A team of researchers studied gait pattern changes in people with lower-limb amputations to advance development of minimally intrusive gait monitoring systems for use in a clinical setting. The study investigated gyroscope and accelerometer data from inertial sensors to evaluate changes in gait patterns.
One group of 11 people with lower-limb amputations completed walk trials with a biofeedback system designed to perturb gait patterns, and an additional 12 people completed a gait training session with a physiotherapist.
Inertial sensors collected the data, and three algorithms were evaluated: a hidden Markov model-based similarity measure, self-organizing maps, and dynamic time warping. According to the study, statistical analyses demonstrated that self-organizing maps and dynamic time warping effectively assessed changes in gait patterns under a variety of gait perturbation strategies; sensors located on the upper and lower legs significantly outperformed the sensors on the pelvis.
The findings suggested that wearable and adaptable gait monitoring systems are capable of assessing changes in gait patterns, according to the authors, which could enable precise gait monitoring and real-time therapeutic intervention in real-world settings.
The study, “Assessment of gait pattern changes in lower limb amputees using inertial sensor signals: An alternative to gait parameter measurement,” was published in IEEE Transactions on Neural Systems and Rehabilitation Engineering.
