Predictive utility of commercial grade technologies for assessing musculoskeletal injury risk in US Marine Corps Officer candidates

Abstract

Recently, commercial grade technologies have provided black box algorithms potentially relating to musculoskeletal injury (MSKI) risk and functional movement deficits, in which may add value to a high-performance model. Thus, the purpose of this manuscript was to evaluate composite and component scores from commercial grade technologies associations to MSKI risk in Marine Officer Candidates. 689 candidates (Male candidates = 566, Female candidates = 123) performed counter movement jumps on SPARTA™ force plates and functional movements (squats, jumps, lunges) in DARI™ markerless motion capture at the start of Officer Candidates School (OCS). De-identified MSKI data was acquired from internal OCS reports for those who presented to the Physical Therapy department for MSKI treatment during the 10 weeks of training. Logistic regression analyses were conducted to validate the utility of the composite scores and supervised machine learning algorithms were deployed to create a population specific model on the normalized component variables in SPARTA™ and DARI™. Common MSKI risk factors (cMSKI) such as older age, slower run times, and females were associated with greater MSKI risk. Composite scores were significantly associated with MSKI, although the area under the curve (AUC) demonstrated poor discrimination (AUC = .55–.57). When supervised machine learning algorithms were trained on the normalized component variables and cMSKI variables, the overall training models performed well, but when the training models were tested on the testing data the models classified MSKI “by chance” (testing AUC avg = .55–.57) across all models. Composite scores and component population specific models were poor predictors of MSKI in candidates. While cMSKI, SPARTA™, and DARI™ models performed similarly, this study does not dismiss the use of commercial technologies but questions the utility of a singular screening task to predict MSKI over 10 weeks. Further investigations should evaluate occupation specific screening, serial measurements, and/or load exposure for creating MSKI risk models.

Countermovement Jump Force-Time Curve Analyses: Reliability and Comparability Across Force Plate Systems

“…Furthermore, according to SS, their RSI is calculated as jump height divided by contraction time (or time to take off) with units reported as meters per second. Yet, at this time, SS referred to this metric as RSI which is typically calculated as the ratio of flight time to contraction time and others have identified this calculation from SS as jump height divided by time to peak force (2). Thus, we recalculated mRSI as jump height divided by time to take off, and the comparisons of SS to FD (CCC 5 0.71, MAPE 5 22.93) and HD (CCC 5 0.85, MAPE 5 28.82) were improved but still resulted in systematic and proportionate bias.…”

“…Coefficients of variation (CoV) and intraclass correlation coefficients of single measures and random testers (ICC [2,1]) were used to test within-session reliability (individual trials within a single CMJ session). Based on previous reports of similar biomechanical metrics, the threshold for acceptable variation was set to CoV ,10% (7,26).…”

Female National Collegiate Athletic Association Division-I Athlete Injury Prediction by Vertical Countermovement Jump Force-Time Metrics

“…However, force-time data have been used to provide additional, valid, and reliable metrics pertaining to vertical countermovement jump (CMJ) movement and performance (5,(18)(19)(20). Although CMJ assessment is primarily aimed to monitor athlete fatigue or training progressions, recent interest pertains to associations with injury risk in tactical and sport athletes (6,7,12,22).…”

“…Others have found no difference in eccentric rate of force development between injured and noninjured athletes, but a greater ratio of eccentric rate of force development to average concentric mean force existed for the injured group compared with noninjured group (24). Much of this research has occurred in military settings, which has shown mixed results regarding baseline jump assessments, on force plates being associated with musculoskeletal injury risk (MSKI) during training (6,7,14). Nonetheless, movement screening associations with MSKI are complex, and discrepancies are likely due to variations in previous injury, sex, sport, competition level, and training requirements (1,11,16,26).…”

Inter-Device Reliability of a Three-Dimensional Markerless Motion Capture System Quantifying Elementary Movement Patterns in Humans

“…It should be noted that the injuries were not classified as contact or non-contact injuries, which makes interpretation of the data challenging [ 17 ]. Still in their infancy, other works in the existing literature within the field of health and sport have used markerless motion capture systems to gain insights into human health and movement characteristics [ 10 , 18 , 19 , 20 ]. While the previously highlighted literature suggests the potentially effective use of markerless motion capture technologies, particularly from a validity standpoint, certain degrees of uncertainty pertaining to the reliability of such devices still remain, especially across a wide range of movement tasks and variables.…”