'Digital twins' of immune system in pregnancy identify drugs to prevent early labor

Researchers at Stanford Medicine have developed a groundbreaking technique using artificial intelligence to identify two common drugs that may prevent premature births when used together during pregnancy. The study, published in Science Advances, builds upon two decades of research on how the maternal immune system changes during pregnancy.

The digital twin system created by the researchers allows for virtual drug testing on individual pregnant women's immune systems at a cell-by-cell level. By analyzing blood samples from pregnant women and exposing immune cells to various drugs, the algorithm was trained on a massive single-cell data set to understand how the immune cells respond to different treatments.

The study identified aspirin and lansoprazole as the most promising drug combination for delaying labor. Low-dose aspirin has previously shown a modest ability to prevent premature birth, while lansoprazole, sometimes prescribed for acid reflux during pregnancy, was found to enhance the immunomodulatory effect when used in combination with aspirin.

The digital twin system, called SIMCO (simulated immune modeling of clinical outcomes), integrates data on how all the body's immune cells behave during pregnancy. By training the algorithm on this vast amount of real biological knowledge, the researchers were able to predict how individual immune cells would respond to various drugs and what this means clinically for each patient.

The combination of aspirin and lansoprazole showed a 15 times higher effect in delaying labor compared to aspirin alone. This finding has the potential to significantly reduce the global health problem of preterm birth, which affects 10% of pregnancies worldwide and is the leading cause of death in children under age 5. A clinical trial is now underway to further test the effectiveness of this drug combination in real patients.