Predicting preeclampsia using artificial intelligence technologies

Abstract

Russian Federation's strategy for the conservation of reproductive potential is focused on the personalized health care for women and is based on the preclinical detection of gynecological diseases and major obstetric syndromes at the prediction of adverse outcomes and subsequent preventive measures that can reduce maternal and perinatal morbidity and mortality, decrease women and newborn disability and significantly reduce the extremely high costs of care of the premature infants. The search for effective methods of prediction of preeclampsia at the stage of preconception and in the first trimester of pregnancy is driven by the desire to identify women who have a greater risk of developing hypertensive disorders in order to take the necessary effective measures to prevent placental pathology as early as possible and thus prevent or reduce the rate of preeclampsia. At the same time, identification of women in the high-risk group will allow to plan a rational prenatal care, timely recognize the occurrence of multiple organ dysfunction and immediately begin pathogenetic and symptomatic therapy. Taking into account the national and world experience in the use of predictive analytics software, that has proven the success of these methods in reproductive medicine, it is reasonable to conclude that the conversion of prognosis into a digital format using artificial intelligence algorithms will open new possibilities of increasing the accuracy of individual risk calculation for preeclampsia, corresponding to modern trends of personalized preventive medicine. This scientific review of the Russian and international publications aims to inform a wide group of obstetrician-gynecologists on the achievements of artificial intelligence technologies and the prospects for machine learning in the prediction of preeclampsia.