News • Screening for specific pregnancy complications

AI model to advance maternal health in low-resource settings

Aim for AI-driven risk stratification to reduce burden on labs, enable timely interventions

The right arm of a woman, with a band-aid with a heart on it

Siemens Healthineers, with funding from the Gates Foundation, plans to develop artificial intelligence (AI) to enable earlier prediction of pre-eclampsia and anemia, conditions that kill over a half million women and children each year and leave millions more in diminished health. The aim is to reduce laboratory burden in low-resource settings while enabling timely clinical interventions that improve maternal health outcomes and save lives.

Machine learning approaches will leverage complete blood count (CBC) data, alongside relevant patient metadata, to improve screening and risk stratification for pregnancy-related health conditions in low-resource environments. The resulting models will be used to derive an integrated maternal health score to support clinical decision-making and early risk intervention. “Healthcare AI will greatly contribute to predicting outcomes rather than just reacting to symptoms,” said Siemens Healthineers CEO Bernd Montag. “I am excited about this effort to make early diagnosis not just a possibility, but a scalable standard for women and children everywhere.”

This initiative builds on the work Siemens Healthineers is doing to close the gender health gap. Women spend a quarter more of their lives in poor health than men which burdens families, communities and economies.

Healthcare AI will greatly contribute to predicting outcomes rather than just reacting to symptoms
Bernd Montag

An in-kind technical contribution from Siemens Healthineers, supported by a grant from the Gates Foundation, will be used to develop and validate machine-learning models alongside partners in the Global South that can be deployed in low-resource settings. CBC and patient metadata such as ferratin levels will be used to build models to create a maternal health score for risk of pre-eclampsia and to flag anemia. Pre-eclampsia causes more than 76,000 maternal and 500,000 perinatal deaths a year, with by far the highest burden in low- and middle-income countries. Anemia is estimated to affect half a billion women 15-29 years of age and 269 million children 6-59 months of age worldwide. It is preventable and treatable and is four times more prevalent among women of reproductive age in developing countries than in developed ones, according to the WHO. Since complete blood count (CBC) tests are routinely prescribed and commonly performed as part of prenatal care, the proposed models will be trained using data from these existing, standard-of-care laboratory tests, eliminating the need for additional testing or added cost.

Siemens Healthineers will publish results on the validity of the algorithms and their use in healthcare settings at the conclusion of the project.

Source: Siemens Healthineers

18.01.2026