Parallel attribute reduction Spark method for large-scale classification of liver electronic medical records and lesions

Abstract

The invention provides a parallel attribute reduction Spark method for large-scale classification of liver electronic medical records and lesions. The method comprises the following steps: S10, reading a data set of liver electronic medical records, dividing the data set into a plurality of liver medical record data subsets, and sending the liver medical record data subsets to corresponding slavenodes; S20, performing inconsistent processing on the liver medical record data subsets, reducing inconsistent data in the liver medical record data, and then calculating an equivalence class divisionvalue of liver medical record data attributes; S30, calculating attribute importance according to data objects in the liver medical record data subsets; S40, calculating an attribute importance set of the liver medical record data subsets in the slave nodes, and performing aggregation operation to obtain an attribute importance set of the liver medical record data; and S50, calculating an attribute reduction set of the liver medical record data set, and judging whether the attribute reduction set meets reduction requirements or not. According to the attribute parallel reduction Spark method for large-scale liver electronic medical record lesion classification, the efficiency and precision of large-scale parallel reduction of liver electronic medical record attributes are effectively improved.

Description

technical field [0001] The invention relates to the technical field of medical image processing, in particular to an attribute parallel reduction Spark method for lesion classification of large-scale electronic medical records of the liver. Background technique [0002] The liver is an important organ in the human body and has a detoxification function. Its main functions are: secrete bile, promote the digestion and absorption of fat; participate in substance metabolism and maintain a constant blood sugar concentration; participate in promoting the synthesis of erythropoietin; participate in most plasma proteins and coagulation factors Synthesis; participate in blood circulation; participate in hormone metabolism, etc. Liver function test is a series of tests for checking liver function, and it is one of the most commonly used laboratory test items. Up to now, domestic and foreign scholars have proposed hundreds of liver function tests with different sensitivities and specif...

AI Technical Summary

Problems solved by technology

However, in most cases, each test can only reflect one aspect of liver function, often requiring multiple or even dozens of tests to be used together

Due to the large amount of data of liver function attribute information in the experiment, general data analysis and processing methods cannot quickly and effectively process and analyze liver attribute information

Liver examination items are the main basis for hospitals to judge whether patients have liver lesions. However, with the development of medical technology and the growing scale of hospitals, the information of liver patients in hospitals often increases exponentially, resulting in large-scale data analysis of liver electronic medical records. Long computation time and inefficiency of

Images