Convolutional neural network-based respiration analysis of electrical activities of the diaphragm

Abstract

The electrical activity of the diaphragm (Edi) is considered a new respiratory vital sign for monitoring breathing patterns and efforts during ventilator care. However, the Edi signal contains irregular noise from complex causes, which makes reliable breathing analysis difficult. Deep learning was implemented to accurately detect the Edi signal peaks and analyze actual neural breathing in premature infants. Edi signals were collected from 17 premature infants born before gestational age less than 32 weeks, who received ventilatory support with a non-invasive neurally adjusted ventilatory assist. First, a local maximal detection method that over-detects candidate Edi peaks was used. Subsequently, a convolutional neural network-based deep learning was implemented to classify candidates into final Edi peaks. Our approach showed superior performance in all aspects of respiratory Edi peak detection and neural breathing analysis compared with the currently used recording technique in the ventilator. The method obtained a f1-score of 0.956 for the Edi peak detection performance and R2 value of 0.823 for respiratory rates based on the number of Edi peaks. The proposed technique can achieve a more reliable analysis of Edi signals, including evaluation of the respiration rate in premature infants.