Chronic obstructive pulmonary disease testing system based on machine learning

A chronic obstructive pulmonary disease, machine learning technology, applied in the fields of instrumentation, informatics, medical informatics, etc., can solve the problem that the chronic obstructive pulmonary disease test system has not yet appeared, and achieve the effect of strong reliability and high test accuracy

Active Publication Date: 2017-06-27
SHANDONG NORMAL UNIV
View PDF4 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in practice, it is found that COPD patients with similar physical and chemical indicators above have different clinical manifestations, different pathological changes, different airway inflammation and systemic inflammatory status, different qu

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
  • Chronic obstructive pulmonary disease testing system based on machine learning
  • Chronic obstructive pulmonary disease testing system based on machine learning
  • Chronic obstructive pulmonary disease testing system based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] A chronic obstructive pulmonary disease testing system based on machine learning, comprising: a lung function detection device, used to obtain the subject's lung function detection items and their measured values; a processor, connected to the lung function detection device, with A principal component characteristic analysis module, a decision tree building module and a decision tree testing module; a display unit, connected with the processor, for outputting the result of the processor;

[0039] The principal component feature analysis module establishes a first sample corresponding to the measurement value of the subject's lung function, performs factor analysis on the first sample, and obtains several parameters based on the test item of the subject's lung function. Principal component features, establish a sample set corresponding to several principal component features as the second sample;

[0040] The decision tree construction module, taking information gain as ...

Embodiment 2

[0073] Example 2: In order to verify the robustness and reliability of the model, we randomly extracted the variable smoking as 0, that is, 48 ​​lung function data without smoking history, and adopted a machine learning-based chronic obstructive pulmonary disease test of the present invention The system converts 54 variables into 13 variables FAC1-FAC13 according to the principal component scoring coefficient matrix obtained by factor analysis, and imports the optimized decision tree model for prediction. The result shows that 6 people suffer from COPD. Compared with the real situation (also Only 6 people suffer from COPD), and it is found that 5 of them are all predicting correctly, with an accuracy of 83%, and the results are not lower than the predictable range of the model. The test shows that the decision tree model has certain reliability and robustness, which is quite satisfactory.

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 chronic obstructive pulmonary disease testing system based on machine learning. The system comprises a lung function detector, a processor and a display unit; the lung function detector is used for obtaining function detection items of lungs of a person to be tested and measurement values of the items; the processor is connected with the lung function detector and comprises a main component feature analysis module, a decision tree construction module and a decision tree testing module; the display unit is connected with the processor and used for outputting results of the processor; the chronic obstructive pulmonary disease testing system based on the machine learning is based on a machine learning model based on a decision tree, a relationship between a chronic obstructive pulmonary disease and all physical signs of lungs of a patient is established, and the system has the advantages of being high in testing accuracy, strong in reliability and more stable.

Description

technical field [0001] The invention relates to the field of medical data mining, in particular to a chronic obstructive pulmonary disease testing system constructed by using a machine learning method. Background technique [0002] Airflow limitation is the most basic feature of chronic obstructive pulmonary disease (COPD). Pulmonary function tests are of great significance in assessing the degree of airflow limitation, and are the most widely used and most reproducible routine tests for COPD patients. At present, there is no published technical information on the COPD testing system based on the relationship between the physiological indicators of lung function and the degree of airflow limitation. At present, it is usually determined by the forced expiratory volume in one second (FEV1) and the ratio of FEV1 to forced vital capacity (FVC) (FEV1 / FVC). In addition, the second maximum expiratory flow-volume curve (MEFV), peak expiratory flow (PEF), ratio of residual volume (...

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
IPC IPC(8): G06F19/00G06K9/62
CPCG16H50/20G06F18/2135G06F18/24323
Inventor 王红于晓梅闫晓燕马孝斌张丽晓李扬胡晓红何天文狄瑞彤孟广婷周莹房有丽姜玉丽张伟
Owner SHANDONG NORMAL UNIV
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