Related Experiment Video
Updated: Jun 6, 2026
Subject-specific Musculoskeletal Model for Studying Bone Strain During Dynamic Motion
Published on: April 11, 2018
Development of a Pragmatic Prediction Model for Bone Stress Injuries in First-Year US Military Academy Cadets
Timothy G Eckard1, Stephen W Marshall2, Kristen L Kucera3
1Division of Physical Therapy, Department of Health Sciences.
Context:
Bone stress injuries (BSIs) have been recognized as some of the most common and potentially serious overuse injuries in military training and result in negative effects on service member health and force readiness. Authors of several studies have purported to develop prediction models that could successfully identify individuals in military training at high risk for BSI, but none are currently acceptable for implementation for 1 or more reasons.
Objective:
To develop an accurate, parsimonious prediction model for BSI risk in a military training population using easily obtained and interpreted predictor variables.
Design:
Prospective cohort study.
Setting:
US Military Academy at West Point.
Patients Or Other Participants:
A total of 3227 (749 females, 23.2%) incoming cadets.
Main Outcome Measures:
A multivariable prediction model for BSI risk during the first year of cadet training was created using potential predictor variables related to demographics, anthropometrics, exercise and injury histories, and lower extremity movement quality. A scree plot of change in model log likelihood value was used to guide selection of variables in the final model. Performance of this model was assessed for calibration (ie, goodness of fit) and discrimination (ie, prognostic accuracy). Minimum acceptable criteria for each were determined a priori.
Results:
A total of 63 BSIs occurred in the study period. The final model consisted of sex and running frequency before entry. Performance of this model was sufficient on some measures (specificity) to recommend implementation but not on others (area under the curve and sensitivity). Sensitivity analyses revealed that an expanded model consisting of all predictor variables also did not reach the minimum acceptable calibration or discrimination criteria.
Conclusions:
Despite use of a large dataset and several predictor variables with well-established associations with BSI risk, we were unable to develop a prediction model for BSI risk with adequate prognostic accuracy properties using a set of easily obtained predictor variables.
