Method and device for classifying man-machine asynchronous phenomenon in mechanical ventilation process

Abstract

The invention discloses a method and a device for classifying man-machine asynchronous phenomena in a mechanical ventilation process. The classification method comprises the following steps: acquiring real-time breathing waveform data of a to-be-detected object in a mechanical ventilation process; extracting Poincare map features of the real-time respiration waveform data; and inputting the Poincare map features into a pre-trained classification model, and outputting a man-machine asynchronous type corresponding to the real-time respiration waveform data by the classification model. According to the method, the Poincare map features are extracted from the original waveform, the method does not depend on other factors except the waveform so as to better reflect information such as form change of the waveform, a classification model capable of being used for various man-machine asynchronous classification tasks in various mechanical ventilation modes is obtained through training, and finally accurate classification of real-time breathing waveform data is achieved.

Description

technical field [0001] The invention belongs to the technical field of electrophysiological detection and monitoring, and specifically relates to a classification method, a classification device, a computer-readable storage medium, and a computer device for human-machine asynchronous phenomena in the process of mechanical ventilation. Background technique [0002] As an important device in the intensive care unit (ICU) of major hospitals, the ventilator plays an extremely important role in the life support system. The interaction process between the ventilator and patients with respiratory diseases is called mechanical ventilation (mechanical ventilation, MV). The patient's respiratory rhythm is controlled by the ventilator, such as pressure control ventilation (PCV) and volume control ventilation (volume control ventilation, VCV); In this mode, the patient has a certain degree of breathing effort, and the ventilator plays a role in assisting the patient's breathing, which ...

AI Technical Summary

Problems solved by technology

[0014] The research found that both machine learning and deep learning have similar performance in terms of classification effects, the difference is that the performance of machine learning algorithms is affected by feature selection, and the current feature selection is mostly composed of statistical features and some clinical data combinations; and depth The model building of the learning algorithm is more complicated than the former

Importantly, there is little existing research on the multi-classification task of multiple ventilation modes in the human-machine asynchronous phenomenon.

Images