Validation of an IMU-based Gait Analysis Method for Assessment of Fall Risk Against Traditional Methods.

Falls are a severe problem in older adults, often resulting in severe consequences such as injuries or loss of consciousness. It is crucial to screen fall risk in order to prescribe appropriate therapies that can potentially prevent falls. Identifying individuals who have experienced falls in the past, commonly known as fallers, is used to evaluate fall risk, as a prior fall indicates a higher likelihood of future falls. The methods that have the most support from evidence are Gait Speed (GS) and Time Up and Go (TUG), which use specific cut-off values to evaluate the fall risk. There have been proposals for alternative methods that use wearable sensor technology to improve fall risk assessment. Although these technological alternatives are promising, further research is necessary to validate their use in clinical settings. In this study, we propose a method for identifying fallers based on a Support Vector Machine (SVM) classifier. The inputs for the classifier are the gait parameters obtained from a 30-minute walk recorded using an Inertial Measurement Unit (IMU) placed at the foot of patients. We validated our proposed method using a sample of 157 patients aged over 70 years. Our findings indicate significant differences (p< 0.05) in stride speed, clearance, angular velocity, acceleration, and coefficient of variability among steps between fallers and non-fallers. The proposed method demonstrates the its potential to classify fallers with an accuracy of [79.6]%, slightly outperforming the GS method which provides an accuracy of [77.0]%, and also overcomes its dependency on the cut-off speed to determine fallers. This method could be valuable in detecting fallers during long-term monitoring that does not require periodic evaluations in a clinical setting.

A database with frailty, functional and inertial gait metrics for the research of fall causes in older adults.

The GSTRIDE database contains information of the health status assessment of 163 elderly adults. We provide socio-demographic data, functional and frailty variables, and the outcomes from tests commonly performed for the evaluation of elder people. The database contains gait parameters estimated from the measurements of an Inertial Measurement Unit (IMU) placed on the foot of volunteers. These parameters include the total walking distance, the number of strides and multiple spatio-temporal gait parameters, such as stride length, stride time, speed, foot angles and clearance, among others. The main processed database is stored, apart from MS Excel, in CSV format to ensure their usability. The database is complemented with the raw IMU recordings in TXT format, in order to let researchers test other algorithms of gait analysis. We include the Python programming codes as a base to reproduce or modify them. The database stores data to study the frailty-related parameters that distinguish faller and non-faller populations, and analyze the gait-related parameters in the frail subjects, which are essential topics for the elderly.

Assessing falls in the elderly population using G-STRIDE foot-mounted inertial sensor.

Falls are one of the main concerns in the elderly population due to their high prevalence and associated consequences. Guidelines for the management of the elder with falls are comprised of multidimensional assessments, especially gait and balance. Daily clinical practice needs for timely, effortless, and precise tools to assess gait. This work presents the clinical validation of the G-STRIDE system, a 6-axis inertial measurement unit (IMU) with onboard processing algorithms, that allows the calculation of walking-related metrics correlated with clinical markers of fall risk. A cross-sectional case-control study was conducted with 163 participants (falls and non-falls groups). All volunteers were assessed with clinical scales and conducted a 15-min walking test at a self-selected pace while wearing the G-STRIDE. G-STRIDE is a low-cost solution to facilitate the transfer to society and clinical evaluations. It is open hardware and flexible and, thus, has the advantage of providing runtime data processing. Walking descriptors were derived from the device, and a correlation analysis was conducted between walking and clinical variables. G-STRIDE allowed measuring walking parameters in non-restricted walking conditions (e.g. hallway). Walking parameters statistically discriminate between falls and non-falls groups. We found good/excellent estimation accuracy (ICC = 0.885; [Formula: see text]) for walking speed, showing good/excellent correlation between gait speed and several clinical variables. G-STRIDE can calculate walking-related metrics that allow for discrimination between falls and non-falls groups, which correlates with clinical indicators of fall risk. A preliminary fall-risk assessment based on the walking parameters was found to improve the Timed Up and Go test in the identification of fallers.