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

Auxiliary system and method for diagnosing chronic obstructive pulmonary disease based on support vector machine

A chronic obstructive pulmonary disease and support vector machine technology, applied in computer-aided medical procedures, medical automated diagnosis, computer components, etc., can solve problems such as COPD multi-dimensional feature extraction system has not yet appeared, so as to improve the accuracy of pattern classification and reduce the cost of treatment Cost, the effect of ensuring real-time performance

Inactive Publication Date: 2018-09-28
SHANDONG NORMAL UNIV
View PDF2 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, based on data mining and machine learning related theories, a multi-dimensional feature extraction system for COPD based on pathological symptoms and physiological indicators of lung function has not yet appeared.

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
  • Auxiliary system and method for diagnosing chronic obstructive pulmonary disease based on support vector machine
  • Auxiliary system and method for diagnosing chronic obstructive pulmonary disease based on support vector machine
  • Auxiliary system and method for diagnosing chronic obstructive pulmonary disease based on support vector machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] In a typical implementation of the present application, such as figure 1 As shown, a support vector machine-based chronic obstructive pulmonary disease diagnostic assistance system is provided, the system includes a multi-feature input device for obtaining the subject's lung function detection items and their measured values; the processor, and multiple The feature input device is connected with a data preprocessing module, a multidimensional feature selection module, a support vector machine building module, a support vector machine parameter optimization module and a support vector machine model testing module; an output module is connected with the processor for outputting the processor structure .

[0053] The data preprocessing module is used for processing the measurement values ​​of the subject's pulmonary function testing items. It is mainly to clean the noisy data and missing data, and perform data conversion on some feature attributes, so that the original da...

Embodiment 2

[0093]The data used in this embodiment include the lung function test reports of 1,200 patients in total, and there are 26 lung physiological indicators that need to be tested for each patient, as shown in Table 1. The dataset contains 1200 samples belonging to two different classes, with a total of 750 COPD patients (62.5%) and 450 (37.5%) non-COPD patients but with similar symptoms to COPD patients.

[0094] Table 1 Pulmonary function test data

[0095]

[0096]

[0097] The purpose of this embodiment is to provide a support vector machine-based COPD diagnosis aid method, the steps of the method comprising:

[0098] (1) Perform data processing on the acquired 1200 sample data

[0099] Step 1: Screen the original data. The test number, hospitalization number, name, race, and department in the data have nothing to do with the present invention, and are not required data, so they are directly deleted;

[0100] The second step: fill in the data and fill in the missing va...

Embodiment 3

[0129] To verify the robustness and reliability of the model, we use public datasets for validation. The data set has 1020 experimenters, including 600 COPD patients and 420 non-COPD patients. Among them, 35 items of lung physiological indicators that need to be detected for each patient are obtained. The purpose of this embodiment is to provide a kind of support vector machine-based chronic obstructive pulmonary disease diagnosis auxiliary method, this method comprises:

[0130] (1) Preprocess the original 1020 experimental data; first, convert the categorical attributes into digital data items, and we use numerical values ​​to represent each categorical value, for example, smoking is represented by 1, and non-smoking is represented by 0; secondly, For the original missing data such as cough and mMRC, 20 and 36 missing values ​​were filled by the experimenter's nearest neighbors;

[0131] (2) Perform high-dimensional feature selection on the preprocessed data set, and reduc...

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 an auxiliary system and method for diagnosing the chronic obstructive pulmonary disease based on a support vector machine. The system comprises a multi-feature input unit and aprocessor, and the processor is provided with a multi-dimensional feature selection module, a support vector machine establishment module and a support vector machine model testing module; the multi-dimensional feature selection module establishes a first sample, the first sample is subjected to feature dimension reduction through a maximum dependence degree algorithm based on a rough set, multiple main feature sub-sets are obtained, and a sample set composed of the main feature sub-sets is established and used as a second sample; the support vector machine establishment module establishes asupport vector machine model; the support vector machine model testing module divides the second sample into a training set and a prediction set randomly, a trainer is generated, and whether or not the second sample obtained through dimension reduction expresses into the chronic obstructive pulmonary disease is predicted according to the support vector machine model. According to the auxiliary system and method, based on the support vector machine model, the relation between the chronic obstructive pulmonary disease and all physiological indexes of a patient is established, and the testing accuracy degree is high.

Description

technical field [0001] The invention relates to the field of medical data mining, and specifically uses a support vector machine method to construct a support vector machine-based chronic obstructive pulmonary disease diagnosis auxiliary system and method. Background technique [0002] Chronic obstructive pulmonary disease (COPD) is a disease that can lead to a gradual decline in the respiratory function of patients. It has become the fourth leading cause of death in the world. There are currently more than 170 million COPD patients in the world. Diagnosis of COPD is of great significance. The development of COPD is a gradual process: in the early stage, the symptoms of COPD are not obvious, mainly cough and sputum, which are not easy for the patient to detect, and it is the best time for treatment; in the middle stage, as the condition worsens, the patient may have dyspnea after exercise In the advanced stage, complications such as cor pulmonale and respiratory failure may...

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): G16H50/20G06K9/46G06K9/62G16H50/30
CPCG16H50/20G16H50/30G06V10/40G06F18/2411
Inventor 王红房有丽狄瑞彤周莹王露潼刘海燕王倩宋永强
Owner SHANDONG NORMAL UNIV
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