Source: Image created by the authors / Freepik; Copyright: The Authors / tirachardz; License: Licensed by the authors
New research suggests that machine learning models using first-trimester pregnancy data outperformed existing early risk assessment approaches in Sweden, Chile, and Singapore.
(Toronto, August 27, 2026) Artificial intelligence (AI) may help identify women and babies at risk of serious health problems earlier in pregnancy, according to a new study analyzing data from more than half a million pregnancies across Sweden, Chile, and Singapore. The machine learning models, which used information available during the first 14 weeks of pregnancy, generally outperformed the early risk assessment methods currently used in each setting.
The findings, published in the Journal of Medical Internet Research article titled “Machine Learning–Based First-Trimester Antenatal Risk Prediction for Adverse Maternal and Neonatal Outcomes: Multicenter Model Development Study,” suggest that AI could eventually support more personalized and equitable prenatal care. The research also found that social and demographic factors were among the most important predictors in some populations, highlighting information that traditional risk assessments may overlook.
In Sweden and Chile, the best-performing machine learning models showed substantially better ability to distinguish between higher- and lower-risk pregnancies than the existing approaches. In Singapore, the improvement was smaller but still statistically significant.
The study also underscores an important challenge: one model did not perform equally well in every population. While the Swedish and Singaporean models showed reasonable agreement between predicted and observed risks, the Chilean model was less well calibrated. This suggests that AI tools for prenatal care may need to be tailored and carefully tested for the populations in which they are used.
The researchers emphasize that such models are not intended to replace health care professionals. Instead, they could serve as decision-support tools, helping clinicians identify pregnancies that may benefit from closer monitoring or earlier intervention.
The study, published by JMIR Publications, points toward a future in which prenatal risk assessment incorporates not only medical history, but also social, demographic, and behavioral factors that can shape pregnancy outcomes.
Original article:
Li S, Tan D, Zhang J, Mahyuddin A, Ramlal H, Illanes S, Monckeberg M, Plaza A, Morgan M, Kemp M, Ngiam K, Lindgren P, Kublickas M, Kublickiene K, Weng R, Yee S, Choolani M
Machine Learning–Based First-Trimester Antenatal Risk Prediction for Adverse Maternal and Neonatal Outcomes: Multicenter Model Development Study
J Med Internet Res 2026;28:e88450
URL: https://www.jmir.org/2026/1/e88450
DOI: 10.2196/88450
About JMIR Publications
JMIR Publications is a leading open access publisher of digital health research and a champion of open science. With a focus on author advocacy and research amplification, JMIR Publications partners with researchers to advance their careers and maximize the impact of their work. As a technology organization with publishing at its core, we provide innovative tools and resources that go beyond traditional publishing, supporting researchers at every step of the dissemination process. Our portfolio features a range of peer-reviewed journals, including the renowned Journal of Medical Internet Research.
To learn more about JMIR Publications, please visit jmirpublications.com or connect with us via X, LinkedIn, YouTube, Facebook, Bluesky, and Instagram.
Head office: 130 Queens Quay East, Unit 1100, Toronto, ON, M5A 0P6 Canada
Media contact: communications@jmir.org
The content of this communication is licensed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, published by JMIR Publications, is properly cited.