Objective: to define the risk factors adversely influencing prenatal development at premature birth at use of methods of assisted reproductive technology (ART); to estimate premature' infants health from multiple induced pregnancy according to Perinatal Center of Saratov for last 3 years. Material and Methods. Under supervision there were 139 pregnant women with application ART. 202 children (51 twins were born and 5 triplet babies), from them 83 premature infants born from multiple induced pregnancy have been analyzed. Results. The newborns examined by method ART, were distributed as follows: 22-28 weeks — 19 children; 29-32 weeks — 23; 33-36 weeks — 41. Asphyxia at birth was marked at all premature infants. Respiratory insufficiency at birth is revealed in 87,3% of cases. The most frequent pathologies in premature infants are revealed: neurologic infringements and bronchopulmonary pathology occured at all children, developmental anomaly — 33, 8%, retinopathies in premature infants — 26,5%. The mortality causes include: extreme immaturity, cerebral leukomalacia, IVN 3 degrees. Conclusion. The risk factors, premature birth at application of methods ART are revealed: aged primiparas, pharmacological influence, absence of physiological conditions of prenatal development; multifetation. The high percent of birth of children with ELBW and ULBW is revealed. RDCN with further BPD development, retinopathies in premature infants and CNS defeat is more often occured.

The purpose of the study is to examine the feasibility of a self-learning neural network to predict the risk of hemo-static disorders in newborns and their mothers. Material: To solve the problems 214 patients have been under the study, of which — 107 women on a day of labor and 107 of their infants. Morphofunctional state of platelets was assessed by automatic hematological analysis, computer cytomorphometry and platelet aggregation. These laboratory studies of patients were used as a training set for a neural network. This study used a neural network with classical structure «layer perceptron.» Results: Testing of the neural network was carried out on two female patients with physiological pregnancy and signs of imbalance of the hemostatic system. At the output of neural network based on laboratory confirmed the presence or absence of pathology of the hemostatic system in two specific patients and their newborns. Conclusion: The introduction of practical obstetric program being developed based on the neural network will reduce and prevent the development of thrombohemorrhagic complications, the protocol will optimize diagnostic and treatment activities, and an opportunity for the state of hemostasis monitor on a background of pathogenetic therapy for women and their newborns during childbirth and neonatal period.