Preeclampsia, characterized by sudden onset high blood pressure prior to delivery, complicates approximately 2% to 8% of pregnancies globally. The condition’s pathophysiology involves complex interactions among the placenta, maternal cardiovascular system, and immune responses. Its late manifestation, often after 34 weeks’ gestation, presents considerable challenges for timely diagnosis and intervention, with serious repercussions including maternal organ damage and fetal growth restrictions.

Traditional predictive models focus primarily on early pregnancy indicators, aiming to stratify risk during the first trimester. These algorithms enable preventive strategies such as aspirin prophylaxis and enhanced surveillance for high-risk patients. However, these early models lack precision in forecasting late-onset and term preeclampsia cases, which constitute the majority of diagnoses. Consequently, clinicians have had limited tools to anticipate onset during the late stages of pregnancy, constraining their capacity to deploy tailored interventions.

Addressing this clinical void, a multidisciplinary team spearheaded the development of a machine-learning algorithm trained on an extensive dataset comprising nearly 59,000 deidentified pregnancies from three NewYork-Presbyterian hospitals. The core training cohort consisted of 35,895 pregnancies delivered at NewYork-Presbyterian/Weill Cornell Medical Center between October 2020 and May 2025. By integrating temporal clinical variables and leveraging advanced computational methods, the model dynamically updates preeclampsia risk scores as new health data become available, closely mirroring the clinical workflow.

Key components impacting model performance include vital signs, laboratory findings, and demographic variables. Notably, blood pressure measurements emerged as the dominant predictor throughout gestation. Early third-trimester abnormalities in routine blood laboratory tests also contributed significant predictive value. These lab markers likely reflect evolving placental dysfunction, highlighting the model’s biological interpretability in addition to its statistical power.

As the pregnancy advances into the later third trimester, the influence of parameters such as maternal age and white blood cell count intensifies. Elevated leukocyte levels suggest systemic inflammation may be a critical mediator of preeclampsia pathogenesis during this period. This nuanced understanding provides a potential window for distinguishing phenotypic subtypes of preeclampsia, stratified by underlying mechanisms such as placental insufficiency versus inflammatory pathways.

Validation of the algorithm on independent cohorts from NewYork-Presbyterian Lower Manhattan Hospital (8,664 pregnancies) and Brooklyn Methodist Hospital (14,280 pregnancies) demonstrated robust generalizability and predictive accuracy. The model’s capacity to identify high-risk pregnancies around the 34-week mark offers clinicians a valuable lead time for intensified monitoring, pharmacologic blood pressure control, and strategic decisions regarding timing of delivery to optimize maternal-fetal outcomes.

Unlike prior static risk calculators that provide a single timepoint assessment, this continuously updated model dynamically incorporates newly acquired electronic health data. This feature aligns closely with real-world clinical decision-making processes in late pregnancy, enabling personalized risk stratification and responsive management plans as patient status evolves.

The work underscores the power of artificial intelligence to transform prenatal care by uncovering complex, temporally dependent risk patterns otherwise imperceptible through conventional analytic methods. It also opens avenues for further investigation into the differential etiologies of preeclampsia manifestations at distinct gestational stages. Clarifying these mechanisms could inform more tailored and effective therapeutic interventions targeting the root causes of the disorder.

Future research directions include prospective clinical trials to evaluate the model’s impact on patient outcomes and its integration into routine obstetric practice. There is also interest in deploying similar AI-driven predictive frameworks for other pregnancy-related complications, potentially broadening the scope of precision medicine in maternal-fetal health.

This innovative model represents a significant step forward in the quest to preemptively identify and mitigate preeclampsia during one of the most vulnerable periods of pregnancy. Its development reflects a successful confluence of clinical expertise, advanced data science, and translational research aimed at improving the safety and well-being of families worldwide.

Subject of Research:
Preeclampsia risk prediction using machine-learning models based on longitudinal electronic health record data in late pregnancy.

Article Title:
Machine-Learning Model for Dynamic Prediction of Preeclampsia Risk in Late Pregnancy.

News Publication Date:
6-Mar-2026

Web References:
Weill Cornell Medicine – Dr. Fei Wang
Weill Cornell Medicine – Dr. Zhen Zhao
Weill Cornell Medicine – Dr. Tracy Grossman

References:
Published in JAMA Network Open, March 6, 2026.

Image Credits:
Not provided.

Keywords
Pregnancy, Preeclampsia, Machine Learning, Artificial Intelligence, Electronic Health Records, Maternal-Fetal Medicine, Predictive Modeling, Placental Dysfunction, Inflammation, Blood Pressure, Third Trimester, Obstetrics

The implications of this research are profound, particularly for healthcare providers who seek to tailor risk assessments for expecting mothers and their babies. As the study indicates, the risk of adverse pregnancy outcomes can differ dramatically depending on a variety of factors, including the interplay between maternal and fetal characteristics. Nathan Blue, MD, the senior author of the study, emphasized that the AI model developed by the team revealed unexpected risk combinations that experienced clinicians might not have recognized.

For clinicians, understanding the nuances of fetal growth is essential, especially for those within the bottom ten percent of the weight spectrum. Traditional clinical guidelines often mandate intense monitoring for these scenarios, leading to unnecessary emotional and financial stress for families. However, the researchers identified that among this group, the risk of negative outcomes could range significantly, presenting an opportunity for healthcare practitioners to reassess protocols and optimize care.

Intriguingly, the findings usher in a new perspective regarding fetal sex and pre-existing maternal conditions. Historically, it has been established that female fetuses might possess a slight advantage over male counterparts in avoiding pregnancy complications. Yet, in cases where a pregnant individual has diabetes, this trend is inverted—female fetuses demonstrated a higher risk of complications. This revelation highlights the capabilities of AI to detect patterns that defy conventional medical assumptions, urging healthcare providers to adopt a more nuanced approach.

The study utilized a dataset collected nationwide, which encompassed a variety of factors attributing to each pregnancy, such as the mother’s social support, medical history, and fetal development parameters. By employing AI to conduct advanced data analysis, the researchers identified complex associations among these factors that pose risks to pregnant individuals and their infants. These associations could lead to wiser decisions regarding prenatal care and a more personalized approach to managing pregnancy risks.

One of the noteworthy attributes of the explainable AI model is its ability to make sense of intricate data relationships and deliver transparent, interpretable conclusions. Unlike traditional AI systems, known as "black box" models, which obscure the reasoning behind their conclusions, the explainable AI framework provides a comprehensive view of how various factors contribute to risk estimation. This level of transparency is crucial in medical decision-making where understanding bias and variable interaction can drastically affect clinical outcomes.

As healthcare moves toward more data-driven practices, the reliance on models that can accurately predict risk based on individualized factors stand to transform the landscape of obstetrics. Clinicians have long relied on experience and intuition, but this study suggests that integrating AI can bolster decision-making processes, minimizing biases that may stem from human judgment. This paradigm shift could lead to standardized risk assessments that cater to unique patient contexts while still being backed by robust data analysis.

Continued research is needed to validate these findings in diverse populations and ensure their applicability in clinical settings. Researchers aspire to develop a model that can accurately predict risks in real-world pregnancy scenarios beyond the confines of their initial dataset. With the advancement of explainable AI, there is optimism that tailored risk assessments could become commonplace, enhancing the quality of care provided to expectant mothers.

As this research evolves, it underscores the dynamic and often unpredictable landscape of pregnancy care. Unraveling the complexities of pregnancy outcomes is paramount for improving maternal and fetal health. By harnessing the collaborative strengths of AI and clinical expertise, healthcare professionals can move toward a future where personalized care is the norm, ultimately leading to healthier pregnancies and improved infant outcomes.

In conclusion, the revelations from this AI-driven study signify a pivotal moment in the understanding of pregnancy risks. As researchers continue to explore these intricate dynamics, the hope remains that such advancements will foster innovative approaches to prenatal care and encourage the sustained application of AI in improving health outcomes for mothers and infants alike. The transition toward leveraging data science in obstetrics not only heralds a new era in healthcare but also holds the promise of better-informed medical practices that prioritize the individual needs of each patient.

The remarkable findings of this study announced in BMC Pregnancy and Childbirth exemplify the convergence of technology and healthcare in rethinking traditional approaches to risk assessment and management in pregnancy. If the potential of explainable AI is realized fully, it could contribute to a more informed, precise, and compassionate healthcare system that puts the well-being of mothers and their children at its forefront.

Subject of Research: Understanding risk factors in pregnancies using AI
Article Title: AI-based analysis of fetal growth restriction in a prospective obstetric cohort quantifies compound risks for perinatal morbidity and mortality and identifies previously unrecognized high risk clinical scenarios
News Publication Date: 30-Jan-2025
Web References: BMC Pregnancy and Childbirth
References: Not provided
Image Credits: Sophia Friesen / University of Utah Health

Keywords

Artificial intelligence, Pregnancy, Pregnancy complications, Risk assessment, Obstetrics