Research in machine learning methods for solving problems of the medical profile
DOI:
https://doi.org/10.34185/1562-9945-3-146-2023-12Keywords:
algorithms, classifier, machine learning, disease diagnosis, random forest, nearest neighbor method, multilayer perceptron, logistic regression, gradient boosting, decision treeAbstract
The work is devoted to the study of machine learning methods for solving medical problems. The aim of the work is to analyze machine learning methods to improve the accuracy and reduce the time for diagnosing diseases of the genitourinary system in children. The object of research is machine learning methods. The subject of the study is a classifier of diseases of the genitourinary system of patients of the Dnipropetrovsk Re-gional Children's Clinical Hospital "Dnepropetrovsk Regional Council". As a result of the study, the following tasks were solved: an analysis of the literature on the applica-tion of machine learning methods to diseases of the genitourinary system was made; a program was developed to extract the necessary information on statements in a semi-automatic mode; Python libraries and part of machine learning methods were analyzed; primary analysis and processing of data was carried out; applied methods of classifica-tion, feature selection and filling in missing values; the obtained results were analyzed and the substantiation of the research results in the subject area was made.
References
Mintser O.P. Obroblennia klinichnykh i eksperymentalnykh danykh u medytsyni: navch. posibnyk / O.P. Mintser, Yu.V. Voronenko, V.V. Vlasov - K.: Vyshcha shk., 2003. - 350 s.
Kobzar A.Y. Prykladnaia matematycheskaia statystyka. – M.: Fyzmatlyt, 2006. – 626–628 s.
Kokhonen T. Samoorhanyzuiushchyesia karti / per. 3-ho anhl. yzd. – M.: BYNOM. Laboratoryia znanyi, 2014. – 655 s.
Holovanova I.A. Osnovy medychnoi statystyky: navch. posib. dlia aspirantiv ta klinichnykh ordynatoriv / I.A. Holovanova, I.V. Bielikova, N.O. Liakhova. – Poltava, 2017. – 113 s.
Fadeev P.A. Bolezny pochek. Pyelonefryt. – M.: Myr y Obrazovanye, 2011. – 180 s.
Flakh P. Mashynnoe obuchenye. Nauka y yskusstvo postroenyia alhorytmov, ko-torыe yzvlekaiut znanyia yz dannыkh / per. s anhl. A.A. Slynkyna. – M.: DMK Press, 2015. – 400 s.
Khaikyn S. Neironnie sety: Polnii kurs / per. s anhl. N.N. Kussul, A.Iu. She-lestova. – 2-e yzd., yspr. – M.: Yzdatelskyi dom Vyliams, 2008. – 1103 s.
Bauer E. An Empirical Comparison of Voting Classification Algorithms: Bagging, Boosting, and Variants / E. Bauer, R. Kohavi // Machine Learning. – 1999. –
P. 105–139.
Boughorbel S. Optimal classifier for imbalanced data using Matthews Correlation Coefficient metric / S. Boughorbel, F. Jarray, M. El-Anbari // PLoS ONE 12(6). –
– 17 p.
Breiman L. Bagging Predictors / L. Breiman // Machine Learning. – 1996. –
P. 123–140.
D’Agostino R.B. An omnibus test of normality for moderate and large sample size / R.B. D’Agostino // Biometrika. – 1971. – Vol. 58, No. 2. – P. 341–348.
Gopika S. Machine learning Approach of Chronic Kidney Disease Prediction us-ing Clustering Technique / S. Gopika, Dr.M. Vanitha // International Journal of In-novative Research in Science, Engineering and Technology. – 2017. – Vol. 6, No. 7. – P. 14488–14496.
Hornik K. Approximation Capabilities of Muitilayer Feedforward Networks / K. Hornik // Neural Networks. – 1990. – Vol. 4. – P. 251–257.
Kazemi Y. A novel method for predicting kidney stone type using ensemble learning / Y. Kazemi, S.A. Mirroshandel // Artificial Intelligence in Medicine. – 2017. – Vol. 79, No. 3. – P. 1696–1707.
Lambodar J. Distributed Data Mining Classification Algorithms for Prediction of Chronic Kidney Disease / J. Lambodar, K. Narendra // International Journal of Emerging Research in Management and Technology. – 2015. – Vol. 4, No. 11. –
P. 110–180.
Ramya S. Diagnosis of Chronic Kidney Disease Using Machine Learning Algo-rithms / S. Ramya, N. Radha // International Journal of Innovative Research in Com-puter and Communication Engineering. – 2016. – Vol. 4, No. 1. – P. 812–820.
Scott D.W. On Optimal and Data-Based Histograms / D.W. Scott // Biometrika. – 1979. – Vol. 66, No. 3. – P. 605–610.
United States Patent № US 7,657,521 B2, 02.02.2010. System and method for parsing medical data [text] / Fred E. Masarie, Stuart Lopez, Michael I. Lieberman // United States Patent № US 7657521 B2. 2010.
Yoruk U. Automatic Renal Segmentation for MR Urography Using 3D-GrabCut and Random Forests / U. Yoruk, B.A. Hargreaves, S.S. Vasanawala // International Society for Magnetic Resonance in Medicine. – 2017. – Vol. 79, No. 3. –
P. 1696–1707.
