Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Machine learning based human disease detection methods and detection product

A technology of machine learning and disease detection, applied in neural learning methods, instruments, sensors, etc., to achieve performance improvement, high accuracy, and rich data feature information

Inactive Publication Date: 2019-08-06
河北默代健康科技有限公司
View PDF9 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The detection method of the human disease provided by the present invention solves the technical problems of the model processing method of the continuous dynamic signal of the cardiac electrical activity, the model analysis of the data feature quantification and the auxiliary diagnosis of the human disease, etc.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Machine learning based human disease detection methods and detection product
  • Machine learning based human disease detection methods and detection product
  • Machine learning based human disease detection methods and detection product

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] Example 1. Sample set construction and preprocessing of sample data

[0045] 1. Establishment of sample set

[0046] The sample set data used for the machine learning decision model is constructed, and the specific construction method is as follows:

[0047] (1) The composition of the sample set: n clinically known healthy individuals (n>1000) and m clinically known individuals with a certain human disease (m>1000) are included as the sample population; sample populations related to specific human diseases are collected The relevant eigenvector data of is used as the sample set data.

[0048] (2) Setting of sample labels: The index data of the gold standard indicators of human diseases and the expert consensus are used as the labels of the sample data.

[0049] 2. Preprocessing of sample data

[0050] After obtaining the aforementioned sample set data, perform preprocessing on the sample set data: perform preprocessing such as filtering or batch normalization on the ...

Embodiment 2

[0051] Example 2. Acquisition of multiple data feature quantification index data related to attributes of specific human diseases

[0052] After obtaining the sample set data preprocessed in Example 1, the quantitative index data of the data characteristics of the attributes related to specific human diseases are obtained. The quantitative index data of data characteristics related to attributes of specific human diseases include quantitative index data of ECG vector data characteristics, etc.; the specific operation process is carried out in accordance with the following steps: (1) Acquisition of quantitative index data of ECG vector data characteristics and corresponding human body Disease Threshold Judgment Criteria

[0053] The quantitative index data of ECG vector data features include but not limited to the quantitative index data of geometric features, and / or the quantitative index data of nonlinear dynamic features, and / or the quantitative index data of model features,...

Embodiment 3

[0140] Example 3. Construction and training of machine learning models for various data feature quantification index data of specific human disease-related attributes

[0141] This embodiment is to carry out further research on the basis of embodiment 2. This embodiment is mainly to construct and train the machine learning model of specific human diseases, and then input the preprocessed specific human disease-related attributes obtained in embodiment 2 A variety of data features quantify index data to train and optimize the machine learning model for specific human diseases.

[0142] (1) Constructing a machine learning judgment model for specific human diseases

[0143] Using the multiple data feature quantification index data of specific human disease-related attributes obtained in Example 2 as input data, carry out machine learning, build a machine learning model adapted to specific human disease, and realize the quantitative index data of each kind of ECG vector data featu...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides machine learning based human disease detection methods and a detection product. The method includes extracting the intrinsic data characteristics of electrocardial vector data,and quantitative index data thereof; constructing a machine learning classification model of the electrocardial vector data characteristics; and assigning corresponding weight values to different classification results identified by the model so that the comprehensive judgment results of human disease detection can be obtained. According to the provided detection method, the technical problems ofthe model processing of electrocardial continuous dynamic signals, the modeling analysis of quantitative data of data characteristics and the auxiliary diagnosis of human diseases can be solved. The detection methods and detection product can improve the accuracy and detection efficiency of human disease detection; and diagnosis effects can be enhanced with the increasing of the quantitative information of the electrocardial vector data characteristics expanded into a database.

Description

technical field [0001] The invention relates to the field of detection of human diseases, in particular to a detection method and detection products for human diseases based on machine learning. Background technique [0002] When external pathogenic factors act on human cells, reaching a certain amount of damage will cause damage to human cells, and then the disorder of human organ function, metabolism and morphological structure will occur, eventually leading to the formation of human diseases. However, when some patients suffer from major recessive diseases of the human body, there are no obvious clinical symptoms. Therefore, it is necessary to develop an assessment method for human disease risk, which can mine the potential pathological information of human bioelectrical signals, so as to fully assess the health status of patients at various stages such as risk and prognosis before onset and after treatment. [0003] At present, the existing technology has made some prog...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): A61B5/0402A61B5/0452G06K9/00G06N3/04G06N3/08
CPCG06N3/08A61B5/349A61B5/318G06N3/045G06F2218/08G06F2218/12A61B5/7267
Inventor 徐赤坤李伟王云霞何毅钒
Owner 河北默代健康科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com