They aimed to identify a small set of signals detectable during the first 16 weeks of pregnancy that could form the basis of a simple and inexpensive diagnostic test that can be used in low-, middle- and high-income countries. To estimate the accuracy of the machine learning models, the researchers first built the models with data from the Discovery Cohort and then confirmed the results by testing their performance on data from women in the Validation Cohort.
When you reduce preeclampsia, you probably also reduce preterm births. It’s a double whammy of good impacts.
A prediction model using a set of nine urinary metabolites was highly accurate, the researchers found. These urinary markers, in samples taken before week 16 of pregnancy, strongly predicted who would later develop preeclampsia. Test performance was measured by a statistical standard used in machine learning called the area under the characteristic curve. An AUC of 1 for a test with two possible outcomes indicates a perfect prediction, while an AUC of 0.5 indicates no predictive value, as do results obtained from a coin toss. For urinary markers, the AUC was 0.88 in the discovery cohort and 0.83 in the validation cohort, indicating high predictive ability.
Measuring the same set of urinary metabolites in samples taken throughout pregnancy produced similar predictive power, with an AUC of 0.89 in the discovery cohort and 0.87 in the validation cohort.
The researchers confirmed that their model had stronger predictive power than using only clinical characteristics linked to a pregnant woman’s risk of preeclampsia, such as chronic hypertension, high body mass index and carrying twins.
A set of nine proteins measured in blood performed almost as strongly, with an AUC of 0.84.
The researchers also created a predictive model combining participants’ clinical characteristics with urinary metabolites, which allowed them to predict preeclampsia early in pregnancy with an AUC of 0.96. The clinical characteristics of the combined model are data already collected as part of standard medical records, such as patient age, height, body mass index, and pre-pregnancy hypertension.
“This data collection is routine and could serve as a first level of triage,” Agheeapour said. “We envision that patients who the data show to be at risk could receive the most comprehensive urine test.”
Discover the biology of the disease
Stanford Medicine researchers are also opening windows into the biology of preeclampsia. Another study, published in February in Natureused cell-free RNA measurements to reveal biological clues about the origin of preeclampsia.
“The ability to eavesdrop on the conversation during pregnancy, by synchronously measuring molecules from the pregnant woman, the fetus and the placenta, is very useful in giving us clues about biological changes that contribute to disease,” said said Mira Moufarrej, PhD, lead author of the study. Nature paper, who was a graduate student in biological engineering when the research was conducted. The lead author of the paper is Stephen Quake, DPhil, Professor of Bioengineering and Applied Physics.
“The most striking changes occurred before 20 weeks gestation, whereas a diagnosis of preeclampsia is usually made more than 30 weeks gestation,” Moufarrej said. “It was surprising. We would expect changes in genetic signals when you see clinical symptoms, and this was happening much earlier in pregnancy.
Using 404 blood samples from 199 pregnant women, Moufarrej and his colleagues identified a set of 18 genes whose activity in early pregnancy predicted the development of preeclampsia.
The genes are consistent with what is known about the developmental biology of the disease, she noted.
Scientists hypothesize that in preeclamptic pregnancies, the placenta does not fully develop; his blood vessels may be too small. At first it’s OK because the fetus is small and doesn’t need much nutrition.
“But later in the pregnancy, the fetus grew, sending signals for more nutrition,” Moufarrej said. “At this point, the only solution to small blood vessels is more blood flow, so we see high blood pressure.” In severe cases, the pressure can cause the placenta to separate prematurely from the uterine lining, creating an emergency in which the baby must be delivered immediately.
The gene activity signals identified by Moufarrej and his colleagues came from genes involved in pathways consistent with the development of preeclampsia, such as tissues related to the endothelial system, the placenta and the brain. (The brain is relevant because full-blown eclampsia causes seizures.) The scientists plan to use the work as a basis for future studies of how the disease develops.
Global Benefits
Scientists involved in both studies will validate their predictive tests in much larger and more diverse populations of women, with the goal of creating tests for universal use.
Knowing more about how preeclampsia develops and how to predict it could have profound benefits for the world’s most vulnerable mothers, the researchers said, noting that about 86% of maternal deaths worldwide are produce in Asia and sub-Saharan Africa.
“That’s where this kind of testing is really needed, where resources are very scarce,” Marić said. Unlike women in high-income countries, many women in low-income areas give birth far from hospitals, which limits their access to emergency care when they have symptoms of preeclampsia or eclampsia. “If we can quickly identify high-risk pregnancies, we can help get these women to health facilities and prevent deaths.”
The Grounds the study was supported by the March of Dimes Prematurity Research Center at Stanford University School of Medicine, the Stanford Maternal and Child Health Research Institute, the Christopher Hess Research Fund, the National Institutes of Health (grants 1R01HL139844, 5RM1HG00773507, and R35GM138353) , Burroughs Wellcome Fund, the Alfred E. Mann Foundation, the Bill and Melinda Gates Foundation, the Thomas C. and Joan M. Merigan Endowment of Stanford University, and the Chan Zuckerburg Biohub Microbiome Initiative.
The Nature the study was supported by the Chan Zuckerberg Biohub, Global Alliance to Prevent Prematurity and Stillbirth, March of Dimes Foundation, National Science Foundation (DGE grant 1656518), Benchmark Stanford Graduate Fellowship, Stanford ChEM- H Chemistry Biology Interface Training Program, and the H&H Evergreen Fund.
#Stanford #Medicine #teams #discover #biomarkers #predict #common #pregnancy #complications