Heart disease predicting method based on Bagging-Fuzzy-GBDT algorithm

A prediction method and heart disease technology, applied in the field of medical data analysis, can solve problems such as blank research, and achieve the effects of avoiding overfitting, improving generalization, and reducing variance

Active Publication Date: 2019-09-20
东北大学秦皇岛分校
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the research on the application of GBDT and its related algorithms in the field of heart disease prediction is still blank

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
  • Heart disease predicting method based on Bagging-Fuzzy-GBDT algorithm
  • Heart disease predicting method based on Bagging-Fuzzy-GBDT algorithm
  • Heart disease predicting method based on Bagging-Fuzzy-GBDT algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0047] Such as figure 1 Shown, the present invention proposes a kind of heart disease prediction method based on Bagging-Fuzzy-GBDT algorithm, comprises the following steps:

[0048] S1. The open source heart disease data set from UCI is used as the original data, and after preprocessing, it is used as the training set D of the algorithm, with a size of N; preprocessing includes normalizing the open source heart disease data set, deleting outliers and nulls value.

[0049] S2. According to the value range of the attribute in the heart disease data set, attribute A with a relatively large value range change i Take it out, and use the triangular membership function in fuzzy logic to fuzzify it.

[0050] S3. Set the number of times of sampling to be replaced m, sample the training set D for m times, and form a new sub-training set D f...

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 discloses a heart disease predicting method based on a Bagging-Fuzzy-GBDT algorithm. The hart disease predicting method comprises the steps of according to characteristics of patient heart disease data, extracting attributes with a large value range change in the data, and fuzzifying the data by means of a fuzzy logic; combining the fuzzified data with a GBDT algorithm, and forming a Fuzzy-GBDT heat disease predicting algorithm; and finally improving data diversity by means of a Bagging algorithm through m times of sampling with replacement, and combining the Bagging algorithm with the Fuzzy-GBDT algorithm for presenting the heart disease predicting algorithm based on the Bagging-Fuzzy-GBDT algorithm. The heart disease predicting method has advantages of reducing variance of the Fuzzy-GBDT predicting algorithm, improving data diversity, preventing over-fitting of a single point, realizing high generalization of the predicting algorithm, and improving accuracy of the predicting algorithm. (4) The heart disease predicting method realizes performance evaluation through an experiment. A result proves a fact that the heart disease predicting algorithm based on the Bagging-Fuzzy-GBDT algorithm has relatively high accuracy and high generalization.

Description

technical field [0001] The invention belongs to the technical field of medical data analysis, and in particular relates to a heart disease prediction method based on a Bagging-Fuzzy-GBDT algorithm. Background technique [0002] The increase in the incidence of chronic diseases has seriously affected people's lives, caused huge economic losses, and seriously hindered the development of national medical and health services. The high morbidity and high mortality of heart disease among chronic diseases must be paid close attention to. According to the statistics of the World Health Organization, one-third of the world's population dies of heart disease. At present, my country's population is aging seriously, and the number of people suffering from heart disease is gradually increasing. Although most heart diseases cannot be completely cured, we can provide health guidance and intervention before the onset of disease through disease prediction algorithms based on real-time healt...

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): G16H50/30G16H50/20G06K9/62
CPCG16H50/30G16H50/20G06F18/2148G06F18/24G06F18/259G06F18/254
Inventor 袁晓铭王雪韩建超刘杰民陈海宴刘志刚
Owner 东北大学秦皇岛分校
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap