Development of machine learning models for fetal birth weight prediction: A single-center study in a Turkish population

Fetal birth weight (BW) is a critical indicator of the prognosis of perinatal health. Accurate estimation of BW is essential in determining the appropriate delivery method. This single-center study aims to evaluate the performance of various machine learning (ML) algorithms in estimating BW. The study population consisted of 456 pregnant women with singleton pregnancies evaluated at a single tertiary center in the Karaman region of Turkiye between 38 and 41 weeks based on their last menstrual period, who gave birth to a phenotypically normal live newborn within 7 days after the ultrasound examination. Seven out of the nine models developed using ML algorithms had the lowest mean absolute error (MAE) values ranging from 184.30 to 190.00 grams. The formula closest to these values was Hadlock III, with an MAE value of 223.33 grams. In our study, the model demonstrating the highest predictive accuracy was provided by Linear Regression algorithm with an MAE value of 184.30 grams. Our findings indicate that data-driven predictive modelin.