ABSTRACT
Background: Due to the high spread rate of SARS-CoV-2 and to the rapid increase in its incidence, including those among pregnant women, the novel coronavirus infection (COVID-19) has become a challenge in modern healthcare. Objective(s): To analyze the impact of the novel coronavirus infection experienced by pregnant women on the health of newborns in the early neonatal period. Material(s) and Method(s): A retrospective analysis was carried out of the birth records of 400 women who had experienced the novel coronavirus infection during pregnancy and the neonatal records of their newborns (n=500) who received health care in the clinical units of the V.I. Kulakov National Medical Research Center of Obstetrics, Gynecology, and Perinatology, Ministry of Health of Russia (Center), in July 2020 to July 2021. A comparison group consisted of randomly selected birth records of 495 pregnant women who had not been infected with COVID-19 and the neonatal records of their babies (n=500) born at the same Center at the same time. Result(s): The vast majority of women who had been infected with COVID-19 during pregnancy were found to have familial obstetric/gynecological and/or somatic histories. Among the factors aggravating pregnancy in the presence of COVID-19, chronic hypertension, hereditary thrombophilia, fat metabolism disorders, urogenital infections, and anemia are more common than those in the control group (p<0.05). This female group also tended to have miscarriage;however, no statistically significant differences could be detected (p=0.06). There were no statistically significant differences in the term and frequency of cesarean delivery in pregnant women in the study and control groups (p>0.05). Neonates born to women who had been infected with COVID-19 in the first trimester had its statistically significantly higher morbidity rates (p<0.05). The frequency of perinatal complications was higher in newborns whose mothers had experienced the novel coronavirus infection in the first trimester. Neonatal infants borns from women who had a new coronavirus infection in the third trimester, rhinitis and otitis media are statistically significantly more common in the early neonatal period. Among the factors leading to disruption of early neonatal adaptation of children whose mothers had a new coronavirus infection during pregnancy, the following were statistically significantly more common: infectious and inflammatory diseases (rhinitis, otitis media), hemorrhagic syndrome, and hypoglycemia (p<0.05). Neonates born to women who had been infected with COVID-19 in the first trimester were observed to have statistically significantly higher morbidity rates (p<0.05). The incidence of perinatal complications was higher in newborns whose mothers had experienced the novel coronavirus infection in the first trimester. Neonatal infants born to women who had the novel coronavirus infection in the third trimester were statistically significantly more commonly recorded to have rhinitis and otitis media in the early neonatal period. Among the factors leading to failure of early neonatal adaptation of babies whose mothers had the novel coronavirus infection during pregnancy, there were statistically significantly more often infectious and inflammatory diseases (rhinitis, otitis media), hemorrhagic syndrome, and hypoglycemia (p<0.05). Conclusion(s): The incidence of perinatal complications in babies born to women who had been infected with COVID-19 depended on their gestational age and was higher than that in newborns whose mothers had experienced the novel coronavirus infection in the first trimester. At the same time, the incidence of infectious and inflammatory diseases proved to be higher in infants whose mothers had a coronavirus infection in the third trimester. Failure of early neonatal adaptation of babies born to women who had an infection caused by SARS-CoV-2 during pregnancy may be due to both infectious and non-infectious factors that complicate the course of pregnancy and childbirth. Copyright © A group of authors, 2022.
ABSTRACT
Edge computing is a fast-growing and much needed technology in healthcare. The problem of implementing artificial intelligence on edge devices is the complexity and high resource intensity of the most known neural network data analysis methods and algorithms. The difficulty of implementing these methods on low-power microcontrollers with small memory size calls for the development of new effective algorithms for neural networks. This study presents a new method for analyzing medical data based on the LogNNet neural network, which uses chaotic mappings to transform input information. The method effectively solves classification problems and calculates risk factors for the presence of a disease in a patient according to a set of medical health indicators. The efficiency of LogNNet in assessing perinatal risk is illustrated on cardiotocogram data obtained from the UC Irvine machine learning repository. The classification accuracy reaches ~91% with the~3-10 kB of RAM used on the Arduino microcontroller. Using the LogNNet network trained on a publicly available database of the Israeli Ministry of Health, a service concept for COVID-19 express testing is provided. A classification accuracy of ~95% is achieved, and~0.6 kB of RAM is used. In all examples, the model is tested using standard classification quality metrics: precision, recall, and F1-measure. The LogNNet architecture allows the implementation of artificial intelligence on medical peripherals of the Internet of Things with low RAM resources and can be used in clinical decision support systems.