OPTIMIZATION OF PREDICTION OF THE DEVELOPMENT OF MORPHOLOGICAL DISORDERS AFTER EXPERIMENTAL ACUTE ISCHEMIA-REPERFUSION BASED ON COMBINED CHANGES IN BIOCHEMICAL PARAMETERS BY MEANS OF CORRELATION ANALYSIS AND NEURAL NETWORK CLUSTERING

Authors

DOI:

https://doi.org/10.11603/mie.1996-1960.2019.4.11017

Keywords:

acute ischemia-reperfusion, morphological changes, correlation analysis, neural network clustering.

Abstract

Background. The study proposes a method for optimizing the prediction of the development of ischemic disorders by experimental acute ischemia-reperfusion based on combined changes in biochemical parameters. The approach is based on the calculation of correlation coefficients and the use of neural network clustering.

The aim of the study is to propose a method for optimizing the prediction of the severity of morphological disorders in the early reperfusion period after experimental acute ischemia-reperfusion based on combined changes in biochemical parameters by means of correlation analysis and neural network clustering.

Materials and Methods. The experimental model of ischemic-reperfusion lesion is represented by five groups of rats with reperfusion terms of 1 and 2 hours, 1 day, 7 and 14 days (18 animals in each group). The control group consisted of 15 animals. Acute ischemia was caused by the imposition of SWAT rubber bundles on the hind limbs of rats for 2 h under thiopental sodium anesthesia. Histological and morphometric examination of skeletal muscle was conducted at the Department of Pathological Anatomy with the section course and forensic medicine of the I. Gorbachevsky Ternopil National Medical University by conventional methods. Statistical data processing with calculating of Mann-Whitney's U-criterion and Spearman's correlation coefficient was performed using the Microsoft Excel (2010) software package according to conventional methods. For a deeper analysis and clustering of the study groups, in order to optimize the prognosis of ischemia-reperfusion lesions, a neural network approach was used by using the Neuro XL Classifier add-in for Microsoft Excel.

Results and Conclusions. By means of correlation analysis, the average strength of the direct correlation between the indicators of the average area of muscle fibers and the indices of alanine aminotransferase (+0,5) and aspartate aminotransferase (+0,5) is revealed, which indicates the predominance of catabolism processes in ischemic muscle tissue. According to neural network clustering the greatest prognostic value for the detection of severity of morphological disorders in the early reperfusion period have the combined changes in creatinine and alanine aminotransferase levels.

References

Mintser, O. P., Zaliskyi, V. M. (2019). Transformuvannia znan z aterohenezu: vykorystannia nanoasotsiiovanykh biotekhnolohii i merezhevoho analizu. [Transformation of knowledge of atherogenesis: the use of nano-associated bio-technologies and network analysis]. Medychna informatyka ta inzheneriia. 1, 4 24.

Selskyy, P. R., Vakulenko, D. V., Televiak, A. T., Veresiuk, T. O. (2018). On an algorithm for decision-making for the optimization of disease prediction at the primary health care level using neural network clustering. Family Medicine & Primary Care Review, 20 (2), 171-5. DOI: https://doi.org/10.5114/fmpcr.2018.76463

Epstein, R. M., Franks, P., Fiscella, K., Shields, C. G., Meldrum, S. C, Kravitz, R. L., Duberstein, P. R. (2005). Measuring patient-centered communication in patient-physician consultations: theoretical and practical issues Soc. Sci. Med., 61, 1516-28. DOI: https://doi.org/10.1016/j.socscimed.2005.02.001

Eastridge, B. J., Mabry, R. L, Seguin, P, Cantrell, J. et al. (2012). Death on the battlefield (2001-2011): implications for the future of combat casualty care. J. Truma Acute Care Surg., 73, 431-7. DOI: https://doi.org/10.1097/TA.0b013e3182755dcc

Wu, M. Y., Yiang G. T., Liao, W. T. et al. (2018). Current Mechanistic Concepts in Ischemia and Reperfusion Injury. Cell Physiol. Biochem., 46, 1650-67. DOI: https://doi.org/10.1159/000489241

Garcia-de-la-Asuncion, J., Perez-Solaz, A., et al. (2013). Different oxidative stress marker levels in blood from the operated knee or the antecubital vein in patients undergoing knee surgery: a tourniquet-induced ischemia-reperfusion model. Redox Report., Vol. 17 (5), 194-9.

Khomenko, I. P., Korol, S. O., Matviichuk, B. V. (2018). Klinichno-orhanizatsiini osoblyvosti nadannia travmatolohichnoi dopomohy poranenym iz defektamy miakykh tkanyn pry vohnepalnykh ta minno-vybukhovykh ushkodzhenniakh kintsivok. [Clinical and organizational peculiarities of traumatological care for the injured with soft tissue defects in inflammatory and mine-explosive injuries of the extremities]. Travma, 19 (5), 125-9. [In Ukrainian].

Hubka, V. O., Konovalenko, I. A., Suzdalenko, O. V. (2015). Rezultaty likuvannia khvorykh iz hostroiu arterialnoiu ishemiieiu kintsivok. [Results of treatment of patients with acute arterial ischemia of extremities]. Patolohiia, 2 (34), 55-8. [In Ukrainian].

Gillani, S., Cao, J. , Suzuki, T., Hak, D. J. (2012). The effect of ischemia reperfusion injury on skeletal muscle. Hak. Injury, 43 (6), 670-5. DOI: https://doi.org/10.1016/j.injury.2011.03.008

Horalskyi, L. P., Khomych, V. T., Kononskyi, O. I. (2011). Osnovy histolohichnoi tekhniky i morfofunktsionalni metody doslidzhen u normi ta pry patolohii. [Fundamentals of histological technique and morphofunctional methods of research in normal and pathology]. Polissia, Zhytomyr: 288. [In Ukrainian].

Bishop, C. M. (1995) Neural Networks for Pattern Recognition. Oxford: Oxford University Press., 504.

Du, K. L. (2010). Clustering: A neural network approach. Neural network,, 23 (1), 89-107. DOI: https://doi.org/10.1016/j.neunet.2009.08.007

Published

2020-06-04

How to Cite

Selskyy, P. R., Televiak, A. T., Veresiuk, T. O., & Selskyy, B. P. . (2020). OPTIMIZATION OF PREDICTION OF THE DEVELOPMENT OF MORPHOLOGICAL DISORDERS AFTER EXPERIMENTAL ACUTE ISCHEMIA-REPERFUSION BASED ON COMBINED CHANGES IN BIOCHEMICAL PARAMETERS BY MEANS OF CORRELATION ANALYSIS AND NEURAL NETWORK CLUSTERING. Medical Informatics and Engineering, (4), 40–45. https://doi.org/10.11603/mie.1996-1960.2019.4.11017

Issue

Section

Articles