Machine learning prediction of combat basic training injury from 3D body shape images

Abstract

Introduction Athletes and military personnel are both at risk of disabling injuries due to extreme physical activity. A method to predict which individuals might be more susceptible to injury would be valuable, especially in the military where basic recruits may be discharged from service due to injury. We postulate that certain body characteristics may be used to predict risk of injury with physical activity. Methods US Army basic training recruits between the ages of 17 and 21 (N = 17,680, 28% female) were scanned for uniform fitting using the 3D body imaging scanner, Human Solutions of North America at Fort Jackson, SC. From the 3D body imaging scans, a database consisting of 161 anthropometric measurements per basic training recruit was used to predict the probability of discharge from the US Army due to injury. Predictions were made using logistic regression, random forest, and artificial neural network (ANN) models. Model comparison was done using the area under the curve (AUC) of a ROC curve.

What Is a 2021 Reference Body?

“…Baton Rouge/Honolulu/San Francisco: A highly stratified, diverse adult (age > 18 yrs) sample (n = 570) with the approximate sex, age, weight, height and body mass index (BMI) distribution of multiethnic group of American adults ( Table S1 ; [ 9 , 10 , 11 ]) was evaluated as part of the Shape Up! Adults study (NIH R01 DK109008).…”

“…In addition, a multi-ethnic database on three-dimensional optical (3DO) imaging together with a machine learning approach relating 3D body scans to body composition in humans has been built as the so-called ‘Shape Up! Adults study’ at the Pennington Biomedical Research Center, Louisiana State University, LSU, Baton Rouge, LA, USA; University of California, San Francisco, CA, USA; and the University of Hawaii Cancer Center, Honolulu, HI, USA [ 9 , 10 ].…”

“…This is a secondary analysis of data obtained in studies published previously (see refs. [ 4 , 6 , 7 , 8 , 9 , 10 , 11 , 12 , 13 , 14 , 16 , 17 , 18 , 21 ]). The study was conducted in accordance with the Declaration of Helsinki, and approved by the Institutional Review Board (or Ethics Committee) of the Medical Faculty of the Christian-Albrechts-University of Kiel (see references published in the original papers) for studies involving humans.…”

Military Body Composition Standards and Physical Performance: Historical Perspectives and Future Directions

“…Taken together, the results of these studies suggest that further investigation in this area could provide important insights and inform future training strategies designed to improve soldier performance. Interestingly, it seems that existing military anthropometric datasets may be of use to researchers seeking to examine the relationship between body measurements and outcomes of interest, as 3 studies to date have used existing anthropometric data derived from 3D scans of recruits taken during basic training for the purpose of uniform fitting (74,90,122). Using such data sets, researchers may be able to identify anthropometric characteristics associated with superior performance on a given outcome of interest or perhaps identify anthropometric traits associated with poor performance on a military-relevant task.…”

Military Applications of Machine Learning: A Bibliometric Perspective

“…Several of these applications have already been discussed in Section 4.1. The following is a list of the most important ones: cybersecurity and threat intelligence [88]; image, speech and pattern recognition [89]; the mental health of soldiers and veterans [74]; military ethics [90]; military personnel behavior analytics and management [91,92]; military robotics and smart devices [63]; and the physical health of soldiers and veterans, etc. It is remarkable that several of these ML applications in the military field have not been identified in previous works [36].…”