Posture analysis in predicting fall-related injuries during French Navy Special Forces selection course using machine learning: A proof of concept study-Reference-Cited by-同舟云学术

Posture analysis in predicting fall-related injuries during French Navy Special Forces selection course using machine learning: A proof of concept study

Published:2023-07-27 Issue: Volume: Page:
ISSN:
Container-title:
language:
Short-container-title:

Author:

Verdonk Charles^ORCID,Duffaud Anaïs M.,Longin Aurélie,Bertrand Matthieu,Zagnoli Fabien,Trousselard Marion,Canini Frédéric

Abstract

ABSTRACTIntroductionInjuries induced by falls represent the main cause of failure in the French Navy Special Forces selection course. In the present study we made the assumption that probing the posture might contribute to predicting the risk of fall-related injury at the individual level.MethodsBefore the start of the selection course, the postural signals of 99 male soldiers were recorded using static posturography while they were instructed to maintain balance with their eyes closed. The event to be predicted was a fall-related injury during the selection course that resulted in the definitive termination of participation. Following a machine learning methodology, we designed an artificial neural network model to predict the risk of fall-related injury from the descriptors of postural signal.ResultsThe neural network model successfully predicted with 69.9% accuracy (95% CI=69.3-70.5) the occurrence of a fall-related injury event during the selection course from the selected descriptors of the posture. The area under the curve (AUC) value was 0.731 (95% CI=0.725-0.738), the sensitivity was 56.8% (95% CI=55.2-58.4), and the specificity was 77.7% (95% CI=76.8-0.78.6).ConclusionIf confirmed with a larger sample, these findings suggest that probing the posture using static posturography and machine learning-based analysis might contribute to inform risk assessment of fall-related injury during military training, and could ultimately lead to the development of novel programs for personalized injury prevention in military population.KEY MESSAGES

Fall-related injuries are a major concern that leads to failure in the French Navy Special Forces selection course.

This proof of concept study shows that analyzing the posture with machine learning can predict the risk of fall-related injury at the individual level.

The findings may prompt the development of novel programs for personalized injury prevention in military settings.

Publisher

Cold Spring Harbor Laboratory

Reference32 articles.

1. At, W. Epidémiologie de la traumatologie aigue sportive chez les sapeurs-pompiers en phase d’incorporation. Medical Degree thesis, Université Paris 13.

2. Pleche, S. Étude des pathologies sportives en lien avec la formation militaire initiale chez des jeunes engagés du Centre de Formation des Militaires du rang d’Angoulême, et engagés sous-officiers de l’École de Saint-Maixent. Medical Degree thesis, Université de Bordeaux.

3. Bertrand, M. Pathologies traumatiques au cours du stage commando marine: analyse des interactions entre vigilance et proprioception. Medical Degree thesis, Université Paris XI.

4. Longin, A. Mécanismes de survenue des traumatismes des membres inférieurs au cours du stage commando marine. Medical Degree thesis, Université Brest - Bretagne Occidentale.

5. Morinière, N. Etude prospective des pathologies médicales et traumatiques au cours du stage commando marine et proposition de mesures de prévention Medical Degree thesis, Université Brest-Bretagne occidentale.