EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Machine learning‐based prediction of large‐for‐gestational‐age neonates in diabetic and non‐diabetic pregnancies

Ohad Houri iD, Asaf Romano, Asnat Walfisch, Eran Hadar, Yinon Gilboa, Leor Perl, Nadav Loebl, Ron Unger

International Journal of Gynecology & Obstetrics · 2025

DOI: 10.1002/ijgo.70751 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Gynecology & Obstetrics, 2025. Verfasst von Ohad Houri und 7 weiteren Autor:innen. Beteiligte Einrichtung: Helen Schneider Hospital for Women, Rabin Medical Center, Petach Tikva, Israel. Hauptthemen laut MEDLINE: Machine Learning, Diabetes, Gestational, Fetal Macrosomia, Ultrasonography, Prenatal. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

This study determines whether a machine‐learning model integrating sonographic biometry with maternal clinical parameters improves prediction of large‐for‐gestational‐age (LGA) compared with Hadlock's EFW formula.

Methods

We conducted a retrospective cohort study including all singleton live births at ≥32 gestational weeks at a tertiary medical center. Predictors comprised biparietal diameter, abdominal circumference, femur length, maternal demographics and anthropometrics, obstetric history, chronic and gestational morbidity, and glucose values from screening and diagnosis. A CatBoost gradient‐boosting model estimated the probability of LGA (birthweight ≥90th percentile). Performance was compared with Hadlock's EFW using area under the curve (AUC) and detection at a fixed 10% false‐positive rate. A prespecified subgroup analysis evaluated pregnancies with pregestational or gestational diabetes. Performance was assessed with fivefold cross‐validation; calibration and utility were examined by decision curve analysis.

Results

Among 31 531 parturients, 18.17% delivered an LGA neonate. The model achieved an AUC of 0.946 (95% confidence interval [CI], 0.938–0.955), significantly outperforming Hadlock's EFW (AUC 0.867; 95% CI, 0.854–0.881; P = 0.01) and yielding a higher detection rate at a 10% false‐positive rate (79% vs. 63%). The most influential contributors were abdominal circumference, gestational age at delivery, fetal sex, and maternal age. In 3871 diabetic pregnancies, among whom 24% delivered LGA, performance remained high (AUC 0.890; 95% CI, 0.847–0.918) and exceeded Hadlock's formula (AUC 0.820; 95% CI, 0.772–0.863; P = 0.02).

Conclusion

A predictive algorithm, incorporating sonographic and non‐sonographic features, as developed here, achieved superior accuracy compared to the traditional EFW formula in predicting LGA neonates, in both general and diabetic pregnant populations.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningDiabetes, GestationalFetal MacrosomiaUltrasonography, PrenatalHumansPregnancyFemaleRetrospective StudiesInfant, NewbornAdultGestational AgeBirth WeightPredictive Value of TestsBiometryMale

Stichwörter der Autor:innen

diabeteslarge‐for‐gestational‐age machine learningprediction

Autor:innen und Institutionen

  • Helen Schneider Hospital for Women, Rabin Medical Center, Petach Tikva, Israel.
  • Faculty of Health and Medical Sciences, Tel Aviv University, Tel Aviv, Israel.
  • BCNatal-Barcelona Center for Maternal-Fetal and Neonatal Medicine (Hospital Clinic and Hospital Sant Joan de Deu), University of Barcelona, Barcelona, Spain.
  • Dina Recanati School of Medicine, Reichman University, Herzliya, Israel.
  • Department of Cardiology, Rabin Medical Center, Petach Tikva, Israel.
  • Innovation Lab, Rabin Medical Center, Petach Tikva, Israel.

ORCID-Profile: Ohad Houri

Zitieren

APA

Houri, O., Romano, A., Walfisch, A., Hadar, E., Gilboa, Y., Perl, L., Loebl, N., & Unger, R. (2025). Machine learning‐based prediction of large‐for‐gestational‐age neonates in diabetic and non‐diabetic pregnancies. International Journal of Gynecology & Obstetrics. https://doi.org/10.1002/ijgo.70751

Vancouver

Houri O, Romano A, Walfisch A, Hadar E, Gilboa Y, Perl L, et al. Machine learning‐based prediction of large‐for‐gestational‐age neonates in diabetic and non‐diabetic pregnancies. International Journal of Gynecology & Obstetrics. 2025. doi:10.1002/ijgo.70751

BibTeX
@article{Houri2025,
  author = {Houri, Ohad and Romano, Asaf and Walfisch, Asnat and Hadar, Eran and Gilboa, Yinon and Perl, Leor and Loebl, Nadav and Unger, Ron},
  title = {Machine learning‐based prediction of large‐for‐gestational‐age neonates in diabetic and non‐diabetic pregnancies},
  journal = {International Journal of Gynecology & Obstetrics},
  year = {2025},
  doi = {10.1002/ijgo.70751}
}
Kostenlos starten →