Machine learning models for estimating fetal weight based on ultrasonographic biometry: Development and validation study

Background Advances in machine learning (ML) offer an innovative approach to accurate fetal weight estimation by integrating multiple biometric and clinical variables. Objective To develop and validate ML models for estimating fetal weight using biometric data obtained via ultrasonography, evaluatin...

Full description

Saved in:
Bibliographic Details
Main Authors: Marcos Espinola-Sánchez, Antonio Limay-Rios, Andrés Campaña-Acuña, Silvia Sanca-Valeriano
Format: Article
Language:English
Published: SAGE Publishing 2025-05-01
Series:Digital Health
Online Access:https://doi.org/10.1177/20552076251342012
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849321763374104576
author Marcos Espinola-Sánchez
Antonio Limay-Rios
Andrés Campaña-Acuña
Silvia Sanca-Valeriano
author_facet Marcos Espinola-Sánchez
Antonio Limay-Rios
Andrés Campaña-Acuña
Silvia Sanca-Valeriano
author_sort Marcos Espinola-Sánchez
collection DOAJ
description Background Advances in machine learning (ML) offer an innovative approach to accurate fetal weight estimation by integrating multiple biometric and clinical variables. Objective To develop and validate ML models for estimating fetal weight using biometric data obtained via ultrasonography, evaluating their accuracy and comparing them with traditional formulas, such as Hadlock and Shepard. Methods A retrospective observational study was conducted at the National Maternal Perinatal Institute of Peru from 2009 to 2022, including 3525 low-risk pregnancies with singleton gestations. ML models, including Gradient Boosting, Support Vector Machine (SVM), Random Forest and TabPFN (Tabular Prior-data Fitted Network), were trained and validated using ultrasonographic measurements such as biparietal diameter, abdominal circumference, head circumference, femur length, and gestational age. Accuracy was assessed using the coefficient of determination ( R ²) and mean squared error (MSE), comparing the ML models to the Hadlock and Shepard formulas. Results Data from the first study stage (2009–2018) indicated that the TabPFN model was the most accurate ( R ² = 0.856; MSE = 0.146), outperforming the Hadlock ( R ² = 0.807; MSE = 0.195) and Shepard ( R ² = 0.801; MSE = 0.201) formulas. In the independent validation sample (2019–2022), TabPFN consistently outperformed other methods ( R ² = 0.873; MSE = 0.144). Model consistency was evaluated through cross-validation and randomization of samples. Conclusions The TabPFN model outperformed traditional formulas, including Hadlock and Shepard, and other evaluated machine learning methods in estimating fetal weight. Its high predictive accuracy, robustness across temporally distinct cohorts, and independence from hyperparameter tuning support its potential as a reliable clinical decision-support tool in obstetric care.
format Article
id doaj-art-64b2e543364442ad94cf679259ce08e4
institution Kabale University
issn 2055-2076
language English
publishDate 2025-05-01
publisher SAGE Publishing
record_format Article
series Digital Health
spelling doaj-art-64b2e543364442ad94cf679259ce08e42025-08-20T03:49:40ZengSAGE PublishingDigital Health2055-20762025-05-011110.1177/20552076251342012Machine learning models for estimating fetal weight based on ultrasonographic biometry: Development and validation studyMarcos Espinola-Sánchez0Antonio Limay-Rios1Andrés Campaña-Acuña2Silvia Sanca-Valeriano3 Centro de Innovación e Investigación Traslacional en Salud (CIITSalud), , Lima, Peru , Lima, Peru , Lima, Peru , Lima, PeruBackground Advances in machine learning (ML) offer an innovative approach to accurate fetal weight estimation by integrating multiple biometric and clinical variables. Objective To develop and validate ML models for estimating fetal weight using biometric data obtained via ultrasonography, evaluating their accuracy and comparing them with traditional formulas, such as Hadlock and Shepard. Methods A retrospective observational study was conducted at the National Maternal Perinatal Institute of Peru from 2009 to 2022, including 3525 low-risk pregnancies with singleton gestations. ML models, including Gradient Boosting, Support Vector Machine (SVM), Random Forest and TabPFN (Tabular Prior-data Fitted Network), were trained and validated using ultrasonographic measurements such as biparietal diameter, abdominal circumference, head circumference, femur length, and gestational age. Accuracy was assessed using the coefficient of determination ( R ²) and mean squared error (MSE), comparing the ML models to the Hadlock and Shepard formulas. Results Data from the first study stage (2009–2018) indicated that the TabPFN model was the most accurate ( R ² = 0.856; MSE = 0.146), outperforming the Hadlock ( R ² = 0.807; MSE = 0.195) and Shepard ( R ² = 0.801; MSE = 0.201) formulas. In the independent validation sample (2019–2022), TabPFN consistently outperformed other methods ( R ² = 0.873; MSE = 0.144). Model consistency was evaluated through cross-validation and randomization of samples. Conclusions The TabPFN model outperformed traditional formulas, including Hadlock and Shepard, and other evaluated machine learning methods in estimating fetal weight. Its high predictive accuracy, robustness across temporally distinct cohorts, and independence from hyperparameter tuning support its potential as a reliable clinical decision-support tool in obstetric care.https://doi.org/10.1177/20552076251342012
spellingShingle Marcos Espinola-Sánchez
Antonio Limay-Rios
Andrés Campaña-Acuña
Silvia Sanca-Valeriano
Machine learning models for estimating fetal weight based on ultrasonographic biometry: Development and validation study
Digital Health
title Machine learning models for estimating fetal weight based on ultrasonographic biometry: Development and validation study
title_full Machine learning models for estimating fetal weight based on ultrasonographic biometry: Development and validation study
title_fullStr Machine learning models for estimating fetal weight based on ultrasonographic biometry: Development and validation study
title_full_unstemmed Machine learning models for estimating fetal weight based on ultrasonographic biometry: Development and validation study
title_short Machine learning models for estimating fetal weight based on ultrasonographic biometry: Development and validation study
title_sort machine learning models for estimating fetal weight based on ultrasonographic biometry development and validation study
url https://doi.org/10.1177/20552076251342012
work_keys_str_mv AT marcosespinolasanchez machinelearningmodelsforestimatingfetalweightbasedonultrasonographicbiometrydevelopmentandvalidationstudy
AT antoniolimayrios machinelearningmodelsforestimatingfetalweightbasedonultrasonographicbiometrydevelopmentandvalidationstudy
AT andrescampanaacuna machinelearningmodelsforestimatingfetalweightbasedonultrasonographicbiometrydevelopmentandvalidationstudy
AT silviasancavaleriano machinelearningmodelsforestimatingfetalweightbasedonultrasonographicbiometrydevelopmentandvalidationstudy