Prediction of development of severe forms of endometriosis in women of reproductive age

Prediction of development of severe forms of endometriosis in women of reproductive age DOI: https://doi.org/10.18370/2309-4117.2018.39.34-37Keywords: endometriosis, prevention, predictionAbstract The article describes the algorithm for predicting the development of severe forms of endometriosis and a mathematical model for predicting the severity of this pathology, used for the identification of risk groups and the timely conduct of preventive measures. The application of this method makes it possible to predict not only the fact of the pathology occurrence, but also the degree of probability of its occurrence. 123 women of reproductive age were examined: 79 with severe forms of endometriosis and 44 healthy women. The method of step-by-step discriminant analysis has identified 8 of the 65 factors that most affected the occurrence of severe form of endometriosis: the chronic stress, especially in puberty, unfavorable ecological conditions of residence, early menarche, manifestations of dysmenorrhea, gastrointestinal tract diseases, abortions in anamnesis, surgical interventions and inflammatory diseases of the reproductive system. Sensitivity of the prediction algorithm for severe endometriosis in the research retrospective sample was 89.87%: out of 79 women with endometriosis 71 cases of its severe form were predicted with high or moderate probability. Accuracy for a high-risk group of severe endometriosis was 94.1%, mean form – 84.8%, and overall system accuracy was 83.75%: out of 80 women with severe or moderate probability of severe endometriosis it was actually observed in 67. Out of 43 patients whose endometriosis was not predicted, in 39 it did not really exist, i. e. for the low-risk group the accuracy of the prediction was 90.69%. Of the 87 women in the control group who were diagnosed with severe endometriosis, 80 (91.95%), according to the forecast, expected its occurrence with high or moderate probability, which confirms the high sensitivity of the prognostic system. The developed algorithm and the mathematical model of prediction of a severe form of endometriosis are highly informative and provide the opportunity to form risk groups of disease developing, taking into account the degree of its occurrence probability for the prior conduct of individualized preventive measures. References - Zakharenko, N.F., Tatarchuk, T.F., Kovalenko, N.V. “The role of oxidative stress in the genesis of endometriosis.” Reproductive endocrinology 4 (2014): 13–16. - Kim, J.-O., Mueller, Ch.U., Klekka, U.R., et al. Factorial, discriminant and cluster analysis: Trans. from Eng. Ed. by I.S. Enukov. Moscow. Finance and Statistics (1989): 215 p. - Miner, O.P., Moskalenko, V.Z., Veselyi, S.V. Information technology in surgery. Kyiv. High school (2004): 109–73. Downloads Published How to Cite Issue Section License Copyright (c) 2018 Н. Ф. Захаренко This work is licensed under a Creative Commons Attribution 4.0 International License. Authors who publish with this journal agree to the following terms: - Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal. - Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.