2023, issue 4, p. 76-83
Received 20.09.2023; Revised 09.11.2023; Accepted 28.11.2023
Published 04.12.2023; First Online 05.12.2023
https://doi.org/10.34229/2707-451X.23.4.9
Previous | FULL TEXT (in Ukrainian) | Next
Algorithm for Classification of Patient Groups Based on the LDA Method
Vitalii Budnyk 1 *
, Mykola Budnyk 1,
2, 3
1 V.M. Glushkov Institute of Cybernetics of the NAS of Ukraine, Kyiv
2 Taras Shevchenko National University of Kyiv
3 Sumy State University
* Correspondence: This email address is being protected from spambots. You need JavaScript enabled to view it.
Introduction. The article is devoted to the development of the algorithm of classification of several groups of patients using the LDA method at certain stages of its work. The algorithm allows achieve high discrimination value, to work with a variety of parameters and to separate more than two groups of patients. It is used for the analysis of biomedical data, namely for the array of indicators of various nature described healthy persons and persons with the detected disease.
The purpose of paper is to develop an algorithm to increase the power of discrimination of an array of medical data that may include hundreds of healthy people and patients with connective tissue diseases, and each person is described by hundreds of parameters.
Results. The authors proposed an algorithm for increasing classification accuracy based on parameter selection using sequential multivariate LDA tests. An example of the application of the algorithm to the task of analyzing a fairly large array of data (501 individuals: 295 healthy, 206 patients, 240 parameters) and identifying informative parameters for diagnosing children with connective tissue diseases is given. As a result of the application of this algorithm, a discriminant function and a decision rule were obtained, which allows achieve an average accuracy of discrimination over the entire set of parameters of 85 %. In addition, the algorithm is applied for two separate groups of parameters - blood indicators and biochemical analysis, while the average accuracy of discrimination reaches 84 % and 90 %, respectively.
Conclusions. The algorithm of classification groups of patients with the use of LDA has been developed, which allows achieve high accuracy of discrimination. The results of its application in solving the real data set are given. The results of its application to solving the task of classification of medical data show its ability to improve classification accuracy.
Keywords: algorithm, classification, analysis, informative parameters, LDA.
Cite as: Budnyk V., Budnyk M. Algorithm for Classification of Patient Groups Based on the LDA Method. Cybernetics and Computer Technologies. 2023. 4. P. 76–83. (in Ukrainian) https://doi.org/10.34229/2707-451X.23.4.9
References
1. Medicine and health care of the modern day in the Ukraine territory. (in Ukrainian) https://vue.gov.ua/Медицина_та_охорона_здоров’я_новітньої_доби_на_теренах_України (accessed: 11.09.2023)
2. Linear discriminant analysis. (in Ukrainian) https://en.wikipedia.org/wiki/Linear_discriminant_analysis (accessed: 11.09.2023)
3. Romakin V.V. Computer analysis of data: Tutorial. Mykolayiv: Publisher Petro Mogyla MDGU, 2006. 144 p. (in Ukrainian) https://lib.chmnu.edu.ua/index.php?m=2&b=210
4. Kolmogorov – Smirnov's criterion of consistency. (in Ukrainian) https://en.wikipedia.org/wiki/Kolmogorov%E2%80%93 Smirnov_test (accessed: 11.09.2023)
5. Budnyk V.M., Oshlyanska O.A., Budnyk M.M. Detection of informative indicators for the diagnosis of connective tissue diseases in children by LDA. Book of abstracts of 3rd international sci.-pract. conference «Intellectual systems in industry and education» (ISPO-2011). 2-4.11.2011. Publisher: SumDU. Sumy. 2011. P. 19–23. (in Ukrainian) https://essuir.sumdu.edu.ua/bitstream-download/123456789/24955/1/Budnik.pdf
6. Sosnytska T.V., Budnyk V.M., Stadnyuk L.A., Moyiseenko Ye.V., Sosnytskiy V.M., Yegorova L.V., Lilyakevych A.A. Analysis of the reproducibility of magnetocardiographic parameters. Ukrainian Cardiological Journal. 2012. No. 2. P. 81–83. (in Ukrainian) https://drive.google.com/file/d/1S5epkuP0TH4p6TwLj0qfZHaOc3O04CAo/view?usp=sharing
7. Oshlyanska O.A., Omelchenko V.P., Chernyshov V.P., Galazyuk L.V. The role of nonspecific cellular immune response in the formation of autoimmunity. Perinatology and pediatrics. 2008. No. 3. P. 83–85. (in Ukrainian)
8. Oshlyanska O.A. Markers of destruction of connective tissue in congenital and acquired pathologies in children. Perinatology and pediatrics. 2009. No. 4. P. 57–61. (in Ukrainian)
9. Chernysheva D.S., Budnyk M.M. Application of discriminant analysis to MCG data processing. Computer tools, systems and networks. 2004. No. 3. P. 57–64. (in Ukrainian) http://dspace.nbuv.gov.ua/handle/123456789/6406
10. Budnyk V.M. Research and certification of biomedical information and measuring systems: dissetation of candidate of technical sciences : 05.13.06. Kyiv, 2021. 270 p. (in Ukrainian) http://irbis-nbuv.gov.ua/aref/0421U104068
ISSN 2707-451X (Online)
ISSN 2707-4501 (Print)
Previous | FULL TEXT (in Ukrainian) | Next