Rough evidence pellet Spark method for chronic kidney disease medical record classification

A chronic kidney disease, rough technology, applied in the field of medical information intelligent processing, can solve problems such as large amount of data and many data attributes, achieve strong application value, improve classification accuracy and calculation efficiency, and improve classification accuracy and calculation efficiency.

Inactive Publication Date: 2022-08-05
NANTONG UNIVERSITY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This will lead to too many experimental test data attributes and a large amount of data, and it will also increase the difficulty for doctors to judge the pathological changes of patients with chronic kidney disease

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
  • Rough evidence pellet Spark method for chronic kidney disease medical record classification
  • Rough evidence pellet Spark method for chronic kidney disease medical record classification
  • Rough evidence pellet Spark method for chronic kidney disease medical record classification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] The present invention will be further described in detail below in conjunction with the accompanying drawings.

[0063] like figure 1 , 3 shown, a rough-evidence Granular Spark method for classification of chronic kidney disease medical records, comprising the following steps:

[0064] Step 1. On the master node Master, read the large-scale chronic kidney disease medical record data set through the Hadoop distributed file system HDFS, and then divide it into training data set S TR and the test dataset S TE , and then convert the chronic kidney disease medical record data into a four-tuple decision information system S=, the decision information system S is expressed as follows:

[0065] S=, where U={x 1 ,x 2 ,...,x M } denotes the set of patient objects in the chronic kidney disease medical record dataset, M denotes the number of chronic kidney disease patients; C={a 1 ,a 2 ,...,a n } represents the non-empty finite set of pathological attributes in chronic kid...

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 relates to the field of medical information intelligent processing, in particular to a rough evidence pellet Spark method for chronic kidney disease medical record classification. The method comprises the following steps: firstly, reading chronic kidney disease medical record data on a main node, and dividing a data set into a training set and a test set; the training subset samples are divided in parallel on the child nodes to generate a plurality of rough evidence particle balls; then obtaining a pathological attribute reduction subset of the training subsets by using a Spark parallel pathological attribute reduction method based on a rough evidence particle ball, and updating pathological attribute sets of all the training subsets and the test set; and finally, obtaining a prediction category label result of a test set sample through a Spark parallelized rough evidence particle ball neighborhood classification method. According to the method, redundant pathological attributes in the large-scale chronic kidney medical record data can be effectively removed, and the influence of redundant samples and abnormal samples on a decision-making process is reduced by utilizing rough evidence, so that the classification precision and the calculation efficiency of the large-scale chronic kidney medical record data are improved.

Description

technical field [0001] The invention relates to the field of intelligent processing of medical information, in particular to a rough evidence pellet Spark method for classifying chronic kidney disease medical records. Background technique [0002] Chronic kidney disease (CKD) refers to a variety of therapeutic factors between the internal environment and external environment of the human body that destroy the balance of the human body, resulting in the dysfunction of viscera, qi and blood, and the disease affects the kidney, causing kidney disease. . At the same time, there are many types of complications caused by chronic kidney disease. Doctors cannot effectively and accurately determine whether a patient has chronic kidney disease only by relying on the patient's physical signs. At present, most of the methods for judging the pathological status of chronic kidney disease are to analyze information such as hematuria, proteinuria, and hypertension. However, the experiment ...

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): G06F16/35G16H10/60G06K9/62
CPCG06F16/35G16H10/60G06F18/214
Inventor 丁卫平李铭陈嘉懿孙颖沈鑫杰秦廷桢鞠恒荣黄嘉爽王海鹏高自强董佳俊
Owner NANTONG UNIVERSITY
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