Machine Learning Intelligent Medical Algorithm Based on Computer Vision and Parallel Optimization of Biomedical Information System

Authors

  • Huayong Yang Department of Information Engineering, Wuhan City College, Wuhan 430083, Hubei, China
  • Xiaoli Lin School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan 430065, Hubei, China

Abstract

With the development of computer technology, there is a huge conflict between information office and traditional office mode. Using efficient machine learning algorithm for scientific analysis and processing of data is an urgent need in various fields. Although the informatization process in the medical field has been advancing, the related research results are not ideal. This paper aims to process and analyze biomedical information efficiently, provide scientific basis for medical diagnosis, and improve the efficiency of medical diagnosis. Firstly, this paper divides the functions of medical information system from the perspective of computer technology and hospital information management, and designs different functional modules. Then the ER model database is used to build the entity model of each sub database of the system. In order to improve the classification
accuracy of high-dimensional data and large-scale data, this paper optimizes the data feature dimension reduction of random forest algorithm, and reduces the dimension of training data set according to the importance of feature variables. The improved random classification algorithm is further optimized in parallel in Apache Spark cloud computing platform, and a parallel random forest algorithm based on parallel Apache Spark is proposed. The proposed distributed parallel random forest algorithm (PRF) is compared with the traditional random forest algorithm RF and DRF in classification accuracy. The highest classification accuracy of PRF algorithm is 0.93 when the number of decision trees is 1500, and the highest classification accuracy is 0.93 when the data size is 1000. When the data volume of data set B is 0.5gb, the execution time of the system is only 18.9s. This shows that the system has shorter execution time and better performance. After using the system, the waiting time of patients in ENT, dermatology, Radiology, pediatrics and oncology increased by 37.93%, 52%, 51.61%, 46.15% and 53.13% respectively, which shows that the use of the system can effectively accelerate the waiting time of patients. 49% of the patients thought that the waiting time was very short, and 72% of the medical staff were very satisfied with the system. This shows that the machine learning intelligent medical algorithm based on computer vision and its biomedical information system are worth promoting.

Keywords: Computer Vision, Machine Learning, Intelligent Medical Algorithm, Biomedical Information System, System Optimization

Cite As

H. Yang, X. Lin, "Machine Learning Intelligent Medical Algorithm Based on Computer Vision and Parallel
Optimization of Biomedical Information System", vol. 30 no. 5, pp. 387-398, 2022.





Downloads

Published

2022-09-01

Issue

Vol. 30 No. 5 (2022): International Journal of Engineering Intelligent Systems

Section

General Submission

License

The submission of a paper implies that, if accepted for publication, it will not be published elsewhere in the same form, in any language, without the prior consent of the publisher. Before publication, authors are requested to assign copyright to CRL Publishing Ltd. This allows CRL to sanction photocopying, and to authorize the reprinting of issues or volumes according to demand. Authors' traditional rights will not be jeopardized by assigning Copyright in this way, as they retain the right to reuse the material following publication, and to veto third-party publication.