GENETIC AND MOLECULAR BIOMARKERS IN PREDICTING PREGNANCY COMPLICATIONS USING ARTIFICIAL INTELLIGENCE

Abstract

Pregnancy complications, in particular preeclampsia and other forms of placental dysfunction, remain one of the leading causes of maternal and perinatal morbidity and require improvement in early diagnosis methods. Traditional clinical criteria often reveal pathology at the stage of clinical manifestation, which limits the possibilities of prevention and timely intervention. In recent years, special attention has been paid to the use of biomarkers of placental and endothelial dysfunction, as well as artificial intelligence and machine learning methods for early prediction of adverse pregnancy outcomes. The review analyzes current data on the role of angiogenic, inflammatory, and molecular markers, as well as integrative digital models in personalized perinatal diagnostics. It is shown that the combination of biomarker approaches and intelligent analytical tools is a promising direction, but requires further clinical validation, standardization and consideration of ethical aspects of implementation.