A Novel Method of Medical Classification Using Parallelization Algorithms

Abstract

Methods of machine learning in the medical field are the subject of significant ongoing research, which mainly focuses on modeling certain human actions, thought processes or disease recognition. Other applications include biomedical systems, which include genetics and DNA analysis. The purpose of this paper is the implementation of machine learning methods – Random Forest and Decision Tree, further parallelization of these algorithms to achieve greater accuracy of classification and reduce the time of training of these classifiers in the field of medical data processing, determining the presence of human cardiovascular disease. The paper conducts research using machine learning methods for data processing in medicine in order to improve the accuracy and execution time using parallelization algorithms. Classification is an important tool in today's world, where big data is used to make various decisions in government, economics, medicine, and so on. Researchers have access to vast amounts of data, and classification is one of the tools that helps them understand data and find certain patterns in it. The paper used a dataset consisting of records of 70000 patients and containing 12 attributes. Analysis and preliminary data preparation were performed. The Random Forest algorithm is parallelized using the sklearn library functional. The time required to train the model was reduced by 4.4 times when using 8 parallel streams, compared with sequential training. This algorithm is also parallelized based on CUDA. As a result, the time required to train the model was reduced by 83.4 times when using this technology on the GPU. The paper calculates the acceleration and efficiency coefficients, as well as provides a detailed comparison with a sequential algorithm.

Accelerating Ore Sintering Mathematical Model Using Gpu

“…It improves simulation realism in the case of sinter layer compressing due melting of its components. In [7] the authors implemented parallelization of learning algorithm for CPU and GPU using CUDA. They compared learning speed on different configurations and showed significant speedup with GPU configuration.…”

A New Information System for Road Surface Condition Classification Using Machine Learning Methods and Parallel Calculation

“…As a result, it was experimentally proven that execution on four threads and with a given parameter of the number of trees equal to 100 training took 77 seconds, which is twice as fast as training using only two threads. However, work [2] shows that using GPU for parallelization is 83.4 times faster than parallelization using 8 CPU threads.…”

“…Thanks to the use of motion sensors, and sensors of the internal combustion engine, it is possible to classify the type of road surface, driving style, and road traffic [1]. Target variable classification [2] based on data gathered during the vehicle movement allows to combine all of this into effective approach for fast classification to determine the condition of the road surface at a certain moment of the time of operation of the sensors and additionally geolocation of the vehicle at the same moment. There are two popular approaches to classifying the condition of a road surface: • Use of tabular data obtained while driving the car; • Use of overlay images.…”