The HumanTrak captures human movement through markerless motion tracking and can be a crucial tool in military physical screening. Reliability was examined in eighteen healthy participants who completed shoulder and hip ROM, and dynamic tasks in three body armour conditions. Generally, for all conditions, good to excellent reliability was observed in shoulder abduction and flexion, hip abduction and adduction, and dynamic squats knee and hip flexion (ICC ≥ 0.75 excluding outliers). Shoulder adduction and hip flexion demonstrated moderate to excellent reliability (ICC ≥ 0.50). Shoulder and hip extension and the drop jump were unreliable (ICC: 0.10–0.94, 0.15–0.89, and 0.30–0.82, respectively) due to the large distribution of ICC scores. Tasks with ROM values ≥ 100° involving movement towards or perpendicular to the HumanTrak camera tended to have greater reliability than movements moving away from the camera and out of the perpendicular plane regardless if body armour was worn. Practitioner summary: The HumanTrak analyses ROM in a time-efficient manner in a military setting. This study established that shoulder abduction and adduction (no body armour) and shoulder, hip, and knee flexion were the most reliable measurement for all conditions. Further work is required for movements across different planes. Abbreviations: ROM: range of motion; NBA: no body armour; BA: unloaded body armour; BA9: body armour with 9 kg; RGB: red, green, blue; ICC: intra-class correlation; SEM: standard error of measurement; MDC: minimal detectable change: MSE: mean square error; r: pearson correlations; N: sample size

The ability to estimate lower-extremity mechanics in real-world scenarios may untether biomechanics research from a laboratory environment. This is particularly important for military populations where outdoor ruck marches over variable terrain and the addition of external load are cited as leading causes of musculoskeletal injury As such, this study aimed to examine (1) the validity of a minimal IMU sensor system for quantifying lower-extremity kinematics during treadmill walking and running compared with optical motion capture (OMC) and (2) the sensitivity of this IMU system to kinematic changes induced by load, grade, or a combination of the two. The IMU system was able to estimate hip and knee range of motion (ROM) with moderate accuracy during walking but not running. However, SPM analyses revealed IMU and OMC kinematic waveforms were significantly different at most gait phases. The IMU system was capable of detecting kinematic differences in knee kinematic waveforms that occur with added load but was not sensitive to changes in grade that influence lower-extremity kinematics when measured with OMC. While IMUs may be able to identify hip and knee ROM during gait, they are not suitable for replicating lab-level kinematic waveforms.

Markerless motion capture has improved physical screening efficiency in sport and occupational settings; however, reliability of kinematic measurements from commercial systems must be established. Further, the impact of torso-borne equipment on these measurements is unclear. The purpose of this study was to evaluate the reliability of HumanTrak, a markerless motion capture system, for estimating peak trunk flexion in squat movements with and without a weighted vest. Eighteen participants completed body weight squats (BWSQ) and overhead squats (OHSQ) to their maximum depth (unrestricted-range) and to a plyometric box (fixed-range) while wearing no body armour (NBA) or 9 kg body armour (BA9). Peak trunk flexion was measured using HumanTrak. Testing was performed in two sessions on one day (intra-day) and one session on a separate day (inter-day) to assess reliability. HumanTrak had a standard error of measurement < 3.74 degrees across all movements and conditions. Reliability was good to excellent (ICC = 0.82-0.96) with very large to nearly perfect Pearson correlations (r > 0.80) for all comparisons except unrestricted-range BWSQ with BA9 (ICC = 0.60-0.71, r = 0.71). HumanTrak was more reliable for intra-than inter-day, but reliability was still excellent for almost all inter-day comparisons (ICC > 0.82). HumanTrak is reliable for detecting differences in peak trunk flexion > 8.5 degrees when body armour is not worn and > 10.5 degrees when body armour is worn. Practitioners can assess meaningful changes in sagittal plane trunk motion when screening squat movements regardless of whether body armour is worn.

Purpose: Optimal performance in military tasks is crucial for operational success. These tasks are often simulated in training, assessing personnel performance within a military environment. However, these assessments are time-consuming and a potential injury risk. Physical characteristics such as muscular strength, power, aerobic endurance, and circumferences can be used to predict these dynamic and demanding tasks. Utilizing machine learning models to predict assessment outcomes may lead to optimized management of personnel, time, and interventions in the military. Methods: This study recruited 35 participants to complete two physical sessions assessing multiple physical characteristics and lift-to-place and jerry-can-carry assessments. Machine learning models were developed to predict assessment outcomes based on a down-selection of physical characteristics metrics. Root mean square error (RMSE), normalized root mean square error (NRMSE), and coefficient of variation of the root mean square error (CVRMSE) were used to evaluate the models’ predictive capabilities. Results: The support vector regression (SVR) and ridge models could predict the lift-to-place outcome to an RMSE of ±1.77 kg (NRMSE = 4.44%, CVRMSE = 0.18) and ±2.33 kg (NRMSE = 5.84%; CVRMSE = 0.24) with four and three physical tests, respectively. The multilayer perceptron and SVR models predicted the jerry-can-carry outcome to ±3.36 laps (NRMSE = 23.06%, CVRMSE = 0.39) and ±3.67 laps (NRMSE = 25.20%, CVRMSE = 0.42) with 12 and 8 physical tests, respectively. Conclusions: The lift-to-place outcome can be accurately predicted, showing potential military implementation. The jerry-can-carry outcome shows promise; however, further model optimization and training metrics are required to reduce error. Machine learning models demonstrate their applicability to optimize occupational selection pathways and training interventions for desirable performance in military settings.

Introduction: Assessing kinematic information within military populations can assist in optimizing physical performance and identifying inefficient movement patterns patterns as part of a regular health screening. The HumanTrak is a portable markerless motion capture system capable of quantifying lower body kinematics within field-based settings. The literature to support HumanTrak validity is novel and has not been assessed in a military context. Valid data under specific military conditions are required to support the use of the HumanTrak device within a military setting in order to validate the findings in this unique population. Material and Methods: The validity of the HumanTrak was examined in 17 individuals who completed lower body frontal and sagittal plane tasks at the hip and knee (Protocol Number: 52022787737978). Tasks were performed with and without body armor being worn. All tasks were assessed for peak angles and range of motion outputs from 3 repetitions in a laboratory. HumanTrak outputs were compared to a gold-standard methodology (marker-based motion capture). Standard error of measurement, intraclass correlations, Bland-Altman Plots, and Pearson Correlations of each system’s lower body kinematic outputs were calculated. Results: The results generally showed good validity between the systems’ outputs for most movement tasks. Overall, low absolute measures of error for all tasks were observed, indicating that the HumanTrak can accurately measure lower body kinematics with minimal error. Besides hip flexion, minimal validity differences were seen between the body armor and no body armor conditions. Conclusion: The HumanTrak’s validity results suggest it provides a valid and accurate representation of lower body kinematics, making it useful for military and sports science applications. Practitioners can confidently use the HumanTrak to quantify lower body kinematics without requiring a sterile laboratory environment, like a gymnasium setting.

Manual materiel handling (MMH) is an important task within the military and routine physical assessments ensure personnel are proficient in MMH tasks. Research demonstrates that predictive models can accurately estimate MMH performance. Optimization of these models may enhance military workflows by providing insights into maximal military performance of MMH tasks. This study recruited a mixed population of 51 general and military participants to assess physical characteristics and MMH lift-to-place performance. Previously developed models (support vector regressions (SVR) and ridge) were retrained and optimized through hyperparameter and feature selection tuning based on physical characteristic metrics. Root mean square errors (RMSE) evaluated the model's prediction performance. The best retrained SVR models had lower prediction error than the best retrained ridge models (RMSEs of 3.04 and 3.62 kgs vs 3.32 and 4.24 kgs, respectively). SVR models require minimal implementation effort and provide robust predictive capabilities, making them a valuable tool for military organizations.