EUVIMEDEUVIMED entdecken
Multizentrische StudieValidierungsstudieOpen Access

Machine Learning–Based First-Trimester Antenatal Risk Prediction for Adverse Maternal and Neonatal Outcomes: Multicenter Model Development Study

Sarah Li, David Y Y Tan, Jingxian Zhang, Aniza P Mahyuddin, Harshaana Ramlal, Sebastian E Illanes, Max Monckeberg, Alejandra F Plaza, Maria L Paz Morgan, Matthew W Kemp, Kee Yuan Ngiam, Peter Lindgren und 5 weitere

Journal of Medical Internet Research · 26.08.2026 · 28 · e88450-e88450

DOI: 10.2196/88450 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Journal of Medical Internet Research, online erschienen am 26.08.2026. Verfasst von Sarah Li und 16 weiteren Autor:innen. Beteiligte Einrichtung: Department of Obstetrics and Gynaecology, National University Hospital, Singapore, Singapore, Singapore. Hauptthemen laut MEDLINE: Machine Learning, Pregnancy Outcome, Pregnancy Trimester, First. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Maternal outcomes remain inequitable worldwide. Severe morbidity persists, and current risk assessment tools are largely arbitrary, focusing on biomedical factors while overlooking social determinants of health. There is a need for data-driven AI models to improve early pregnancy risk identification and management.

Objective

The study aimed to develop and internally validate first-trimester AI-based antenatal risk assessment models across three geographically and socioethnically diverse populations (Sweden, Chile, and Singapore) and to compare their performance with existing clinical risk assessment strategies.

Methods

We conducted a retrospective population-based study using routinely collected first-trimester data from over 700,000 pregnancies from Sweden, Chile, and Singapore. Separate machine learning models predicting a composite of adverse maternal and neonatal outcomes were trained and internally validated for each population. Input variables were limited to information available at or before 14 weeks’ gestation. Model discrimination, measured by the area under the receiver operating characteristic (AUROC) curve, was compared with corresponding proxies for real-world first-trimester risk assessment approaches in each setting. Model interpretability was assessed using Shapley additive explanations.

Results

The prevalence of the composite adverse outcome was 10.40% (75,647/727,354) in Sweden, 21.94% (1302/5934) in Chile, and 16.25% (6145/37,813) in Singapore. In Sweden, the guideline-based risk assessment achieved an AUROC of 0.53, compared with 0.65 for the LightGBM (light gradient boosting machine) model ( P

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningPregnancy OutcomePregnancy Trimester, FirstAdultFemaleHumansInfant, NewbornPregnancyBoosting Machine Learning AlgorithmsChilePrediction AlgorithmsPredictive Learning ModelsRetrospective StudiesRisk AssessmentSingaporeSweden

Stichwörter der Autor:innen

adverse pregnancy outcomesantenatal careantenatal risk stratificationmachine learningobstetrics and gynecologyrisk predictions

Autor:innen und Institutionen

  • Department of Obstetrics and Gynaecology, National University Hospital, Singapore, Singapore, Singapore.
  • Diagnostics Development Hub, Agency for Science, Technology and Research, Singapore, Singapore.
  • Department of Obstetrics and Gynaecology, NUS Yong Loo Lin School of Medicine, National University of Singapore, 1E Kent Ridge Road, NUHS Tower Block, Level 12, Singapore, Singapore, 119228, Singapore, 65 93889316.
  • Department of Obstetrics and Gynecology and Reproductive Biology Laboratory, Universidad de los Andes, Santiago, Chile.
  • IMPACT, Center of Interventional Medicine for Precision and Advanced Cellular Therapy, Santiago, Chile.
  • Women and Infants Research Foundation, King Edward Memorial Hospital, Perth, Australia.

Zitieren

APA

Li, S., Tan, D. Y. Y., Zhang, J., Mahyuddin, A. P., Ramlal, H., Illanes, S. E., Monckeberg, M., Plaza, A. F., Morgan, M. L. P., Kemp, M. W., Ngiam, K. Y., Lindgren, P., Kublickas, M., Kublickiene, K., Weng, R., Yee, S., & Choolani, M. (2026). Machine Learning–Based First-Trimester Antenatal Risk Prediction for Adverse Maternal and Neonatal Outcomes: Multicenter Model Development Study. Journal of Medical Internet Research, 28, e88450-e88450. https://doi.org/10.2196/88450

Vancouver

Li S, Tan DYY, Zhang J, Mahyuddin AP, Ramlal H, Illanes SE, et al. Machine Learning–Based First-Trimester Antenatal Risk Prediction for Adverse Maternal and Neonatal Outcomes: Multicenter Model Development Study. Journal of Medical Internet Research. 2026;28:e88450-e88450. doi:10.2196/88450

BibTeX
@article{Li2026,
  author = {Li, Sarah and Tan, David Y Y and Zhang, Jingxian and Mahyuddin, Aniza P and Ramlal, Harshaana and Illanes, Sebastian E and Monckeberg, Max and Plaza, Alejandra F and Morgan, Maria L Paz and Kemp, Matthew W and Ngiam, Kee Yuan and Lindgren, Peter and Kublickas, Marius and Kublickiene, Karolina and Weng, Ruifen and Yee, Sidney and Choolani, Mahesh},
  title = {Machine Learning–Based First-Trimester Antenatal Risk Prediction for Adverse Maternal and Neonatal Outcomes: Multicenter Model Development Study},
  journal = {Journal of Medical Internet Research},
  year = {2026},
  volume = {28},
  pages = {e88450--e88450},
  doi = {10.2196/88450}
}
Kostenlos starten →