requirements on packages. Two types of transceiver circuits were implemented in a 65 nm CMOS technology for the sensor IC and the SoC, and they were designed for transmission rates of 1 Mb/s and 250 Kb/s, core areas of 0.008 mm2 and 0.142 mm2, and power consumptions of 7.1 µW and 145.8 µW, respectively. The transceiver circuit for the sensor IC was also applied to a monolithic PPG sensor implemented in 180 nm CMOS, and the acquisition and transmission of PPG sensor data with the transceiver for the SoC, implemented in 65 nm, was successfully achieved.

Cervical coupling motion characteristics in healthy people using a wireless inertial measurement unit.

Objective. The objectives were to show the feasibility of a wireless microelectromechanical system inertial measurement unit (MEMS-IMU) to assess the time-domain characteristics of cervical motion that are clinically useful to evaluate cervical spine movement. Methods. Cervical spine movements were measured in 18 subjects with wireless IMUs. All rotation data are presented in the Euler angle system. Amount of coupling motions was evaluated by calculating the average angle ratio and the maximum angle ratio of the coupling motion to the primary motion. Reliability is presented with intraclass correlation coefficients (ICC). Results. Entire time-domain characteristics of cervical motion were measured with developed MEMS-IMU system. Cervical range of motion (CROM) and coupling motion range were measured with high ICCs. The acquired data and calculated parameters had similar tendency with the previous studies. Conclusions. We evaluated cervical motion with economic system using a wireless IMU of high reliability. We could directly measure the three-dimensional cervical motion in degrees in realtime. The characteristics measured by this system may provide a diagnostic basis for structural or functional dysfunction of cervical spine. This system is also useful to demonstrate the effectiveness of any intervention such as conventional medical treatment, and Korean medical treatment, exercise therapy.