Predicting Individualized Joint Kinematics over a Continuous Range of Slopes and Speeds

Abstract

Individuality in clinical gait analysis is often quantified by an individual's kinematic deviation from the norm, but it is unclear how these deviations generalize across different walking speeds and ground slopes. Understanding individuality across tasks has important implications in the tuning of prosthetic legs, where clinicians have limited time and resources to personalize the kinematic motion of the leg to therapeutically enhance the wearer's gait. This study seeks to determine an efficient way to predictively model an individual's kinematics over a continuous range of slopes and speeds given only one personalized task at level ground. We were able to predict the kinematics of able-bodied individuals at a wide variety of conditions that were not specifically tuned. Applied to 10 human subjects, the individualization method reduced the RMSE between the model and subject's kinematics over all tasks by an average of 2% (max 52%) at the ankle, 27% (max 59%) at the knee, and 45% (max 83%) at the hip. Our results indicate that knowing how an individual subject differs from the average subject at level ground alone is enough information to improve kinematic predictions across all tasks. This research offers a new method for personalizing robotic prosthetic legs over a variety of tasks without the need of an engineer, which could make these complex devices more clinically viable.

Statistical-Shape Prediction of Lower Limb Kinematics During Cycling, Squatting, Lunging, and Stepping—Are Bone Geometry Predictors Helpful?

“…As such, simulation output denoting subject immobility was rejected ( Van Houcke et al, 2019 ; De Roeck et al, 2020 ). Then, each kinematic curve was discretized into 101 registration entries assigning 0–100% of movement progression ( Sadeghi et al, 2003 ; Schwartz et al, 2004 ; Chau et al, 2005 ; Deluzio and Astephen, 2007 ; Kobayashi et al, 2016 ; Matsuki et al, 2017 ; Bouças et al, 2019 ; Moissenet et al, 2019 ; Van Houcke et al, 2019 ; De Roeck et al, 2020 ; Reznick et al, 2020 ; Duquesne et al, 2021 ; Warmenhoven et al, 2021 ). At last, a continuous registration (CR) method was applied to remove the phase variability of the curves ( Sadeghi et al, 2003 ; Chau et al, 2005 ; Duquesne et al, 2021 ).…”

“…Differences in motion patterns can be attributed to a large number of associated variables: velocity, proprioceptive, vestibular, and visual stimuli as well as neurocognitive and executive functions, body weight, sex, aging effects, and pathological deviations ( Schwartz et al, 2004 ; Chau et al, 2005 ; Martin et al, 2013 ; Kobayashi et al, 2016 ; Reznick et al, 2020 ). While intuitively vital, the impact of bone and joint geometry on in vivo motor variability, nonetheless, remains controversial ( Hoshino et al, 2012 ; Freedman and Sheehan, 2013 ; Lynch et al, 2020 ).…”

“…First, we intend to quantify individual differences for a wide range of activities of daily living (ADL) at a population-wide level. Statistical kinematic models that aim to describe the inter-subject variance in natural joint motion are appropriate for this purpose ( Chau et al, 2005 ; Deluzio and Astephen, 2007 ; Leardini et al, 2017 ; Reznick et al, 2020 ; Duquesne et al, 2021 ). Secondly, we aspire to improve upon the understanding the extent to which segmented bone morphometry or subject characteristics are related to model-derived lower limb kinematics.…”

Data-Driven Variable Impedance Control of a Powered Knee-Ankle Prosthesis for Adaptive Speed and Incline Walking

“…While one of the major advantages of HKIC is that it required no manual tuning, it could be limited by the lack of an ability to customize to an individual's preferred behavior. Future work will investigate methods to incorporate user preferences in the impedance model, such as weighting the optimization with a single baseline personalization for level-ground walking, as suggested in [44]. This baseline personalization could be gathered using tools in a standard clinic, maintaining the minimal-tuning nature of the controller.…”

Lower-limb kinematics and kinetics during continuously varying human locomotion

“…These kinematic models can be trained based on across-participant averages from the presented dataset to generate baseline control strategies for powered prostheses [8][9][10] and exoskeletons 11,12 . Because these models continuously connect a range of tasks, they can be efficiently individualized by heavily weighting one participant-specific task (e.g., level-ground walking) amongst across-participant averages for all other tasks 26 .…”