Survey of kinesiologists' functional capacity evaluation practice in Canada

Detecting subject-specific fatigue-related changes in lifting kinematics using a machine learning approach

Individual responses to fatigue have been observed in lifting kinematics, suggesting a subject-specific approach is necessary for fatigue identification. One-class support vector machines (OCSVM) may provide an objective method to classify fatigue-related kinematic changes during repetitive lifting. Participants completed a repetitive lifting protocol while motion capture recorded lifting motions. Subject-specific kinematics from participants' first 35% of lifts trained OCSVM decision boundaries. The remaining lifts were separated into test sets and classified against the decision boundary to identify the percentage of outlier lifts within each test set. Spearman's correlation assessed if the test sets' percentage of outlier lifts increased concurrently with participants' rating of perceived exertion (RPE). Significant positive associations were found for participants who demonstrated evidence of fatigue, while no significant associations were found for participants who did not demonstrate evidence of fatigue. These results demonstrate the prospective efficacy of an outlier detection tool for fatigue detection during repetitive lifting.Practitioner Summary: An objective subject-specific fatigue detection method is desired for workplace tasks, such as lifting. An outlier detection machine learning approach was identified when lifting movement patterns changed from baseline throughout a repetitive lifting protocol. Participants who demonstrated an increase in outlier movement patterns had a concurrent increase in self-reported fatigue.

Towards the Use of 2D Video-Based Markerless Motion Capture to Measure and Parameterize Movement During Functional Capacity Evaluation

Purpose The objective of this study was to determine the agreement of kinematic parameters calculated from motion data collected via a 2D video-based pose-estimation (markerless motion capture) approach and a laboratory-based 3D motion capture approach during a floor-to-waist height functional lifting test. Method Twenty healthy participants each performed three floor-to-waist height lifts. Participants' lifts were captured simultaneously using 2D video (camcorder) in the sagittal plane and 3D motion capture (Vicon, Oxford, UK). The three lifts were representative of a perceived light, medium, and heavy load. Post-collection, video data were processed through a pose-estimation software (i.e., markerless motion capture). Motion data from 3D motion capture and video-based markerless motion capture were each used to calculate objective measures of interest relevant to a functional capacity evaluation (i.e., posture, balance, distance of the load from the body, and coordination). Bland-Altman analyses were used to calculate agreement between the two methods. Results Bland-Altman analysis revealed that mean differences ranged from 1.9° to 22.1° for posture and coordination-based metrics calculated using markerless and 3D motion capture, respectively. Limits of agreement for most posture and coordination measures were approximately + 20°. Conclusions 2D video-based pose estimation offers a strategy to objectively measure movement and subsequently calculated metrics of interest within an FCE context and setting, but at present the agreement between metrics calculated using 2D video-based methods and 3D motion capture is insufficient. Therefore, continued effort is required to improve the accuracy of 2D-video based pose estimation prior to inclusion into functional testing paradigms.

Feature Detection and Biomechanical Analysis to Objectively Identify High Exposure Movement Strategies When Performing the EPIC Lift Capacity test

Purpose The Epic Lift Capacity (ELC) test is used to determine a worker's maximum lifting capacity. In the ELC test, maximum lifting capacity is often determined as the maximum weight lifted without exhibiting a visually appraised "high-risk workstyle." However, the criteria for evaluating lifting mechanics have limited justification. This study applies feature detection and biomechanical analysis to motion capture data obtained while participants performed the ELC test to objectively identify aspects of movement that may help define "high-risk workstyle". Method In this cross-sectional study, 24 participants completed the ELC test. We applied Principal Component Analysis, as a feature detection approach, and biomechanical analysis to motion capture data to objectively identify movement features related to biomechanical exposure on the low back and shoulders. Principal component scores were compared between high and low exposure trials (relative to median exposure) to determine if features of movement differed. Features were interpreted using single component reconstructions of principal components. Results Statistical testing showed that low exposure lifts and lowers maintained the body closer to the load, exhibited squat-like movement (greater knee flexion, wider base of support), and remained closer to neutral posture at the low back (less forward flexion and axial twist) and shoulder (less flexion and abduction). Conclusions Use of feature detection and biomechanical analyses revealed movement features related to biomechanical exposure at the low back and shoulders. The objectively identified criteria could augment the existing scoring criteria for ELC test technique assessment. In the future, such features can inform the design of classifiers to objectively identify "high-risk workstyle" in real-time.

Exploring the Application of Pattern Recognition and Machine Learning for Identifying Movement Phenotypes During Deep Squat and Hurdle Step Movements

Background

Movement screens are increasingly used in sport and rehabilitation to evaluate movement competency. However, common screens are often evaluated using subjective visual detection of a priori prescribed discrete movement features (e.g., spine angle at maximum squat depth) and may not account for whole-body movement coordination, or associations between different discrete features.

Objective

To apply pattern recognition and machine learning techniques to identify whole-body movement pattern phenotypes during the performance of exemplar functional movement screening tasks; the deep squat and hurdle step. Additionally, we also aimed to compare how discrete kinematic measures, commonly used to score movement competency, differed between emergent groups identified via pattern recognition and machine learning.

Methods

Principal component analysis (PCA) was applied to 3-dimensional (3D) trajectory data from participant's deep squat (DS) and hurdle step performance, identifying emerging features that describe orthogonal modes of inter-trial variance in the data. A gaussian mixture model (GMM) was fit and used to cluster the principal component scores as an unsupervised machine learning approach to identify emergent movement phenotypes. Between group features were analyzed using a one-way ANOVA to determine if the objective classifications were significantly different from one another.

Results

Three clusters (i.e., phenotypes) emerged for the DS and right hurdle step (RHS) and 4 phenotypes emerged for the left hurdle step (LHS). Selected discrete points commonly used to score DS and hurdle step movements were different between emergent groups. In regard to the select discrete kinematic measures, 4 out of 5, 7 out of 7 and 4 out of 7, demonstrated a main effect (p < 0.05) between phenotypes for the DS, RHS, and LHS respectively.

Conclusion

Findings support that whole-body movement analysis, pattern recognition and machine learning techniques can objectively identify movement behavior phenotypes without the need to a priori prescribe movement features. However, we also highlight important considerations that can influence outcomes when using machine learning for this purpose.

Is deep squat movement strategy related to floor-to-waist height lifting strategy: implications for physical employment testing

Generalised predictive tests may be viable screening tools to evaluate job candidate workability if movement strategy used in assessment is consistent with movement strategy used in work. This study investigated if deep squat (DS) kinematics could predict floor-to-waist height lifting kinematics. Participants performed three DS repetitions, and 10 lifts of both a 10 kg and 20 kg box. Whole body kinematics were collected to calculate knee, hip and low back angles, and coordination as measured by relative phase angles. Movement features of lower extremity control, including knee and hip angles and coordination, were significantly correlated (r = 0.43-0.85) between the DS and lifting. However, low back movement features, measures linked to injury risk, were not significantly correlated between the DS and lifting. These findings do not support the DS as a suitable movement screen to predict lifting strategy, specifically when considering low back control. Practitioner summary: This study investigated whether lifting strategy could be inferred from deep squat performance. Knee and hip movement strategies were associated between the deep squat and lifting. However, inconsistencies in low back control between the deep squat and lifting limit the deep squat's injury risk assessment potential.