The use of artificial intelligence to diagnose diseases and predict their outcomes in newborns

   In recent years, modern models of artificial intelligence, including neural networks, have been successfully introduced into clinical practice, due to the high accuracy of functioning and the prospects of their use for the diagnosis and prediction of various diseases.

   Purpose. To improve the processes of predicting and diagnosing diseases and their outcomes in newborns using neural network intelligent technologies.

   Material and methods. The study is based on statistically reliable collection of patient history data, mathematical analysis, fuzzy logic theory and principles of trainable neural network systems.

   Results. Neural network programs have been developed to predict the course of posthypoxic disorders of the cardiovascular system in newborns; to determine the probability of occurrence and outcomes in newborns of such significant diseases as cerebral leukomalacia, intracranial hemorrhages, hydrocephalus, necrotizing enterocolitis, bronchopulmonary dysplasia, retinopathy of prematurity, early anemia of prematurity; to predict the physical and neuropsychiatric development of a child to age of one year; and also to predict an unfavorable outcome (death or disability with persistent health problems) of children born earlier than 32 weeks of gestation.

   Conclusion. The developed artificial neural network programs can be used for personification of the therapeutic and diagnostic process and nursing of newborns, including very preterm ones.

1. Vyucheyskaya M.V., Krainova I.N., Gribanov A.V. Neural network technologies in the diagnosis of diseases (review). Zhurnal mediko-biologicheskikh issledovanii 2018; 6(3): 284–294. (in Russ.) DOI: 10.17238/issn2542-1298.2018.6.3.284

2. Basova L.A., Karyakina O.E., Martynova N.A., Kochorova L.V. Prediction of postoperative complications based on neural network technologies. Vestnik novykh meditsinskikh tehnologii 2015; 22(4): 117–121. (in Russ.) DOI: 10.12737/17035

3. Kravchenko V.O. Methods of using artificial neural networks in medicine. Ustoichivoe razvitie nauki i obrazovaniya 2018; 6: 266–270. (in Russ.)

4. Golovinova V.Yu., Kireev S.G., Kotenko P.K., Minaev Yu.L., Shtamburg I.N., Kuzmin S.G. Neural network models of morbidity prediction in organized collectives. Vestnik Rossiiskoi voenno-meditsinskoi akademii 2014; 3(47): 150–154. (in Russ.)

5. Faustova K.I. Neural networks: application today and prospects for development. Territoriya nauki 2017; 4: 83–87. (in Russ.)

6. Melikhova O.A., Veprintseva O.V., Chumicheva V.S., Dzhambinov S.V., Gaidukov A.B. Learning modes in artificial neural networks. Innovatsii v nauke 2016; 1(50): 17–22. (in Russ.)

7. Caliskan A., Yuksel M.E. Classification of Coronary Artery Disease Data Sets by Using a Deep Neural Network. Euro Biotech J 2017; 1(4): 271–277.

8. Yasnitskiy L.N., Dumler A.A., Bogdanov K.V., Poleshchuk A.N., Cherepanov F.M., Makurina T.V., Chugainov S.V. Diagnosis and prediction of the course of diseases of the cardiovascular system based on neural networks. Meditsinskaya tekhnika 2013; 3(279): 42–44. (in Russ.)

9. Sanoob M.U., Madhu A., Ajesh K., Varghese S.M. Artificial Neural Network for Diagnosis of Pancreatic Cancer. IJCI 2016; 5 (2): 41–49. DOI: 10.5121/ijci.2016.5205

10. Gantsev Sh.Kh., Zimichev A.A., Khrisanov N.N., Klimentyeva M.S. The use of a neural network in predicting bladder cancer. Meditsinskii vestnik Bashkortostana 2010; 3: 44–47. (in Russ.)

11. Makarova L.S., Semeryakova E.G. Development of decisive rules for the decision support system of differential diagnosis of bronchial asthma. Vestnik nauki Sibiri 2012; 3(4): 162–167. (in Russ.)

12. Panova I.A., Rakityanskaya E.A., Yasinsky I.F., Malyshkina A.I., Nazarov S.B., Pareishvili V.V., Bogatova I.K. The use of neural network technology to predict preeclampsia in pregnant women with chronic arterial hypertension. Sovremennye tehnologii v meditsine 2018; 10(4): 151–158. (in Russ.) DOI: 10.17691/stm2018.10.4.18

13. Rokotyanskaya E.A., Panova I.A., Malyshkina A.I., Fetisova I.N., Fetisov N.S., Kharlamova N.V., Kuligina M.V. Technologies for predicting preeclampsia. Sovremennye tekhnologii v meditsine 2020; 12(5): 78–86. (in Russ.) DOI: 10.17691/stm2020.12.5.09

14. Mantzaris D., Vrizas M., Trougkakos S., Priska E., Vadikolias K. Artificial Neural Networks for Estimation of Dementias Types. Artif Intell Appl 2014; 1(1): 74–82.

15. Lins A.J.C.C., Muniz M.T.C., Garcia A.N.M., Gomes A.V., Cabral R.M., Bastos-Filho C.J.A. Using Artificial Neural Networks to Select the Parameters for the Prognostic of Mild Cognitive Impairment and Dementia in Elderly Individuals. Comput Methods Programs Biomed 2017; 152: 93–104. DOI: 10.1016/j.cmpb.2017.09.013

16. Alekseeva O. V., Rossiev D.A., Ilyenkova N.A. The use of artificial neural networks in the differential diagnosis of recurrent bronchitis in children. Sibirskoe meditsinskoe obozrenie 2010; 6: 75–79. (in Russ.)

17. Reznichenko N.S., Shilov S.N. Using a neural network system to diagnose attention deficit hyperactivity disorder. Mediko-biologicheskie nauki 2014; 1: 48–54. (in Russ.)

18. Slavutskaya E.V., Slavutsky L.A. Using artificial neural networks to analyze gender differences in younger adolescents. Psikhologicheskie issledovaniya 2012; 5(23): 4. (in Russ.)

19. Chasha T.V., Kharlamova N.V., Klimova O.I., Yasinsky F.N., Yasinsky I.F. The use of neural networks to predict the course of posthypoxic disorders of the cardiovascular system in newborns. Vestnik Ivanovskogo gosudarstvennogo energeticheskogo universiteta 2009; 4: 57–59. (in Russ.)