Scholarship 24/18309-2 - Estudos de coortes, Saúde materno-infantil - BV FAPESP
Advanced search
Start date
Betweenand

Structural equation modeling and machine learning for predicting fetal growth based on gestational weight gain: Araraquara Cohort Study.

Grant number: 24/18309-2
Support Opportunities:Scholarships abroad - Research Internship - Doctorate
Start date until: January 02, 2025
End date until: November 01, 2025
Field of knowledge:Health Sciences - Collective Health - Epidemiology
Principal Investigator:Patricia Helen de Carvalho Rondó
Grantee:Audencio Victor
Supervisor: Eric Ohuma
Host Institution: Faculdade de Saúde Pública (FSP). Universidade de São Paulo (USP). São Paulo , SP, Brazil
Institution abroad: London School of Hygiene and Tropical Medicine, England  
Associated to the scholarship:23/07936-3 - The influence of gestational weight gain on fetal growth and neonatal outcomes: Araraquara Cohort Study., BP.DR

Abstract

Introduction: Adequate gestational weight gain (GWG) is crucial for maternal health and fetal growth. The Institute of Medicine (IOM) guidelines from the United States provide specific recommendations for GWG based on pre-pregnancy body mass index, but these guidelines may not be entirely applicable to Brazilian pregnant women due to population, nutritional, and lifestyle differences. This study aims to investigate the relationship between GWG and fetal growth, using advanced structural equation modeling (SEM) and machine learning (ML) techniques to develop robust predictive models of fetal and neonatal outcomes. Methods: This is a prospective cohort epidemiological study using data from the Araraquara Cohort. The sample includes women with a gestational age ¿ 19 weeks who received prenatal care at Basic Health Units in the municipality of Araraquara and surrounding areas. Socioeconomic, demographic, lifestyle, obstetric history, prenatal and birth conditions, as well as anthropometric and body composition data of the mother, fetus, and neonate, were collected. Data analysis will be performed using SEM techniques to explore complex relationships between multiple variables and ML algorithms to develop predictive models of the outcomes of interest. Data analysis: Initial descriptive analysis will characterize the study population. Statistical tests will be applied to assess the normality of the variables and bivariate analyses will be conducted to explore relationships between independent variables and outcomes. SEM will allow the simultaneous analysis of multiple cause-and-effect relationships, while ML algorithms, such as decision trees, random forests, neural networks, and ensemble methods, will be used to develop predictive models. Model evaluation will be conducted using cross-validation and metrics such as accuracy, sensitivity, specificity, and area under the ROC curve. Expected results: This study will contribute to a better understanding of the relationship between GWG and fetal and neonatal outcomes in Brazilian pregnant women. It is expected that the results will provide evidence to adapt the recommendations to local realities, improving public health guidelines for the Brazilian population.

News published in Agência FAPESP Newsletter about the scholarship:
More itemsLess items
Articles published in other media outlets ( ):
More itemsLess items
VEICULO: TITULO (DATA)
VEICULO: TITULO (DATA)

Please report errors in scientific publications list using this form.