Impact of multimodal information on the estimation of fetal growth indicators using machine learning regression models
Authors:
- Orlando Castellanos-DiazOCOrlando Castellanos-Diaz
- Jorge Perez-GonzalezJPJorge Perez-Gonzalez
- Fernando Arambula CosioFCFernando Arambula Cosio
- Laura Gonzalez-MezaLGLaura Gonzalez-Meza
- Lisbeth Camargo-MarinLCLisbeth Camargo-Marin
- Mario Guzman-HuertaMGMario Guzman-Huerta
- Fernanda Vazquez-SalazarFVFernanda Vazquez-Salazar
- Jesus Aguilera-PerezJAJesus Aguilera-Perez
- Veronica Ortega-CastilloVOVeronica Ortega-Castillo
- Veronica Medina-BanuelosVMVeronica Medina-Banuelos
- Raquel Valdes-CristernaRVRaquel Valdes-Cristerna
Open Access
- 8 April 2026
- journal article
- Published by IOP Publishing in Biomedical Physics & Engineering Express
- Vol. 12 (3) , 035005
Abstract
Accurate estimation of fetal growth indicators such as birth weight, birth length, and gestational age at birth is essential for monitoring pregnancy outcomes and guiding clinical decisions. Traditional predictive models typically rely on ultrasound-based fetometric data to estimate fetal weight or length. While valuable, these models provide estimates only at the time of measurement, rather than predicting values at birth, and may overlook important clinical and sociodemographic factors that also influence fetal growth. This study aimed to evaluate whether incorporating echographic, clinical, and sociodemographic features could improve the accuracy of predicting fetal growth indicators at birth and to quantify the contribution of each variable. Data from 154 cases were collected and processed for model development (61.5% for training and 38.5% for testing), divided into three feature sets: fetometric, clinical–sociodemographic, and combined clinical, echographic, and sociodemographic data. Six regression models were developed to predict three fetal growth indicators: birth weight, birth length, and gestational age at birth. Model performances were assessed using R2, Mean Absolute Error, and Mean Absolute Percentage Error. The multimodal models significantly outperformed those relying only on fetometric or clinical–sociodemographic data, with the Random Forest achieving the best performance for birth weight R2: 0.8991; MAE: 255.08 g; MAPE: 8.46%, birth length R2: 0.8679; MAE: 7.21 cm; MAPE: 2.73%, and gestational age at birth R2: 0.8886; MAE: 1.34 days; MAPE: 2.76%. Feature relevance analysis revealed that variables such as maternal height, maternal weight, placenta location, and alcohol consumption played substantial roles in prediction accuracy, alongside classic fetometric measurements such as head circumference. These findings highlight the multifactorial nature of fetal growth and demonstrate that integrating clinical and sociodemographic information enhances the performance of fetal growth prediction models, ultimately supporting improved perinatal care.Keywords
Funding Information
- Universidad Autónoma Metropolitana unidad Iztapalapa (UAMI-DCBI-PEAPDI2025)
- Universidad Nacional Autónoma de México (IA100924)
This publication has 31 references indexed in Scilit:
- Sociodemographic factors associated with preterm birth and low birth weight: A cross-sectional studyWomen and Birth, 2019
- EP02.02: The effect of placental location on uterine artery Doppler measurementsUltrasound in Obstetrics & Gynecology, 2018
- Association between ABO blood type and live-birth outcomes in single-embryo transfer cyclesFertility and Sterility, 2017
- Racial/ethnic standards for fetal growth: the NICHD Fetal Growth StudiesAmerican Journal of Obstetrics and Gynecology, 2015
- National and regional estimates of term and preterm babies born small for gestational age in 138 low-income and middle-income countries in 2010The Lancet Global Health, 2013
- Placental Laterality as a Predictor for Development of PreeclampsiaThe Journal of Obstetrics and Gynecology of India, 2012
- A high uterine artery pulsatility index reflects a defective development of placental bed spiral arteries in pregnancies complicated by hypertension and fetal growth retardationEuropean Journal of Obstetrics & Gynecology and Reproductive Biology, 1993
- Effect of placental resistance, arterial diameter, and blood pressure on the uterine arterial velocity waveform: A computer modeling approachUltrasound in Medicine & Biology, 1989
- Estimation of fetal weight with the use of head, body, and femur measurements—A prospective studyAmerican Journal of Obstetrics and Gynecology, 1985
- An evaluation of two equations for predicting fetal weight by ultrasoundAmerican Journal of Obstetrics and Gynecology, 1982