2023, issue 3, p. 23-43

Received 12.09.2023; Revised 23.09.2023; Accepted 26.09.2023

Published 29.09.2023; First Online 19.10.2023

https://doi.org/10.34229/2707-451X.23.3.3

Previous  |  FULL TEXT (in Ukrainian)  |  Next

 

MSC 62J05

Using the Ellipsoid Method to Study Relationships in Medical Data

Petro Stetsyuk * ORCID ID favicon Big,   Mykola Budnyk ORCID ID favicon Big,   Ivan Sen’ko ORCID ID favicon Big,   Viktor Stovba ORCID ID favicon Big,   Illia Chaikovsky

V.M. Glushkov Institute of Cybernetics of the NAS of Ukraine, Kyiv

* Correspondence: This email address is being protected from spambots. You need JavaScript enabled to view it.

 

Deterioration of moral and psychological state on the background of a full–scale war is observed in many social groups. Timely detection of various types of pre–depressive states and appropriate therapy is a critically important task nowadays. In addition, an equally important task is to identify relationships between physical and psychological indicators of health. Establishing such regularities will allow detecting anxious states, avoiding direct profile testing of a patient.

The article is devoted to construction of a mathematical apparatus for predicting psychological conclusions based on cardiological data. For this, a linear regression model and the ellipsoid method are used to determine its parameters with a criterion based on least moduli method (LMM), a feature selection procedure and a metric for assessing consistency of a data set.

Material of the article is presented in 5 sections. Section 1 describes the ellipsoid method for finding parameters of linear regression with the least moduli method as a criterion in the power of p. Problem dimensions that can be successfully solved using the ellipsoid method on modern computers are indicated.

The 2nd Section is devoted to Octave program emlmp, which implements the ellipsoid method, and the results of two computational experiments with its use. The obtained results demonstrate robustness of the obtained solutions when parameter p values are close to one.

The 3rd Section describes mechanism of variable selection for the best prediction of psychological state of patients based on cardiological data. Variable selection was carried out using the Python Sequential Feature Selector procedure for predicting two psychological indicators – Beck's anxiety scale and psychologist's formalized conclusion.

The 4th Section contains the results of a computational experiment using the emlmp program with LMM and least square method (LSM) criteria for predicting a psychologist’s formalized conclusion based on 84 selected patients and 22 parameters. Obtained solutions and forecasts for comparing criteria based on LMM and LSM are given.

In the 5th Section, a metric for evaluation consistency of a data set is proposed, which allows to evaluate consistency for each parameter separately. A linear connection was found between 4 psychological parameters and the maximum accuracy of regression models with optimal number of parameters in specified models.

 

Keywords: linear regression, convex function, ellipsoid method, least moduli method, data prediction, GNU Octave.

 

Cite as: Stetsyuk P., Budnyk M., Sen’ko I., Stovba V., Chaikovsky I. Using the Ellipsoid Method to Study Relationships in Medical Data. Cybernetics and Computer Technologies. 2023. 3. P. 23–43. (in Ukrainian) https://doi.org/10.34229/2707-451X.23.3.3

 

References

           1.     Chaikovsky І., Primin М., Kazmirchuk А. Development and implementation into medical practice new information technologies and metrics for analysis of small changes in electromagnetic field of human heart. Visnyk of the National Academy of Sciences of Ukraine. 2021. Vol. 2. P. 33–43. (in Ukrainian) https://doi.org/10.15407/visn2021.02.033

           2.     Chaikovsky I. Electrocardiogram scoring beyond the routine analysis: subtle changes matters. Expert Review of Medical Devices. 2020. 17 (5). P. 379–382. https://doi.org/10.1080/17434440.2020.1754795

           3.     Huber J. P. Robust Statistics. М.: Mir. 1984. 304 p. (in Russian)

           4.     Stetsyuk P.I., Kolesnik Y.S., Leibovich М.М. On robustness of the least moduli method. Computer Mathematics. 2002. P. 114–123. (in Russian)

           5.     Mudrov V.I., Kushko V.L. The Least Moduli Method. М.: Izdatelstvo «Znanie». 1971. 64 p. (in Russian)

           6.     Stetsyuk P.І., Stetsyuk M.G., Bragin D.О., Molodyk М.О. Using Shor’s r-algorithm in linear problems of robust optimization. Cybernetics and Computer Technologies. 2021. 1. P. 29–42. (in Ukrainian) https://doi.org/10.34229/2707–451X.21.1.3

           7.     Shor N.Z. Cut–off Method with Space Dilation for Solving Convex Optimization Problems. Cybernetics. 1977. Vol. 1. P. 94–95. (in Russian) https://doi.org/10.1007/BF01071394

           8.     Stovba V.О. The Ellipsoid Methods for Linear Regression Parameters Determination. Cybernetics and Computer Technologies. 2020. Vol. 3. P. 14–24. (in Ukrainian) https://doi.org/10.34229/2707–451X.20.3.2

           9.     Fischer A., Khomyak O., Stetsyuk P. The ellipsoid method and computational aspects. Commun. Optim. Theory. Vol. 21. 2023. P. 1–14. https://doi.org/10.1097/01.NME.0000899392.70376.a2

       10.     James G., Witten D., Hastie T., Tibshirani R., Taylor J. An Introduction to Statistical Learning with Applications in Python. New York: Springer. 2023. 613 p. https://doi.org/10.1007/978-3-031-38747-0

       11.     Zharinova V.Y., Tabakovych-Vatzeba V.О., Senko І.О. Diagnostic and prognostic possibilities of cardiotropic autoantibodies in elderly patients with coronary heart disease with different contractility of the myocardium. Ukrainian cardiological journal. 2015. Vol. 4. P. 8186. (in Ukrainian) https://ucardioj.com.ua/index.php/UJC/issue/view/29

       12.     Kumar V., Minz S. Feature selection: a literature review. SmartCR. 2014. 4 (3). P. 211229. https://doi.org/10.6029/smartcr.2014.03.007

       13.     Ferria F. J., Pudilb P., Hatefc M., Kittlerca J. Comparative Study of Techniques for Large–Scale Feature Selection. Machine Intelligence and Pattern Recognition. 1994. Vol. 16. P. 403413. https://doi.org/10.1016/B978–0–444–81892–8.50040–7

       14.     Rossum G.V., Drake F.L. Python 3 Reference Manual. Scotts Valley, CA: CreateSpace. 2009.

       15.     Harris C.R., Millman K.J., van der Walt S.J. et al. Array programming with NumPy. Nature. 2020. Vol. 585. P. 357–362. https://doi.org/10.1038/s41586–020–2649–2

       16.     McKinney W. Data structures for statistical computing in python. Proceedings of the 9th Python in Science Conference. 2010. Vol. 445. P. 5661. https://doi.org/10.25080/Majora–92bf1922–00a

       17.     Pedregosa F., Varoquaux G., Gramfort A., Michel V., Thirion B., Grisel O., Blondel M., Prettenhofer P., Weiss R., Dubourg V., Vanderplas J., Passos A., Cournapeau D., Brucher M., Perrot M., Duchesnay, E. Scikit–learn: Machine Learning in Python. Journal of Machine Learning Research. 2011. Vol. 12. P. 28252830. https://doi.org/10.5555/1953048.2078195

       18.     Google Colaboratory. https://colab.research.google.com/ (accessed: 02.10.2023)

       19.     Scikit–Learn: Sequential Feature Selection. https://scikit–learn.org/1.2/modules/feature_selection.html#sequential–feature–selection (accessed: 02.10.2023)

       20.     Liu F.T., Ting K.M., Zhou Z.-H. Isolation Forest. Eighth IEEE International Conference on Data Mining, Pisa, Italy, 2008. P. 413422. https://doi.org/10.1109/ICDM.2008.17

       21.     Liu F.T., Ting K.M., Zhou Z.–H. Isolation–Based Anomaly Detection. ACM Transactions on Knowledge Discovery from Data. 2012. Vol. 6, N 1. P. 1–39. https://doi.org/10.1145/2133360.2133363

       22.     Scikit-Learn: Isolation Forest. https://scikit–learn.org/1.2/modules/outlier_detection.html#isolation–forest (accessed: 02.10.2023)

       23.     Akoglu H. User's guide to correlation coefficients. Turk J Emerg Med. 2018. 18 (3). P. 9193. https://doi.org/10.1016/j.tjem.2018.08.001

       24.     Fuller W. A. Measurement Error Models. New York: Wiley. 1987. https://doi.org/10.1002/9780470316665

       25.     Sen’ko I.O. Consistency of an adjusted least–squares estimator in a vector linear model with measurement errors. Ukrainian mathematical journal. 2013. Vol. 64, N 11. P. 17391751. https://doi.org/10.1007/s11253–013–0748–z

       26.     Sen’ko I. The asymptotic normality of an adjusted least squares estimator in a multivariate vector errors–in–variables regression model. Theory of Probability and Mathematical Statistics. 2014. Vol. 88. P. 175190. https://doi.org/10.1090/S0094–9000–2014–00929–1

       27.     Snedecor G.W., Cochran W.G. Statistical Methods. Eighth Edition. Iowa State University Press. 1989.

       28.     Grabovetzky B.Y. Economic forecasting and planning: a study guide. Vinnytsia: VDTU. 2000. 163 p. (in Ukrainian)

       29.     Knopov P.S., Korkhin A.S. Regression Analysis Under A Priori Parameter Restrictions. Springer Optimization and Its Applications. 2013. Vol. 54. 234 p. https://doi.org/10.1007/978-1-4614-0574-0

 

 

ISSN 2707-451X (Online)

ISSN 2707-4501 (Print)

Previous  |  FULL TEXT (in Ukrainian)  |  Next

 

 

            Archive

 

© Website and Design. 2019-2024,

V.M. Glushkov Institute of Cybernetics of the NAS of Ukraine,

National Academy of Sciences of Ukraine.