Recognising Gait Patterns of People in Risk of Falling with a Multi-layer Perceptron

Motion Sensors-Based Machine Learning Approach for the Identification of Anterior Cruciate Ligament Gait Patterns in On-the-Field Activities in Rugby Players

Sensors ◽

10.3390/s20113029 ◽

2020 ◽

Vol 20 (11) ◽

pp. 3029

Author(s):

Salvatore Tedesco ◽

Colum Crowe ◽

Andrew Ryan ◽

Marco Sica ◽

Sebastian Scheurer ◽

...

Keyword(s):

Machine Learning ◽

Anterior Cruciate Ligament ◽

Cruciate Ligament ◽

Gradient Boosting ◽

Support Vector ◽

Motion Sensors ◽

Multi Layer Perceptron ◽

Gait Patterns ◽

Anterior Cruciate ◽

Rugby Players

Anterior cruciate ligament (ACL) injuries are common among athletes. Despite a successful return to sport (RTS) for most of the injured athletes, a significant proportion do not return to competitive levels, and thus RTS post ACL reconstruction still represents a challenge for clinicians. Wearable sensors, owing to their small size and low cost, can represent an opportunity for the management of athletes on-the-field after RTS by providing guidance to associated clinicians. In particular, this study aims to investigate the ability of a set of inertial sensors worn on the lower-limbs by rugby players involved in a change-of-direction (COD) activity to differentiate between healthy and post-ACL groups via the use of machine learning. Twelve male participants (six healthy and six post-ACL athletes who were deemed to have successfully returned to competitive rugby and tested in the 5–10 year period following the injury) were recruited for the study. Time- and frequency-domain features were extracted from the raw inertial data collected. Several machine learning models were tested, such as k-nearest neighbors, naïve Bayes, support vector machine, gradient boosting tree, multi-layer perceptron, and stacking. Feature selection was implemented in the learning model, and leave-one-subject-out cross-validation (LOSO-CV) was adopted to estimate training and test errors. Results obtained show that it is possible to correctly discriminate between healthy and post-ACL injury subjects with an accuracy of 73.07% (multi-layer perceptron) and sensitivity of 81.8% (gradient boosting). The results of this study demonstrate the feasibility of using body-worn motion sensors and machine learning approaches for the identification of post-ACL gait patterns in athletes performing sport tasks on-the-field even a number of years after the injury occurred.

Download Full-text

Gait Instability in Older People with Hallux Valgus

Foot & Ankle International ◽

10.1177/107110070502600610 ◽

2005 ◽

Vol 26 (6) ◽

pp. 483-489 ◽

Cited By ~ 90

Author(s):

Hylton B. Menz ◽

Stephen R. Lord

Keyword(s):

Older People ◽

Hallux Valgus ◽

Vertical Plane ◽

Step Length ◽

Upper Body ◽

Risk Of Falling ◽

Gait Patterns ◽

Irregular Terrain ◽

Foot Problems ◽

Detrimental Impact

Background: Hallux valgus is a common condition that may lead to considerable pain and disability. There is also evidence that hallux valgus may impair balance and increase the risk of falling in older people. Although a number of plantar pressure studies have been undertaken in people with and without hallux valgus, little is known about how hallux valgus affects basic gait patterns or the movement of the upper body when walking. Methods: Measurements of temporospatial parameters of gait and acceleration patterns of the head and pelvis were obtained in 71 people (24 men, 47 women) between 75 and 93 (mean 80 ± 4) years of age when walking on both a level surface and a specially designed irregular walkway. Foot problems, vision, peripheral sensation, strength, and reaction time also were evaluated. Results: After adjusting for potential confounders, subjects with moderate to severe hallux valgus were found to exhibit significantly reduced velocity and step length on both walking surfaces and less rhythmic acceleration patterns in the vertical plane when walking on the irregular surface compared to subjects with no or mild hallux valgus. Conclusion: These findings indicate that hallux valgus has a significant detrimental impact on gait patterns that may contribute to instability and risk of falling in older people, particularly when walking on irregular terrain.

Download Full-text

Effects of Indoor Footwear on Balance and Gait Patterns in Community-Dwelling Older Women

Gerontology ◽

10.1159/000448892 ◽

2016 ◽

Vol 63 (2) ◽

pp. 129-136 ◽

Cited By ~ 9

Author(s):

Hylton B. Menz ◽

Maria Auhl ◽

Shannon E. Munteanu

Keyword(s):

Older Women ◽

Walking Speed ◽

Postural Sway ◽

Step Length ◽

Stability Test ◽

Walk Test ◽

Risk Of Falling ◽

Gait Patterns ◽

Limits Of Stability ◽

Balance Ability

Background: Footwear worn indoors is generally less supportive than outdoor footwear and may increase the risk of falls. Objective: To evaluate balance ability and gait patterns in older women while wearing different styles of indoor footwear: a backless slipper and an enclosed slipper designed to optimise balance. Methods: Older women (n = 30) aged 65-83 years (mean 74.4, SD 5.6) performed a series of laboratory tests of balance ability (postural sway, limits of stability, and tandem walking, measured with the NeuroCom® Balance Master) and gait patterns (walking speed, cadence, and step length, measured with the GAITRite® walkway) while wearing (1) socks, (2) backless slippers with a soft sole, and (3) enclosed slippers with a firm sole and Velcro® fastening. Perceptions of the footwear were also documented using a structured questionnaire. Results: Significant overall effects of footwear were observed for postural sway, the limits of stability test (directional control), the tandem walk test (step width and end sway), and temporospatial gait patterns (walking speed, cadence, and step length). No footwear effects were observed for maximum excursion when performing the limits of stability test or for speed when performing the tandem walk test. Post hoc tests indicated that performances were best while wearing the enclosed slippers, intermediate with socks, and worst with backless slippers. The enclosed slippers were perceived to be more attractive, comfortable, and well fitted, but heavier than the backless slippers. Most participants (n = 23; 77%) reported that they would consider wearing the enclosed slippers to reduce their risk of falling. Conclusion: Indoor footwear with an enclosed heel, Velcro® fastening, and a firm sole optimises balance and gait compared to backless slippers, and is therefore recommended to reduce the risk of falling.

Download Full-text

Efficiency and Stability of Step-To Gait in Slow Walking

Frontiers in Human Neuroscience ◽

10.3389/fnhum.2021.779920 ◽

2022 ◽

Vol 15 ◽

Author(s):

Kento Hirayama ◽

Yohei Otaka ◽

Taichi Kurayama ◽

Toru Takahashi ◽

Yutaka Tomita ◽

...

Keyword(s):

High Risk ◽

Muscle Weakness ◽

Lateral Displacement ◽

Gait Pattern ◽

Motor Deficit ◽

Risk Of Falling ◽

Gait Patterns ◽

Normal Gait ◽

Percent Recovery ◽

Low Speeds

As humans, we constantly change our movement strategies to adapt to changes in physical functions and the external environment. We have to walk very slowly in situations with a high risk of falling, such as walking on slippery ice, carrying an overflowing cup of water, or muscle weakness owing to aging or motor deficit. However, previous studies have shown that a normal gait pattern at low speeds results in reduced efficiency and stability in comparison with those at a normal speed. Another possible strategy is to change the gait pattern from normal to step-to gait, in which the other foot is aligned with the first swing foot. However, the efficiency and stability of the step-to gait pattern at low speeds have not been investigated yet. Therefore, in this study, we compared the efficiency and stability of the normal and step-to gait patterns at intermediate, low, and very low speeds. Eleven healthy participants were asked to walk with a normal gait and step-to gait on a treadmill at five different speeds (i.e., 10, 20, 30, 40, and 60 m/min), ranging from very low to normal walking speed. The efficiency parameters (percent recovery and walk ratio) and stability parameters (center of mass lateral displacement) were analyzed from the motion capture data and then compared for the two gait patterns. The results suggested that step-to gait had a more efficient gait pattern at very low speeds of 10–30 m/min, with a larger percent recovery, and was more stable at 10–60 m/min in comparison with a normal gait. However, the efficiency of the normal gait was better than that of the step-to gait pattern at 60 m/min. Therefore, step-to gait is effective in improving gait efficiency and stability when faced with situations that force us to walk slowly or hinder quick walking because of muscle weakness owing to aging or motor deficit along with a high risk of falling.

Download Full-text