Machine Learning Prediction of Pulmonary Function in Children With Cystic Fibrosis

Cystic fibrosis is a multisystem genetic disorder characterized by progressive pulmonary impairment and extrapulmonary limitations. This retrospective observational study will perform a secondary analysis of previously collected data from children with cystic fibrosis. The primary objective is to determine the relative contribution of peripheral muscle oxygenation and postural balance parameters to the prediction of pulmonary function, including forced expiratory volume in 1 second, forced vital capacity, and peak expiratory flow, using machine-learning regression methods. The additional contribution of exercise-related oxygen saturation responses, symptoms, nutritional and anthropometric characteristics, physical activity, respiratory muscle function, quality of life, treatment burden, and disease-related clinical variables will also be examined. No new assessment, intervention, or participant contact will occur.