High-tech tool to perform low-cost health screening for newborns and mothers

UNIVERSITY PARK, Pa. — In 2017, nearly 300,000 women died during or following childbirth, but most of those could have been prevented, according to the World Health Organization. Additionally, four million babies die each year before reaching their first birthday. 

In an effort to save many of these lives, a new, $1.9 million grant from the National Institute of Biomedical Imaging and Bioengineering will enable an interdisciplinary team of Penn State researchers to develop software that can evaluate the health of a newborn and their mother with only a photograph of the placenta. 

The placenta, an organ that provides nutrients and oxygen to a developing fetus, is typically delivered minutes after a baby is born. Rapid evaluation of the placenta can provide valuable information about the health of both the baby and mother, but a pathological examination requires a specialized pathologist. This evaluation of the placenta only occurs in about 20% of births in the United States. In less wealthy nations where there are fewer pathologists per capita, evaluation of the placenta is usually less common and often completely unavailable. 

“By understanding placentas, we can understand a lot about health — both on the mom’s side and the baby’s side,” said Alison Gernand, associate professor of nutritional sciences and one of the principal investigators on the project. “But placentas are hard to assess, and this work currently requires a pathologist. We are not trying to replace pathologists, but we want to create something easy to use that can provide good information about any placenta, anywhere.” 

The researchers explored a broad array of funding possibilities to continue this work, and this new grant will make progress possible. The final software would make the evaluation of placentas possible in a wide range of birth settings around the world. 

To evaluate a placenta with the software, the user only needs to blot excessive blood with a paper towel and then take a digital photograph of the placenta. The software will evaluate the basic characteristics of the placenta — including size, color, shape, and circumference — and check for signs of infection to identify potential pathologies. Health care providers can then use this information to help them assess the health of the newborn and mother. 

“When it is available, information from placental pathology is already used to help understand and explain critical events in pregnancy,” said Kelly Gallagher, assistant research professor of nursing and investigator on this project. “This information is also used to counsel families for future pregnancies and in the clinical care of medically vulnerable newborns. Rapid access to placental pathology information has the potential to dramatically improve care.”  

The creation of this software requires expertise across multiple domains. The team includes researchers from Penn State’s College of Health and Human Development, College of Information Sciences and Technology and Ross and Carol Nese College of Nursing.  

Each member of the project’s leadership team contributes to the research in a separate way. Gernand studies the placenta and pregnancy outcomes in low-resource settings. James Wang, distinguished professor of information sciences and technology and one of the principal investigators on the project, studies how to interpret and use large, complex, visual data. Jeffery Goldstein, assistant professor of pathology at Northwestern University’s Feinberg School of Medicine and one of the principal investigators on this project, studies bioimaging and informatics to improve diagnosis and treatment of problems in maternal-child health. Gallagher, a nurse-midwife, will coordinate the clinical aspects of data collection and provide expertise on maternal and infant health outcomes. 

The researchers have already developed a prototype of the artificial intelligence software needed to evaluate the placentas. The algorithm that powers their software was granted a patent in the United States. Once the software is complete, the researchers are hoping to develop a mobile app that can perform the same evaluations. Making the software available in a mobile app would truly allow people in almost any birth setting to evaluate placentas during birth. 

“We have developed and evaluated the software primarily using a large and comprehensive dataset collected over the years by our research partners at the Northwestern Memorial Hospital,” Wang said. “We are currently extending the capacity of the software so that it can reliably handle the diverse imaging infrastructure and lighting conditions in various hospitals and delivery settings. We will be expanding the software’s classification power so that more pathologies can be identified. We are also integrating the images with clinical data to improve accuracy.” 

Additionally, the new grant will enable the researchers to build a first-of-its-kind dataset of more than 50,000 images and expert pathology reports on placentas from Northwestern Memorial Hospital in Chicago, Magee-Womens Hospital in Pittsburgh, and Mbarara Regional Referral Hospital in Uganda. The records will capture a range of pregnancies with healthy and adverse outcomes. This dataset will be used to train and validate the software so that the software provides information that is trustworthy in a variety of lighting settings and with a variety of cameras.  

Beyond health care, the software will also serve as a useful tool for studying pregnancy. Researchers will be able to collect data instantly on placentas in any delivery setting at very low cost. 

“Previous research has revealed how much the placenta can tell us about immediate and long-term health of the mother and newborn,” Gernand said. “With this project, we hope to break the barriers of cost, time, and expertise needed to obtain information about the placenta right at birth. We believe this project will save many lives and increase the level of scientific knowledge about pregnancy, and we are so grateful to the National Institute of Biomedical Imaging and Bioengineering for this opportunity.”