Artificial Neural Network Identification Of Exercise Expiratory Flow-limitation In Adults

This study aimed to develop and implement a convolutional neural network (CNN) to identify expiratory flow limitation (EFL) in adults exhibiting a range of baseline airway function. Data was collected from non-smokers between the ages of 18-50 years, and the results of the study have not been published previously. The CNNs were trained to identify eFVLs that met or exceeded the expiratory limb of a MEFV curve. The results of this study suggest that deep machine learning might be a viable new approach for identifying EFL during exercise.