Machine Learning Approach For Early Prediction Of Low Birth Weight Cases
Main Article Content
Abstract
Predicting baby birth weight is an important component of prenatal care since it allows for early intervention and personalised healthcare for pregnant mothers and their infants. This project introduces "Birth Weight Predictor," a user-friendly web application developed using Flask and powered by machine learning that estimates birth weight depending on maternal characteristics. The application makes use of a large dataset that includes maternal health variables such as age, weight, height, medical history, habits, and more. Machine learning methods are used to analyse these maternal characteristics and predict birth weight accurately. The following are some of the application's key features: Maternal Data Input: Users can enter maternal data such as age, weight, height, and other pertinent parameters to get a personalised birth weight prediction Sophisticated machine learning methods, such as voting classifier with Random forest, Boosting algorithm, and logistic regression, are used to process the maternal data, allowing the model to uncover relevant patterns and associations for accurate predictions. Flask Web Interface: The user-friendly Flask-based web interface makes birth weight projections accessible and instructive for both healthcare providers and pregnant parents. This software is a useful tool for healthcare providers, expectant parents, and researchers, as it provides early insights into prospective birth weight outcomes. It contributes to improving prenatal care, minimising problems, and maintaining the well-being of both moms and newborns by leveraging the power of machine learning and Flask.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
Yu Z, Han S, Zhu J, Sun X, Ji C, Guo C. Pre-pregnancy body mass index in relation to infant birth weight and offspring overweight/obesity: a systematic review and meta-analysis. PLOS ONE. 2013;8(4):61627.
Shepard M, Richards V, Berkowitz R, Warsof S, Hobbins J. An evaluation of two equations for predicting birthweight by ultrasound. Am J Obstetr Gyneco. 1982;142(1):47–544.
Hadlock F, Harrist R, Carpenter R, Deter R, Park S. Sonographic estimation of birthweight. The value of femur length in addition to head and abdomen measurements. Radiology. 1984;150(2):535–40.
Zhu T, Zhao X, Ai M, Ma R, Lei J, Liu J. Comparison of accuracy of six calculations for predicting fetal body weight. Chin Mater Child Health Care. 2016;(20):4179–81.
Möst L, Schmid M, Faschingbauer F, Torsten H. Predicting birth weight with conditionally linear transformation models. Chin Mater Child Health Care. 2016;25(6):2781–810.
Hong C, Ji Y. Comparison of common methods for birthweight prediction and clinical value. Chin Women Children Health Res. 2017;5:2781–810.
Kuhle S, Maguire B, Zhang H, Hamilton D, Allen A, Joseph K, Victoria M. Comparison of logistic regression with machine learning methods for the prediction of fetal growth abnormalities: a retrospective cohort study. BMC Pregn Childbirth. 2018;18(1):333.
Farmer R, Medearis A, Hirata G, Platt L. The use of a neural network for the ultrasonographic estimation of birthweight in the macrosomic fetus. Am J Obstetr Gynecol. 1992;166(5):1467–72.
Cheng Y, Hsia C, Chang F, Hou C, ChiU Y, Chung K. Zeolites and synthetic mechanisms. In: 6th World Congress of Biomechanics (WCB 2010), Singapore 2010;1514–1517
Mohammadi H, Nemati M, Allahmoradi Z, Forghani H, Sheikhani A. Ultrasound estimation of birthweight in twins by artificial neural network. J Biomed Sci Eng. 2011;4(1):46–50.
Feng M, Wan L, Li Z, Qing L, Qi X. Fetal weight estimation via ultrasound using machine learning. IEEE Access. 2019;7:87783–91.