Researchers have identified two common drugs that may, when given together during pregnancy, prevent premature births.
The finding is the fruit of a new, Stanford Medicine-led, artificial intelligence-powered technique for screening drugs to prevent early labor. It uses a comprehensive atlas of the immune system, which the researchers built to be accurate at a cell-by-cell level, to create “digital twins” of the immune systems of individual pregnant women for virtual drug testing.
The study, which is publishing online Oct. 21 in Science Advances , builds on two decades of Stanford Medicine research on how the maternal immune system shifts during pregnancy. When the immune clock of pregnancy runs too quickly, preterm labor can result. Being born prematurely, meaning three or more weeks before the due date, carries a host of risks for the baby. Prematurity is now the leading cause of death in children under age 5 worldwide.
After screening several possible treatments with the digital twin system, the researchers identified one drug combination that promises to markedly lower the risk of early labor. It shows so much potential for averting preterm birth that researchers are starting a clinical trial in real patients.
“We’re on the brink of having a real impact for the treatment of preterm birth, a global health problem that affects 10% of pregnancies worldwide,” said senior study author Brice Gaudilliere , MD, PhD, professor of anesthesiology, perioperative and pain medicine. It’s been decades since there was a new pharmacological intervention for preventing preterm birth, he noted.
The winning drug combination was aspirin and lansoprazole. Low-dose aspirin alone has a modest ability to prevent premature birth, prior research has shown. Lansoprazole is sometimes prescribed in pregnancy to treat acid reflux.
“In the digital twin system, these two drugs in combination had a large effect on the delay of labor, 15 times higher than aspirin alone,” Gaudilliere said.
Modeling how the immune clock ticks
Although the triggers of labor in humans are still not fully explained, Stanford Medicine research has demonstrated that immune signals play a key role in readying the mother’s body for labor.
Early in pregnancy, the mother’s immune system adjusts to tolerate the immunologically different fetus. Late in pregnancy, a series of immune changes — including a switch toward pro-inflammatory signals — help prepare the body for labor. When the immune clock of pregnancy runs too fast, with pro-inflammatory signals activated too soon, early labor can result.
The new digital twin system, called SIMCO (simulated immune modeling of clinical outcomes), uses AI and machine-learning techniques to integrate into its model an enormous amount of data on how all the body’s immune cells behave during pregnancy.
To create the model, the researchers first collected blood samples from pregnant women, then exposed immune cells from these samples to many different drugs.
“We measured responses from a quarter of a billion cells, training the algorithm on a massive single-cell dataset,” Gaudilliere said.
Such a deep foundation of real biological knowledge is a key element of building a working digital twin that realistically mimics an individual’s biology.
“A digital twin has the prerequisite that you understand a biological system very well,” said co-lead author Jakob Einhaus , MD, a postdoctoral scholar at Stanford Medicine. “The digital twin represents the complexity and connections in the immune system.”
Einhaus shares lead authorship of the study with graduate students Peter Neidlinger and Olivier Fondeur, and with Masaki Sato, MD, PhD, who was a postdoctoral scholar at Stanford Medicine when the research was conducted and is now at the National Center for Child Health and Development in Tokyo.
Once they had constructed the cell-response model, the researchers integrated longitudinal data from 63 pregnancies, linked to information about the patients’ clinical outcomes, to help the model understand which patterns of cell behavior match which clinical states and to train the model to understand patient-to-patient variability.
The final algorithm has both the ability to predict how individual immune cells will respond to various drugs, and — with a bit of starting knowledge about a specific patient, such as that obtained from a small blood sample — what this means clinically for the patient. For example, do findings from the digital twin predict that a certain medication will make her immune clock of pregnancy run faster or slower?
“You’re making the prediction for one individual based on knowledge of millions of single cells from dozens of patients,” Einhaus said.
Common medications may delay delivery
After validating that SIMCO accurately forecasts time to labor — by comparing its predictions with what happened in the pregnancies of the patients in their dataset — the scientists used the digital twin system to evaluate nine possible drug regimens to see whether they would likely speed up or slow down the immune clock of pregnancy. The drugs were chosen based on a drug-repurposing pipeline — developed by a group led by study coauthor Marina Sirota, PhD, a professor of pediatrics at the University of California, San Francisco — because they were already known to be safe for pregnancy.
The researchers evaluated multiple copies of each digital twin, comparing what would happen to the immune system in treated versus untreated scenarios for each individual, with each drug.
The research team was surprised by how strongly the model predicted that the aspirin-lansoprazole combination would delay labor.
“Our findings suggest that salicylic acid [aspirin] and lansoprazole act synergistically … this synergy may enhance their immunomodulatory effect,” the investigators write in their paper.
The study also found that taking folic acid — a B vitamin already recommended in pregnancy to reduce the risk of spinal cord defects in the fetus — can delay immunological progression toward labor.
“We’re giving folic acid for spina bifida prevention, but maybe, unknowingly, we’re also helping the maternal immune system adapt to pregnancy,” Einhaus said. “We didn’t know it had such profound immunomodulatory properties.”
The digital twin model gave the researchers information about which specific immune signals were predicted to change with each of the medications, details that could help contribute to further understanding premature labor’s exact mechanics.
For instance, for the aspirin-plus-lansoprazole combination, immune processes that help pregnancy continue are enhanced, whereas those involved in triggering labor are inhibited, Gaudilliere said. “So it all makes sense biologically. That was super exciting.”
The model lets researchers test many possible drugs and drug combinations before exposing any patients, offering an ethical way to narrow down possible therapies for early labor without risking real pregnancies.
Because the model captures variation among patients, it could also show that not all individuals respond to each drug equally well. Being able to predict likely responders and non-responders would be a valuable addition to planning clinical trials, the research team said: By restricting clinical trial enrollment to likely responders to any drug being tested, researchers could get clear answers about a drug’s effectiveness from smaller trials.
The researchers tested the drug combination of aspirin plus lansoprazole in an animal model of an inflammatory state in pregnancy, demonstrating that the combination delays the onset of labor in that context. They subsequently obtained approval from the U.S. Food and Drug Administration to try the combination in a human clinical trial.
“We’re going in a short time from discovery work — done the Stanford way, using technology, AI and really understanding the mechanism of a disease process — all the way to identifying a potentially impactful new treatment and testing in patients,” Gaudilliere said.
Researchers from UC San Diego and the AP-HP Sorbonne University Hospital Group in Paris also contributed to the study.
This work was supported by the Stanford Maternal and Child Health Research Institute, the March of Dimes Prematurity Research Center at Stanford, the March of Dimes Prematurity Research Center at UCSF, the Center for Human Systems Immunology at Stanford, the Charles and Mary Robertson Foundation, the National Institute of Health (grants P01HD106414, K99HD115829 and 1K99HD105016), and a Society for Reproductive Investigation Bayer Discovery/Innovation grant.
# # #
About Stanford Medicine
Stanford Medicine is an integrated academic health system comprising the Stanford School of Medicine and adult and pediatric health care delivery systems. Together, they harness the full potential of biomedicine through collaborative research, education and clinical care for patients. For more information, please visit med.stanford.edu .
Science Advances
Computational simulation/modeling
Cells
Single-cell-level digital twins for preterm birth prevention strategies
21-Oct-2026