An artificial intelligence (AI) based analysis of almost 10 000 pregnancies has discovered previously unidentified combinations of risk factors linked to serious negative pregnancy outcomes, including stillbirth, say the researchers.
The study, led by the University of Utah, USA, also found there may be up to a tenfold difference in risk for infants who are currently treated identically under clinical guidelines.
Nathan Blue, MD, the senior author, said that the AI model the researchers generated helped identify a “really unexpected” combination of factors associated with higher risk, and was an important step toward more personalised risk assessment and pregnancy care.
The results were published in BMC Pregnancy and Childbirth.
Unexpected risks
The researchers started with an existing dataset of 9 558 pregnancies nationwide, which included information on social and physical characteristics ranging from pregnant women’s level of social support to their blood pressure, medical history, and foetal weight, as well as the outcome of each pregnancy.
By using AI to look for patterns in the data, they identified new combinations of maternal and foetal characteristics that were linked to unhealthy pregnancy outcomes like stillbirth.
Usually, female foetuses are at slightly lower risk for complications than male foetuses – a small but well-established effect. But the research team found that if a pregnant woman has pre-existing diabetes, female foetuses are at higher risk than males.
This previously undetected pattern shows that the AI model can help researchers learn new things about pregnancy health, said Blue, an assistant professor of obstetrics and gynaecology in the Spencer Fox Eccles School of Medicine at the University of Utah.
“It detected something that could be used to inform risk that not even the really flexible, experienced clinician brain was recognising,” he added.
The researchers were especially interested in developing better risk estimates for foetuses in the bottom 10% for weight, but not the bottom 3%.
These babies are small enough to be concerning, but large enough that they are usually perfectly healthy. Figuring out the best course of action in these cases is challenging: will a pregnancy need intensive monitoring and potentially early delivery, or can it proceed largely as normal?
Current clinical guidelines advise intensive medical monitoring for all such pregnancies, which can represent a significant emotional and financial burden.
But the researchers found that within this foetal weight class, the risk of an unhealthy pregnancy outcome varied widely, from no riskier than an average pregnancy to nearly 10 times the average risk.
The risk was based on a combination of factors such as foetal sex, presence or absence of pre-existing diabetes, and presence or absence of a foetal anomaly, such as a heart defect.
Blue said the study only detected correlations between variables and doesn’t provide information on what actually causes negative outcomes.
The wide range of risk is backed up by physician intuition, Blue said; experienced doctors are aware that many low-weight foetuses are healthy and will use many additional factors to make individualised judgment calls about risk and treatment.
But an AI risk-assessment tool could provide important advantages over such “gut checks”, helping doctors make recommendations that are informed, reproducible, and fair.
For humans or AI models, estimating pregnancy risks involves taking a very large number of variables into account, from maternal health to ultrasound data. Experienced clinicians can weigh all these variables to make individualised care decisions, but even the best doctors probably wouldn’t be able to quantify exactly how they arrived at their final decision.
Human factors like bias, mood, or sleep deprivation almost inevitably creep into the mix and can subtly skew judgment calls away from ideal care.
To help address this problem, the researchers used a type of model called “explainable AI”, which provides the user with the estimated risk for a given set of pregnancy factors and also includes information on which variables contributed to that risk estimation, and how much.
Unlike the more familiar “closed box” AI, which is largely impenetrable even to experts, the explainable model “shows its work”, revealing sources of bias so they can be addressed.
Essentially, explainable AI approximates the flexibility of expert clinical judgment while avoiding its pitfalls. The researchers’ model is also especially well-suited to judging risk for rare pregnancy scenarios, accurately estimating outcomes for people with unique combinations of risk factors.
This kind of tool could ultimately help personalise care by guiding informed decisions for people whose situations are one-of-a-kind.
The researchers still need to test and validate their model in new populations to make sure it can predict risk in real-world situations.
But Blue is hopeful that an explainable AI-based model could ultimately help personalise risk assessment and treatment during pregnancy.
“AI models can essentially estimate a risk that is specific to a given patient’s context," he says, “and they can do it transparently and reproducibly, which is what our brains can’t do. This kind of ability would be transformational across our field.”
Study details
AI-based analysis of foetal growth restriction in a prospective obstetric cohort quantifies compound risks for perinatal morbidity and mortality and identifies previously unrecognised high risk clinical scenarios
Raquel Zimmerman, Edgar Hernandez, Mark Yandell et al.
Published in BMC Pregnancy & Childbirth on 30 January 2025
Abstract
Background
Foetal growth restriction (FGR) is a leading risk factor for stillbirth, yet the diagnosis of FGR confers considerable prognostic uncertainty, as most infants with FGR do not experience any morbidity. Our objective was to use data from a large, deeply phenotyped observational obstetric cohort to develop a probabilistic graphical model (PGM), a type of “explainable artificial intelligence (AI)”, as a potential framework to better understand how interrelated variables contribute to perinatal morbidity risk in FGR.
Methods
Using data from 9,558 pregnancies delivered at ≥ 20 weeks with available outcome data, we derived and validated a PGM using randomly selected sub-cohorts of 80% (n = 7645) and 20% (n = 1,912), respectively, to discriminate cases of FGR resulting in composite perinatal morbidity from those that did not. We also sought to identify context-specific risk relationships among inter-related variables in FGR. Performance was assessed as area under the receiver-operating characteristics curve (AUC).
Results
Feature selection identified the 16 most informative variables, which yielded a PGM with good overall performance in the validation cohort (AUC 0.83, 95% CI 0.79–0.87), including among “N of 1” unique scenarios (AUC 0.81, 0.72–0.90). Using the PGM, we identified FGR scenarios with a risk of perinatal morbidity no different from that of the cohort background (e.g. female foetus, estimated foetal weight (EFW) 3-9th percentile, no pre-existing diabetes, no progesterone use; RR 0.9, 95% CI 0.7–1.1) alongside others that conferred a nearly 10-fold higher risk (female foetus, EFW 3-9th percentile, maternal pre-existing diabetes, progesterone use; RR 9.8, 7.5–11.6). This led to the recognition of a PGM-identified latent interaction of foetal sex with pre-existing diabetes, wherein the typical protective effect of female foetal sex was reversed in the presence of maternal diabetes.
Conclusions
PGMs are able to capture and quantify context-specific risk relationships in FGR and identify latent variable interactions that are associated with large differences in risk. FGR scenarios that are separated by nearly 10-fold perinatal morbidity risk would be managed similarly under current FGR clinical guidelines, highlighting the need for more precise approaches to risk estimation in FGR.
See more from MedicalBrief archives:
MRI technique spots placental problems in foetuses in early weeks – US study
Biomarker can predict depression, poor foetal growth, in pregnancy