Application of Machine Learning to Predict Trajectory of the Center of Pressure (COP) Path of Postural Sway Using a Triaxial Inertial Sensor

Abstract

Postural sway indicates controlling stability in response to standing balance perturbations and determines risk of falling. In order to assess balance and postural sway, costly laboratory equipment is required, making it impractical for clinical settings. The study aimed to develop a triaxial inertial sensor and apply machine learning (ML) algorithms for predicting trajectory of the center of pressure (COP) path of postural sway. Fifty-three healthy adults, with a mean age of 46 years, participated. The inertial sensor prototype was investigated for its concurrent validity relative to the COP path length obtained from the force platform measurement. Then, ML was applied to predict the COP path by using sensor-sway metrics as the input. The results of the study revealed that all variables from the sensor prototype demonstrated high concurrent validity against the COP path from the force platform measurement (ρ > 0.75; p < 0.001 ). The agreement between sway metrics, derived from the sensor and ML algorithms, illustrated good to excellent agreement (ICC; 0.89–0.95) between COP paths from the sensor metrics, with respect to the force plate measurement. This study demonstrated that the inertial sensor, in comparison to the standard tool, would be an option for balance assessment since it is of low-cost, conveniently portable, and comparable to the accuracy of standard force platform measurement.

Feasibility Study of a Prototype Wearable Inertial Measurement Unit for Elderly Postural Sway Assessment

“…The gyroscope-derived angular velocities in three-dimensional axes (x, y, and z axes) were transmitted via WIFI to computer laptop, where a web-based application examined the perturbation of postural sway. The time-domain parameters were determined in order to quantify the magnitude and trajectory of postural sway in accordance with the earlier studies of Martinez-Mendez et al [ 15 ], Rouis et al [ 20 ], McManus et al [ 25 ] and the authors of this study [ 21 ]. The following metrics were utilized in these studies to detect sway perturbations: the RMS of magnitude, the generalized mean of the quadratic representing the average of signals, the Range, the summation of the range of signals, the summation of the sway area (SA) or area spanned from the signals normalized with respect to the duration of the measurement, and the summation of distance (SD) or total trajectory length.…”

“…Previous research revealed a significant correlation between accelerometer measures and force-plate-derived COP values, specifically for normalized path length, root mean square (RMS), and peak-to-peak values across various standing balance test conditions [ 14 ]. A previous study by the authors utilized supervised machine learning to determine the COP trajectory of a force-plate system, based on inertial sensor metrics, yielding excellent agreement between the two measures (intraclass correlation coefficient (ICC): 0.89 - 0.95) [ 21 ]. Therefore, the objective of this study was to evaluate IMU-based postural sway metrics during quiet stance with four different bases of support and compare them among elderly individuals at risk and non-risk of falls based on clinical balance tests.…”