EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine Learning Estimation of Gestational Age at Delivery Using Linked Mother–Infant Electronic Health Records Across Two Health Systems

Machine-Learning-Schätzung des Gestationsalters bei Geburt mithilfe verknüpfter elektronischer Gesundheitsakten von Mutter und Kind über zwei Gesundheitssysteme

Cosmin A Bejan iD, Xiaotong Yang, Amelie Pham iD, Layth Qassem iD, Abin Abraham, Leena Choi iD, S Trent Rosenbloom iD, Lana X Garmire, Elizabeth J Phillips iD

Pharmacoepidemiology and Drug Safety · 2026-11 · 35 (11)

DOI: 10.1002/pds.70516 ↗

Auf einen Blick

Das Modell schätzte das Gestationsalter bei Geburt mithilfe von EHR-Daten aus zwei Gesundheitssystemen. Die Ensemblemodelle zeigten insgesamt hohe Übereinstimmung, in einem System besser als im anderen.

Fragestellung

Lassen sich mit Machine-Learning-Modellen aus verknüpften Mutter-Kind-EHRs das Gestationsalter bei Geburt genau schätzen?

Methode

Entwicklung und Evaluation von random forest-, gradient boosting- und Ensemblemodellen mit EHR-Daten aus zwei Gesundheitssystemen; unabhängige Reimplementierung und Retraining an einem zweiten Standort.

Ergebnisse

Eingeschlossen waren 54 344 und 34 345 Mutter-Kind-Dyaden an VUMC und UMich. VUMC: ±1 Woche 85,1 %, ±2 Wochen 94,3 %, MAE 4,4 Tage. UMich: ±1 Woche 93,1 %, ±2 Wochen 97,8 %, MAE 2,8 Tage.

Schlussfolgerung der Autor:innen

Die Studie stellt ein robustes Machine-Learning-Framework zur Schätzung des Gestationsalters bei Geburt vor, dessen Entwicklung über zwei Gesundheitssysteme reproduzierbar war.

Kernaussagen

  • Ensemblemodelle schätzten das Gestationsalter insgesamt mit hoher Übereinstimmung.
  • Die Leistung war bei Frühgeburten deutlich geringer.
  • Die Modellierung war über zwei Gesundheitssysteme reproduzierbar.

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

Kurz gefasst

Fachartikel in der Zeitschrift Pharmacoepidemiology and Drug Safety, online erschienen am 29.10.2026. Verfasst von Cosmin A Bejan und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, Tennessee, USA. Hauptthemen laut MEDLINE: Electronic Health Records, Gestational Age, Machine Learning. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NLM NIH HHS, U.S. National Library of Medicine, NIH Office of the Director.

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

This study aimed to develop and evaluate machine‐learning models for estimating gestational age at delivery using EHR data from two health systems.

Methods

We trained random forest, gradient boosting, and ensemble models using EHR data from mother–infant dyads at Vanderbilt University Medical Center (VUMC) and independently reimplemented and retrained the modeling pipeline at the University of Michigan (UMich). We further analyzed EHR predictors of gestational age, assessed temporal drift in EHR data elements, and evaluated model performance stratified by gestational‐age category at delivery.

Results

The study included pregnancies corresponding to 54 344 and 34 345 mother–infant dyads at VUMC (2005–2025) and UMich (2012–2024), respectively. The gestational age predictions of the ensemble models showed high agreement with the reference standard on the VUMC dataset (±1 week: 85.1%, ±2 weeks: 94.3%, MAE: 4.4 days). When the same modeling pipeline was independently implemented and retrained on the UMich dataset, the ensemble models achieved higher agreement with the reference standard (±1 week: 93.1%, ±2 weeks: 97.8%, MAE: 2.8 days). Further, performance was better among pregnancies delivered in more recent years, and among full‐ and late‐term deliveries compared with preterm deliveries.

Discussion

The results indicate that supervised machine learning methods leveraging linked mother–infant EHRs can accurately estimate gestational age at delivery overall, although performance was substantially lower for preterm deliveries. Reproducibility of the modeling approach and portability of the analytic workflow were demonstrated across the two health systems.

Conclusion

This study presents a robust machine learning framework to estimate gestational age at delivery, whose development process was reproducible across two health systems. The framework has the potential to support large‐scale real‐world maternal and neonatal health studies requiring retrospective estimation of gestational age.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Electronic Health RecordsGestational AgeMachine LearningHumansFemalePregnancyPredictive Learning ModelsInfant, NewbornBoosting Machine Learning AlgorithmsRandom ForestAdultPrediction AlgorithmsMichiganMothersClassification Algorithms

Stichwörter der Autor:innen

electronic health recordsgestational age estimationgradient boostingmachine learningrandom forest

Autor:innen und Institutionen

  • Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, Tennessee, USA.
  • Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, Michigan, USA.
  • Division of Maternal Fetal Medicine, Department of Obstetrics and Gynecology, Vanderbilt University Medical Center, Nashville, Tennessee, USA.
  • Division of Neonatology, Children's Hospital of Philadelphia, Philadelphia, Pennsylvania, USA.
  • Department of Biostatistics, Vanderbilt University Medical Center, Nashville, Tennessee, USA.
  • Department of Medicine, Vanderbilt University Medical Center, Nashville, Tennessee, USA.

ORCID-Profile: Cosmin A Bejan, Amelie Pham, Layth Qassem, Leena Choi, S Trent Rosenbloom, Elizabeth J Phillips

Förderung

  • NLM NIH HHS
  • U.S. National Library of Medicine
  • NIH Office of the Director
  • NICHD NIH HHS
  • Eunice Kennedy Shriver National Institute of Child Health and Human Development
  • NIH HHS
  • NIGMS NIH HHS
  • National Institute of General Medical Sciences

Zitieren

APA

Bejan, C. A., Yang, X., Pham, A., Qassem, L., Abraham, A., Choi, L., Rosenbloom, S. T., Garmire, L. X., & Phillips, E. J. (2026). Machine Learning Estimation of Gestational Age at Delivery Using Linked Mother–Infant Electronic Health Records Across Two Health Systems. Pharmacoepidemiology and Drug Safety, 35(11). https://doi.org/10.1002/pds.70516

Vancouver

Bejan CA, Yang X, Pham A, Qassem L, Abraham A, Choi L, et al. Machine Learning Estimation of Gestational Age at Delivery Using Linked Mother–Infant Electronic Health Records Across Two Health Systems. Pharmacoepidemiology and Drug Safety. 2026;35(11). doi:10.1002/pds.70516

BibTeX
@article{Bejan2026,
  author = {Bejan, Cosmin A and Yang, Xiaotong and Pham, Amelie and Qassem, Layth and Abraham, Abin and Choi, Leena and Rosenbloom, S Trent and Garmire, Lana X and Phillips, Elizabeth J},
  title = {Machine Learning Estimation of Gestational Age at Delivery Using Linked Mother–Infant Electronic Health Records Across Two Health Systems},
  journal = {Pharmacoepidemiology and Drug Safety},
  year = {2026},
  volume = {35},
  number = {11},
  doi = {10.1002/pds.70516}
}
Kostenlos starten →