Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
SYSTEM AND METHOD FOR GENERATING ELECTROCARDIOGRAM ON BASIS OF DEEP LEARNING ALGORITHM
Document Type and Number:
WIPO Patent Application WO/2022/182182
Kind Code:
A1
Abstract:
The present invention relates to a system and a method for generating an electrocardiogram on the basis of a deep learning algorithm. According to the present invention, the system for generating an electrocardiogram on the basis of a deep learning algorithm comprises: a data input unit for receiving input 12-lead electrocardiograms measured by a plurality of patients; a data extraction unit for extracting training data from the input 12-lead electrocardiograms; a training unit for training characteristics of electrocardiograms by inputting the extracted training data to a plurality of training models; an electrocardiogram generation unit for receiving one or more input reference electrocardiograms from a measurement target person, and generating virtual electrocardiograms by inputting the input reference electrocardiograms to the plurality of training models for which training has been completed; and a control unit for mutually synchronizing the reference electrocardiograms and the generated virtual electrocardiograms, and outputting waveforms for the synchronized reference electrocardiograms and virtual electrocardiograms.

Inventors:
KWON JOON MYOUNG (KR)
Application Number:
PCT/KR2022/002747
Publication Date:
September 01, 2022
Filing Date:
February 24, 2022
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
MEDICALAI CO LTD (KR)
BODYFRIEND CO LTD (KR)
International Classes:
A61B5/327; A61B5/00; A61B5/332; A61B5/346
Foreign References:
KR102142841B12020-08-10
KR20060117546A2006-11-17
KR20200068161A2020-06-15
KR20190141326A2019-12-24
US20200121255A12020-04-23
KR102180135B12020-11-17
Attorney, Agent or Firm:
OH, Sung Hwan (KR)
Download PDF: