Title:
ECG-BASED DISEASE PREDICTION METHOD, APPARATUS AND ELECTRONIC DEVICE
Document Type and Number:
WIPO Patent Application WO/2021/031151
Kind Code:
A1
Abstract:
An ECG-based disease prediction method, apparatus and electronic device. The method comprises: S100, obtaining an ECG identification unit on the basis of the ECG signal of each lead; S200, breaking down the ECG identification unit into multiple scale spaces, and correspondingly obtaining multiple wave-frequency units; S300, constructing a multi-scale spatial signal on the basis of the multiple wave-frequency units of multiple leads; S400, obtaining a disease prediction result of the ECG signals on the basis of the multi-scale spatial signal. The method solves the technical problem in the prior art of poor accuracy in predicting diseases on the basis of ECG signals when the quality of the ECG signals is poor, and achieves the technical effect of improving the accuracy of obtaining disease prediction results on the basis of multi-scale spatial signals.
Inventors:
LIU JIKUI (CN)
LI YE (CN)
MIAO FEN (CN)
WEN BO (CN)
LIU ZENGDING (CN)
LI YE (CN)
MIAO FEN (CN)
WEN BO (CN)
LIU ZENGDING (CN)
Application Number:
PCT/CN2019/101791
Publication Date:
February 25, 2021
Filing Date:
August 21, 2019
Export Citation:
Assignee:
SHENZHEN INST OF ADV TECH CAS (CN)
International Classes:
A61B5/0402
Domestic Patent References:
| WO2015164833A1 | 2015-10-29 |
Foreign References:
| CN109674464A | 2019-04-26 | |||
| CN109730672A | 2019-05-10 | |||
| CN104367317A | 2015-02-25 |
Other References:
PADHY SIBASANKAR, DANDAPAT S.: "Third-order tensor based analysis of multilead ECG for classification of myocardial infarction", BIOMEDICAL SIGNAL PROCESSING AND CONTROL, ELSEVIER, AMSTERDAM, NL, vol. 31, 1 January 2017 (2017-01-01), NL, pages 71 - 78, XP055783087, ISSN: 1746-8094, DOI: 10.1016/j.bspc.2016.07.007
Attorney, Agent or Firm:
SHENZHEN KEJIN INTELLECTUAL PROPERTY OFFICE (CN)
Download PDF: