Interpretable prediction of gross motor coordination in children aged 9-10 using machine learning and SHAP: the influence of physical fitness, basic coordination, and executive function.
Аннотация
BACKGROUND
Gross motor coordination is a fundamental component of children's physical development and motor skill acquisition, closely associated with physical fitness, cognitive function, and overall health. This study aimed to examine the influence of physical fitness, basic coordination, and executive function (EF) on gross motor coordination, and to evaluate the predictive performance of machine learning models compared with traditional multiple linear regression (MLR).
METHODS
A total of 167 children (85 boys and 82 girls), aged 9-10 years, participated in the study. Gross motor coordination was assessed using the Körperkoordinationtest für Kinder (KTK). Physical fitness (e.g., 50 m sprint, standing long jump, sit-ups), basic coordination (e.g., kinesthetic differentiation, spatial orientation, balance), and EF (e.g., inhibitory control, working memory) were measured as predictors. Model performance was evaluated using R2, root mean square error (RMSE), and mean absolute error (MAE). SHapley Additive exPlanations (SHAP) were applied to interpret the best-performing model and analyze feature importance and nonlinear effects.
RESULTS
Among the models, Random Forest Regression (RFR) achieved the highest performance (R 2 = 0.533, RMSE = 6.075, MAE = 4.850). SHAP analysis revealed that spatial orientation, body mass index (BMI), dynamic balance, standing long jump, and closed-eye balance were the most important predictors, with spatial orientation, BMI, and closed-eye balance showing notable nonlinear effects. EF contributed minimally to prediction.
CONCLUSION
Spatial-body integration, physical fitness, and postural control are primary determinants of gross motor coordination in children, while cognitive regulation plays a secondary role. Training programs aiming to enhance gross motor coordination should emphasize spatial orientation, body weight management, balance, and lower-limb strength.
Предметные рубрики MeSH
Подготовка и перевод публикации
Обработка статьи · этапы, ошибки и управление
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Тип публикации указан по данным источника. Уровень доказательности автоматически не присваивается.