METHOD AND APPARATUS FOR GRAPH NEURAL NETWORK-BASED DETECTION OF MAN-MACHINE ASYNCHRONISM IN MECHANICAL VENTILATION

Title:

METHOD AND APPARATUS FOR GRAPH NEURAL NETWORK-BASED DETECTION OF MAN-MACHINE ASYNCHRONISM IN MECHANICAL VENTILATION

Document Type and Number:

WIPO Patent Application WO/2023/155601

Kind Code:

A1

Abstract:

Provided are a method and an apparatus for graph neural network-based detection of man-machine asynchronism in mechanical ventilation, a computer-readable storage medium (11), and a device. The method comprises: acquiring real-time waveform data of a subject to be detected in a mechanical ventilation process (S10); converting the acquired real-time waveform data into real-time graph structure data (S20); and inputting the real-time graph structure data into a pre-trained graph-convolutional neural network model to obtain a man-machine asynchronism type (S30). By means of converting waveform data into graph structure data in a non-Euclidean space and using a graph-convolutional neural network model to predict the man-machine asynchronism type, the method improves the data dimensions, enhances the degrees of freedom in data analysis, and extends the vision of analysis and processing, thus elevating the prediction accuracy of man-machine asynchronism type of said subject in the mechanical ventilation process.

Inventors:

XIONG FUHAI (CN)
ZHONG WEI (CN)
MA LIANG (CN)
YAN TING (CN)
LI HUIHUI (CN)
LIAO TIANZHENG (CN)
WANG LEI (CN)

Application Number:

PCT/CN2022/142445

Publication Date:

August 24, 2023

Filing Date:

December 27, 2022

Export Citation:

Click for automatic bibliography generation Help

Assignee:

SHENZHEN INST ADV TECH (CN)

International Classes:

A61M16/00

Foreign References:

CN113521460A	2021-10-22
CN113749622A	2021-12-07
CN114712643A	2022-07-08
CN113642512A	2021-11-12
US20190371460A1	2019-12-05
US20210407676A1	2021-12-30

Other References:

李瑞瑞等 (LI, RUIRUI ET AL.): "基于深度学习的机械通气患者人机不同步预警方法 (Non-official translation: A Deep Learning-Based Method for Early Warning of Human-Machine Asynchrony in Mechanically Ventilated Patients)", 2021中国自动化大会论文集 (PROCEEDINGS OF CAC2021), vol. \, no. \, 22 October 2021 (2021-10-22), pages 1 - 6

Attorney, Agent or Firm:

PURPLEVINE INTELLECTUAL PROPERTY (SHENZHEN) CO., LTD. (CN)

Download PDF:

View/Download PDF PDF Help

Previous Patent: COMMON-MODE VOLTAGE DYNAMIC MODULATION CIRCUIT AND METHOD AND D-CLASS AUDIO POWER AMPLIFIER

Next Patent: CLADDING LIGHT STRIPPER AND MANUFACTURING METHOD THEREFOR