Machine Learning in Biomechanics: Key Applications and Limitations in Walking, Running and Sports Movements

Springer optimization and its applications, Год журнала: 2024, Номер unknown, С. 91 - 148

Опубликована: Окт. 18, 2024

Язык: Английский

Wearable sensor and machine learning accurately estimate tendon load and walking speed during immobilizing boot ambulation

medRxiv (Cold Spring Harbor Laboratory), Год журнала: 2023, Номер unknown

Опубликована: Июнь 5, 2023

Achilles tendon injuries are treated with progressive weight bearing to promote healing and restore function. Patient rehabilitation progression typically studied in controlled, lab settings do not represent the long-term loading experienced during daily living. The purpose of this study is develop a wearable paradigm accurately monitor walking speed using low-cost sensors that reduce subject burden. Ten healthy adults walked an immobilizing boot under various heel wedge conditions (30°, 5°, 0°) speeds. Three-dimensional motion capture, ground reaction force, 6-axis inertial measurement unit (IMU) signals were collected per trial. We used Least Absolute Shrinkage Selection Operator (LASSO) regression predict peak load speed. effects only accelerometer data, different sampling frequency, multiple train model also explored. Walking models outperformed (mean absolute percentage error (MAPE): 8.41 ± 4.08%) (MAPE: 33.93 23.9%). Models trained subject-specific data performed significantly better than generalized models. For example, our personalized was predicted 11.5 4.41% MAPE 4.50 0.91% MAPE. Removing gyroscope channels, decreasing combinations had inconsequential on performance (changes < 6.09%). developed simple monitoring uses LASSO while ambulating boot. This provides clinically implementable strategy longitudinally patient activity recovering from injuries.

Язык: Английский

Towards Out-of-Lab Anterior Cruciate Ligament Injury Prevention and Rehabilitation Assessment: A Review of Portable Sensing Approaches

medRxiv (Cold Spring Harbor Laboratory), Год журнала: 2022, Номер unknown

Опубликована: Окт. 21, 2022

Abstract Anterior cruciate ligament (ACL) injury and ACL reconstruction (ACLR) surgery are common. Many ACL-injured subjects develop osteoarthritis within a decade of injury, major cause disability without cure. Laboratory-based biomechanical assessment can evaluate risk rehabilitation progress after ACLR; however, lab-based measurements expensive inaccessible to majority people. Portable sensors such as wearables cameras be deployed during sporting activities, in clinics, patient homes for assessment. Although many portable sensing approaches have demonstrated promising results various assessments related they not yet been widely adopted tools prevention training, evaluation reconstructions, return-to-sport decision making. The purpose this review is summarize research on out-of-lab applied ACLR offer our perspectives new opportunities future development. We identified 49 original articles ACL-related assessment; the most common modalities were inertial measurement units (IMUs), depth cameras, RGB cameras. studies combined with direct feature extraction, physics-based modeling, or machine learning estimate range parameters (e.g., knee kinematics kinetics) jump-landing tasks, cutting, squats, gait. reviewed depict proof-of-concept methods potential clinical applications including screening, By synthesizing these results, we describe important that exist using sophisticated modeling techniques enable more accurate along standardization data collection creation large benchmark datasets. If successful, advances will widespread use portable-sensing identify factors, mitigate high-risk movements prior optimize paradigms.

Язык: Английский