Background: Gestational age determination is a critical aspect of prenatal care, allowing healthcare providers to monitor fetal development and identify potential complications. Nevertheless, traditional methods which are used to determine gestational age, including ultrasound and relying on the date of the last menstrual period, may be prone to variability and inaccuracies. Objective: The objective of this paper is to provide an overview and critical analysis of various machine learning techniques and methodologies utilized for gestational age determination. The aim is to assess the precision of these techniques and their potential to enhance the accuracy and effectiveness of forecasting gestational age. Selection Criteria: After conducting a comprehensive search of academic databases using keywords and phrases related to gestational age determination and automated machine learning, the studies that met the inclusion criteria were identified. A total of 161 articles were selected, encompassing studies that employed automated machine learning techniques for gestational age determination and were published in peer-reviewed journals from 2015 to 2023. Results: After applying inclusion and exclusion criteria, 24 research articles were selected. These studies used biparietal diameter, head circumference, and femur length as predictive measurement features for calculation of gestational age. The machine learning approaches that yielded the most promising outcomes were the ones employing BPD and HC to predict gestational age, achieving an accuracy rate exceeding 95%. Conclusion: The measurement criteria of BPD and HC produced the best results with a high level of accuracy. However, an alternative approach would be to incorporate all three measurement criteria, including Abdominal Circumference (AC), and calculate the average measurement as the gestational age.