Influence of the Backpack on School Children’s Gait: A Statistical and Machine Learning Approach

Studies and reviews show that the vast majority of students around the world use heavy and uncomfortable backpacks, which could negatively affect their skeletal-muscle development or at least generate a non-physiological functional overload and a change in the kinematics of gait. The purpose of this study is to investigate the role of the school backpack during the execution of the Walk test trying to identify if and how much it affects walking in terms of space-time parameters considering whether it might be correlated to potential spine disorders during the development age. A population-based sample of 98 students (60% female) aging from 10 to 12 years old was studied; gender, age, weight and lower limb length were recorded. Kinematic data were computed using a wearable inertial device for gait analysis: G-WALK System by BTS Bioengineering and analyzed using t-test and Machine Learning. Overall, concerning t-test between free walk and walk with backpack, it emerges a significant statistical difference on 9 out of 10 kinematic parameters, of which 6 with maximum statistical significance (p-value < 0.0001). Machine Learning analysis was carried out through Linear Discriminant Analysis, Naive Bayes, AdaBoost and Random Forest algorithms considering as different classes: free walk and walk with backpack. Accuracy and ROC Area were considered as evaluation metrics. The best performances were reached with Linear Discriminant Analysis with an accuracy of 85.71% and a ROC Area of 0.92. Study results showed a drastic change on kinematic due to the backpack. These results should be taken in correct account to safeguard children’s health wearing backpack for prolonged periods.