Using Artificial Intelligence to Predict Fall-risk During Adaptive Locomotion in Humans

Abstract

Falls are the third leading cause of unintentional injuries for ages 18-35 years according to the CDC; although there are many studies for falls in the elderly population, the causes and circumstances of falls for younger adults are understudied. The primary objective of this research is to develop a predictive fall indicator using machine learning for this poorly studied population of fallers that are of high risk of injury or death. This work is anchored by a novel locomotion dataset due to the population studied, young adults. This dataset is composed of 88 participants tracked over 150 runs. In this work, Gradient Boosting algorithm yielded the best prediction rates.