Predictive Models to Estimate Probabilities of Injuries, Poor Physical Fitness, and Attrition Outcomes in Australian Defense Force Army Recruit Training

Stephen C Allison, Bruce C Cohen, Edward J Zambraski, Mark Jaffrey, Rob Marc Orr

Research output: Book/ReportCommissioned reportResearchpeer-review

Abstract

The purpose of this investigation was to assess the predictive potential of variables collected during the Australian Defence Force Recruit Training (n=19,769; 7,692 [28-day reservists course]; 12,077 [80-day standard]. The 28-day incurred 17.6% injury rate, 1 stress fracture, 5.2% attrition, 30.0% fitness test failure. The 80-day: 34.3% injury rate, 44 stress fractures, 5.0% attrition, 12.1% fitness test failure. Separate models were derived to predict injuries, attrition, and failure to pass the final physical fitness tests. Areas under the receiver operating characteristic curves (AUCs) for course-specific predictive models were relatively low (ranging from 0.51 to 0.69) consistent with failed to poor predictive accuracy. Course-combined models performed somewhat better, with 2 models having AUCs of 0.70 and 0.78; considered fair predictive accuracy. Although overall predictive accuracy was poor, accuracy was improved in models that included course length (28 vs. 80 day) as a predictor; suggesting the potential for using duration of training as a proxy for physical activity dosage to help predict injury and physical fitness.
Original languageEnglish
Place of PublicationNatick
Publisher US Army Research Institute of Environmental Medicine
Number of pages58
Publication statusPublished - 1 Nov 2015

Fingerprint

Physical Fitness
Stress Fractures
Wounds and Injuries
Area Under Curve
Proxy
ROC Curve
Exercise

Cite this

Allison, S. C., Cohen, B. C., Zambraski, E. J., Jaffrey, M., & Orr, R. M. (2015). Predictive Models to Estimate Probabilities of Injuries, Poor Physical Fitness, and Attrition Outcomes in Australian Defense Force Army Recruit Training. Natick: US Army Research Institute of Environmental Medicine.
Allison, Stephen C ; Cohen, Bruce C ; Zambraski, Edward J ; Jaffrey, Mark ; Orr, Rob Marc. / Predictive Models to Estimate Probabilities of Injuries, Poor Physical Fitness, and Attrition Outcomes in Australian Defense Force Army Recruit Training. Natick : US Army Research Institute of Environmental Medicine, 2015. 58 p.
@book{ad48318546ac44a1849b3d1593ea6e9c,
title = "Predictive Models to Estimate Probabilities of Injuries, Poor Physical Fitness, and Attrition Outcomes in Australian Defense Force Army Recruit Training",
abstract = "The purpose of this investigation was to assess the predictive potential of variables collected during the Australian Defence Force Recruit Training (n=19,769; 7,692 [28-day reservists course]; 12,077 [80-day standard]. The 28-day incurred 17.6{\%} injury rate, 1 stress fracture, 5.2{\%} attrition, 30.0{\%} fitness test failure. The 80-day: 34.3{\%} injury rate, 44 stress fractures, 5.0{\%} attrition, 12.1{\%} fitness test failure. Separate models were derived to predict injuries, attrition, and failure to pass the final physical fitness tests. Areas under the receiver operating characteristic curves (AUCs) for course-specific predictive models were relatively low (ranging from 0.51 to 0.69) consistent with failed to poor predictive accuracy. Course-combined models performed somewhat better, with 2 models having AUCs of 0.70 and 0.78; considered fair predictive accuracy. Although overall predictive accuracy was poor, accuracy was improved in models that included course length (28 vs. 80 day) as a predictor; suggesting the potential for using duration of training as a proxy for physical activity dosage to help predict injury and physical fitness.",
author = "Allison, {Stephen C} and Cohen, {Bruce C} and Zambraski, {Edward J} and Mark Jaffrey and Orr, {Rob Marc}",
year = "2015",
month = "11",
day = "1",
language = "English",
publisher = "US Army Research Institute of Environmental Medicine",

}

Allison, SC, Cohen, BC, Zambraski, EJ, Jaffrey, M & Orr, RM 2015, Predictive Models to Estimate Probabilities of Injuries, Poor Physical Fitness, and Attrition Outcomes in Australian Defense Force Army Recruit Training. US Army Research Institute of Environmental Medicine, Natick.

Predictive Models to Estimate Probabilities of Injuries, Poor Physical Fitness, and Attrition Outcomes in Australian Defense Force Army Recruit Training. / Allison, Stephen C; Cohen, Bruce C; Zambraski, Edward J; Jaffrey, Mark; Orr, Rob Marc.

Natick : US Army Research Institute of Environmental Medicine, 2015. 58 p.

Research output: Book/ReportCommissioned reportResearchpeer-review

TY - BOOK

T1 - Predictive Models to Estimate Probabilities of Injuries, Poor Physical Fitness, and Attrition Outcomes in Australian Defense Force Army Recruit Training

AU - Allison, Stephen C

AU - Cohen, Bruce C

AU - Zambraski, Edward J

AU - Jaffrey, Mark

AU - Orr, Rob Marc

PY - 2015/11/1

Y1 - 2015/11/1

N2 - The purpose of this investigation was to assess the predictive potential of variables collected during the Australian Defence Force Recruit Training (n=19,769; 7,692 [28-day reservists course]; 12,077 [80-day standard]. The 28-day incurred 17.6% injury rate, 1 stress fracture, 5.2% attrition, 30.0% fitness test failure. The 80-day: 34.3% injury rate, 44 stress fractures, 5.0% attrition, 12.1% fitness test failure. Separate models were derived to predict injuries, attrition, and failure to pass the final physical fitness tests. Areas under the receiver operating characteristic curves (AUCs) for course-specific predictive models were relatively low (ranging from 0.51 to 0.69) consistent with failed to poor predictive accuracy. Course-combined models performed somewhat better, with 2 models having AUCs of 0.70 and 0.78; considered fair predictive accuracy. Although overall predictive accuracy was poor, accuracy was improved in models that included course length (28 vs. 80 day) as a predictor; suggesting the potential for using duration of training as a proxy for physical activity dosage to help predict injury and physical fitness.

AB - The purpose of this investigation was to assess the predictive potential of variables collected during the Australian Defence Force Recruit Training (n=19,769; 7,692 [28-day reservists course]; 12,077 [80-day standard]. The 28-day incurred 17.6% injury rate, 1 stress fracture, 5.2% attrition, 30.0% fitness test failure. The 80-day: 34.3% injury rate, 44 stress fractures, 5.0% attrition, 12.1% fitness test failure. Separate models were derived to predict injuries, attrition, and failure to pass the final physical fitness tests. Areas under the receiver operating characteristic curves (AUCs) for course-specific predictive models were relatively low (ranging from 0.51 to 0.69) consistent with failed to poor predictive accuracy. Course-combined models performed somewhat better, with 2 models having AUCs of 0.70 and 0.78; considered fair predictive accuracy. Although overall predictive accuracy was poor, accuracy was improved in models that included course length (28 vs. 80 day) as a predictor; suggesting the potential for using duration of training as a proxy for physical activity dosage to help predict injury and physical fitness.

UR - http://www.dtic.mil/docs/citations/AD1000577

M3 - Commissioned report

BT - Predictive Models to Estimate Probabilities of Injuries, Poor Physical Fitness, and Attrition Outcomes in Australian Defense Force Army Recruit Training

PB - US Army Research Institute of Environmental Medicine

CY - Natick

ER -

Allison SC, Cohen BC, Zambraski EJ, Jaffrey M, Orr RM. Predictive Models to Estimate Probabilities of Injuries, Poor Physical Fitness, and Attrition Outcomes in Australian Defense Force Army Recruit Training. Natick: US Army Research Institute of Environmental Medicine, 2015. 58 p.