Improvement prenatal care with artificial intelligence: A systematic review

Introduction: Health issues can occur during pregnancy causing complications, as well as deathof the fetus or neonate or maternal. Prenatal care avoids pathologies for the mother and her fetus.Recent studies show that Artificial Intelligence (AI), mainly through machine learning and deeplearning models, has excessive potential for prediction, diagnosis, early detection of diseases andmonitoring of the gestational and postpartum period. Computational models have been commonlyused to predict prematurity, birthweight, mortality, hypertensive disorders, postpartum depression,….The main goal of this study is to present a systematic review of literature focused on computationalmodels to predict mortality and morbidity perinatal period.Methods: We conducted a systematic review of literature, limiting the search to the last ۱۰ yearsof publications considering the five main scientific databases as source.Results: From ۴۵۸ works, ۱۶ of them were selected as primary studies for further analysis. Wefound that most of works are focused on prediction of neonatal and maternal deaths, using machinelearning models. The top five most common features used to train models are birth weight,gestational age, Apgar score and mother’s age. Having predictive models for preventing mortalityduring and post-pregnancy not only improve the mother’s quality of life, as well as it can be apowerful and low-cost tool to decrease mortality ratios.Conclusion: Based on the results of this study, scientific efforts have been done in this extent, thecommunity have to develop opportunities for many open research in this area.

کلیدواژه ها:

Machine Learning ، Prenatal Care ، Stillbirth ، Neonatal Mortality ، Maternal Mortality.