Impact of multimodal information on the estimation of fetal growth indicators using machine learning regression models.
Authors
Affiliations (7)
Affiliations (7)
- Electrical Engineering Department, Universidad Autonoma Metropolitana Iztapalapa Division de Ciencias Basicas e Ingenieria, Av. Ferrocarril San Rafael Atlixco, 186., Reyes de Reforma 1ª Sección, Mexico City, Mexico City, 09340, Mexico.
- Instituto de Investigaciones en Matemáticas Aplicadas y en Sistemas, Universidad Nacional Autónoma de México, Escolar 3000, C.U., Coyoacán, 04510 Ciudad de México, CDMX, Ciudad de México, 04510, Mexico.
- Instituto de Investigaciones en Matemáticas Aplicadas y en Sistemas, Universidad Nacional Autonoma de Mexico, Escolar 3000, C.U., Coyoacán, 04510 Ciudad de México, CDMX, Mexico City, CDMX, 04510, Mexico.
- Departamento de Medicina Materno Fetal, Instituto Nacional de Perinatologia, Montes Urales 800, Lomas - Virreyes, Lomas de Chapultepec IV Secc, Miguel Hidalgo, 11000 Ciudad de México, CDMX, Mexico City, CDMX, 11000, Mexico.
- Instituto Nacional de Perinatologia, Montes Urales 800, Lomas - Virreyes, Lomas de Chapultepec IV Secc, Miguel Hidalgo, 11000 Ciudad de México, CDMX, Mexico City, CDMX, 11000, Mexico.
- Electrical Engineering, Universidad Autónoma Metropolitana Iztapalapa, Av. Ferrocarril San Rafael Atlixco Núm. 186, Col. Reyes de Reforma 1ª Sección, Alcaldía Iztapalapa, CP 09310, Ciudad de México, Iztapalapa, 09340, Mexico.
- Department of Electrical Engineering, Universidad Autonoma Metropolitana Iztapalapa Division de Ciencias Basicas e Ingenieria, Av. Ferrocarril San Rafael Atlixco Núm. 186, Col. Reyes de Reforma 1ª Sección, Alcaldía Iztapalapa, CP 09310, Ciudad de México, Iztapalapa, Distrito Federal, 09340, Mexico.
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.
.