Machine learning-based bioimpedance assessment of knee osteoarthritis severity.

This study proposes a multiclass model to classify the severity of knee osteoarthritis (KOA) using bioimpedance measurements. The experimental setup considered three types of measurements using eight electrodes: global impedance with adjacent pattern, global impedance with opposite pattern, and direct impedance measurement, which were taken using an electronic device proposed by authors and based on the Analog Devices AD5933 impedance converter. The study comprised 37 participants, 25 with healthy knees and 13 with three different degrees of KOA. All participants performed 20 repetitions of each of the following five tasks: (i) sitting with the knee bent, (ii) sitting with the knee extended, (iii) sitting and performing successive extensions and flexions of the knee, (iv) standing, and (v) walking. Data from the 15 experimental setups (3 types of measurements×5 exercises) were used to train a multiclass random forest. The training and validation cycle was repeated 100 times using random undersampling. At each of the 100 cycles, 80% of the data were used for training and the rest for testing. The results showed that the proposed approach achieved average sensitivities and specificities of 100% for the four KOA severity grades in the extension, cyclic, and gait tasks. This suggests that the proposed method can serve as a screening tool to determine which individuals should undergo x-rays or magnetic resonance imaging for further evaluation of KOA.

A low-cost, portable, two-dimensional bioimpedance distribution estimation system based on the AD5933 impedance converter.

This study proposes a low-cost, portable, eight-channel electrical impedance tomograph based on the AD5933 impedance converter. The patterns for current injection and voltage measurement are managed by an Arduino Mega 2560 board and four 74HC4067 Texas Instruments multiplexers. Regarding the experimental results, the errors in the impedance estimates of an electrical circuit that represents a Cole model were less than 1.14% for the magnitude and 4.15% for the phase. Furthermore, the signal-to-noise ratio measured in a resistive phantom was 55.23 dB. Additional experiments consisted of placing five spheres of different size and conductivity in a saline tank, measuring their impedance through eight electrodes, and then generating impedance maps using the Electrical Impedance Tomography and Diffuse Optical Tomography Reconstruction Software (EIDORS). These maps were different for each sphere, suggesting the proposed prototype as a promising alternative for medical applications.

Dataset for gait analysis and assessment of fall risk for older adults.

This article presents a five-part dataset for human gait analysis in a healthy older adult population (37 women and seven men; age 69.98 ± 8.57 years, body mass index 27.71 ± 4.57). Part 1 compromises demographic data for the 44 participants, along with the results of the Short Physical Performance Battery (SPPB) motor function test and the Mini-Mental State Examination (MMSE). We used the MMSE to ensure the participants could understand the experimental protocol instructions. Part 2 presents the anthropometric measurements of the participants. Part 3 shows the results for each item of the Gait component of the Performance Oriented Mobility Assessment (POMA-G). Part 4 contains five files per participant, storing motion-capture data for the lower limb in the Coordinate 3D (C3D) format. These files were generated using a Vicon motion analysis system, consisting of 24 reflective markers and seven cameras (Vantage V5) sampled at 100 Hz. Part 5 contains 26 gait parameters for each C3D file obtained using Nexus 2.9.3. The dataset is available in a Mendeley repository (Reserved DOI: 10.17632/xgw6bg3g8h.1).

Electronic system for step width estimation using programmable system-on-chip technology and time of flight cameras.

This paper proposes a low-cost portable electronic system for estimating step width during the human gait cycle. This device, intended to support the Walking Stance item of the fall risk assessment test Performance Oriented Mobility Assessment (POMA), contains three electronic boards, comprising two sensing nodes and a concentrator. Each sensing node contains a force sensitive resistor (FSR) and time-of-flight camera (TOF). Each FSR is placed inside the subject's shoe, while each TOF camera is located at the back of their foot. The FSR detects contact between heel and ground, and the TOF measures the distance to a barrier located on the right side of the walking path. Step width is calculated as the difference between the TOF measurements. After the walk is complete, the information obtained by the FSRs and TOFs is sent via a 433 MHz wireless communication to the concentrator board, which is connected to the USB port of a personal computer (PC). The proposed step width measurement system was validated with an infrared based motion capture (Vicon Corp.), giving an error equal to 11.4%  ±  5.5%.