Potential of Artificial Intelligence to Estimate the Birthweight of Newborns Based on Ultrasound Data – Comparison between AI and Hadlock Formula Das Potenzial künstlicher Intelligenz zur Schätzung des Geburtsgewichts von Neugeborenen anhand von Ultraschalldaten – Vergleich zwischen künstlicher Intelligenz und der Hadlock-Formel
- 1Department of Gynaecology, Obstetrics and Gyn. EndocrinologyJohannes Kepler University Linz, Kepler University HospitalLinzAustria.
- 2Department of Anaesthesiology and Intensive CareJohannes Kepler University Linz, Kepler University HospitalLinzAustria.
Abstract
Objective
When managing labor and delivery, an accurate estimation of fetal weight is essential. The aim of this study was to compare if a prediction model developed by Artificial intelligence (AI) can predict fetal birthweight or macrosomia with greater accuracy than the Hadlock formula, which is commonly used to estimate fetal weight at the time of ultrasound.Methods
17691 ultrasonography exams from 2013-2022 were included in this study. The dataset was split. The first 70% of the data were used for training the models, the results were validated on 15% of the data and the remaining 15% were designated as the testing dataset. Several machine learning methods were examined. Three AI models were created: the regression model to predict the birthweight and two classification models to predict a birthweight of over 4000 g and over 4500 g respectively.Results
In the regression model the best prediction accuracy was attained with random forest regression (RMSE 315.071, SD 10.055). These results were better compared to the Hadlock formula (RMSE of 323.14). In the classification model with a threshold of 4000 g the best result was achieved with deep neural network (AUC 0.889, SD 0.008). Similarly in the second classification model (threshold 4500 g) the best results were observed with random forest classification (AUC 0.894, SD 0.054) and with deep neural network (AUC 0.910, SD 0.032).Conclusion
AI-supported models such as random forest and deep neural network facilitate accurate prediction of macrosomia and fetal weight at birth by considering a variety of parameters.
Related
- Early erythropoiesis‐stimulating agents in preterm or low‐birthweight infants
- Compartment-specific soluble immune profiles associated with preterm birth, perinatal death, and low birthweight in pregnant individuals living with HIV
- Red blood cell transfusion is not associated with lymphocyte subpopulation counts in very low birthweight infants.
- Association between birth order and birthweight percentile: population-level and within-mother analyses in a large birth cohort
- Maternal Exposure to Ambient Ozone and Birthweight Reduction During COVID-19 Epidemic in East China: A Sex- and Window-Specific Retrospective Cohort Study
BibTeX
@article{kaufmann2026potential,
title = {{Potential of Artificial Intelligence to Estimate the Birthweight of Newborns Based on Ultrasound Data – Comparison between AI and Hadlock Formula Das Potenzial künstlicher Intelligenz zur Schätzung des Geburtsgewichts von Neugeborenen anhand von Ultraschalldaten – Vergleich zwischen künstlicher Intelligenz und der Hadlock-Formel}},
author = {Natalia Anna Kaufmann and Peter Oppelt and Jens Meier and Teresa Eichinger and Sabine Enengl and Julia Lastinger and Elisabeth Reiter},
journal = {Geburtshilfe und Frauenheilkunde},
year = {2026},
month = aug,
doi = {10.1055/a-2915-6606},
url = {https://europepmc.org/article/PMC/PMC13754455},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Potential of Artificial Intelligence to Estimate the Birthweight of Newborns Based on Ultrasound Data – Comparison between AI and Hadlock Formula Das Potenzial künstlicher Intelligenz zur Schätzung des Geburtsgewichts von Neugeborenen anhand von Ultraschalldaten – Vergleich zwischen künstlicher Intelligenz und der Hadlock-Formel
AU - Natalia Anna Kaufmann
AU - Peter Oppelt
AU - Jens Meier
AU - Teresa Eichinger
AU - Sabine Enengl
AU - Julia Lastinger
AU - Elisabeth Reiter
PY - 2026
DA - 2026/08/24
JO - Geburtshilfe und Frauenheilkunde
DO - 10.1055/a-2915-6606
UR - https://europepmc.org/article/PMC/PMC13754455
AB - Objective When managing labor and delivery, an accurate estimation of fetal weight is essential. The aim of this study was to compare if a prediction model developed by Artificial intelligence (AI) can predict fetal birthweight or macrosomia with greater accuracy than the Hadlock formula, which is commonly used to estimate fetal weight at the time of ultrasound.Methods 17691 ultrasonography exams from 2013-2022 were included in this study. The dataset was split. The first 70% of the data were used for training the models, the results were validated on 15% of the data and the remaining 15% were designated as the testing dataset. Several machine learning methods were examined. Three AI models were created: the regression model to predict the birthweight and two classification models to predict a birthweight of over 4000 g and over 4500 g respectively.Results In the regression model the best prediction accuracy was attained with random forest regression (RMSE 315.071, SD 10.055). These results were better compared to the Hadlock formula (RMSE of 323.14). In the classification model with a threshold of 4000 g the best result was achieved with deep neural network (AUC 0.889, SD 0.008). Similarly in the second classification model (threshold 4500 g) the best results were observed with random forest classification (AUC 0.894, SD 0.054) and with deep neural network (AUC 0.910, SD 0.032).Conclusion AI-supported models such as random forest and deep neural network facilitate accurate prediction of macrosomia and fetal weight at birth by considering a variety of parameters.
SN - 0016-5751
SN - 1438-8804
ER -