Title:
METHOD, PROGRAM, AND DEVICE FOR TRAINING NEURAL NETWORK MODEL BASED ON ELECTROCARDIOGRAM
Document Type and Number:
WIPO Patent Application WO/2024/014821
Kind Code:
A1
Abstract:
Disclosed, according to one embodiment of the present disclosure, are a method, a program, and a device for training a neural network model based on an electrocardiogram, carried out by a computing device. The method may comprise the steps of: generating first electrocardiogram data by using an electrocardiogram simulator or a pre-trained electrocardiogram generation model; and, on the basis of the first electrocardiogram data, carrying out self-supervised learning-based first training of a neural network model which is used for determining the health status of a person.
Inventors:
KWON JOONMYOUNG (KR)
LEE BYEONGTAK (KR)
LIM SEONYU (KR)
KANG SEONMI (KR)
LEE BYEONGTAK (KR)
LIM SEONYU (KR)
KANG SEONMI (KR)
Application Number:
PCT/KR2023/009814
Publication Date:
January 18, 2024
Filing Date:
July 11, 2023
Export Citation:
Assignee:
MEDICAL AI CO LTD (KR)
International Classes:
A61B5/319; A61B5/00; G06N3/042; G06N3/08; G16H50/20
Foreign References:
CN108714026A | 2018-10-30 | |||
KR20210058676A | 2021-05-24 | |||
KR20200041697A | 2020-04-22 | |||
KR20220036292A | 2022-03-22 | |||
KR20220059711A | 2022-05-10 |
Attorney, Agent or Firm:
BEATBOARD IP LAW FIRM (KR)
Download PDF: