Purdue technology has been studied as a potential tool for identifying women at higher risk of preeclampsia

Purdue technology has been studied as a potential tool for identifying women at higher risk of preeclampsia

A researcher from Purdue University's Weldon School of Biomedical Engineering is participating in a two-year research study that will evaluate approaches to monitoring the health of pregnant women in Africa and informing future efforts to reduce maternal mortality.

Young Kim, professor of biomedical engineering, University Faculty Scholar and Showalter Faculty Scholar, has developed an innovation that is being studied as a potential tool for identifying women at higher risk of developing preeclampsia.

Preeclampsia is a leading cause of maternal mortality, premature birth, stillbirth and neonatal death worldwide. The two-year study is funded through the Gates Foundation's Grand Challenge Awards to reduce the burden of preeclampsia.

The solution uses a patented, non-invasive computer vision method called mHealth Conjunctiva AI Imaging to analyze smartphone photos of the eyeball to provide early prediction of preeclampsia. The method extracts microvascular patterns from photos of the conjunctiva, a thin and transparent membrane that covers the inner eyelids and the white part of the eyeball. It is used in collaboration with AMPATH in Kenya.

Kim disclosed the computer and color vision methods to Purdue Innovate's Office of Technology Commercialization, which has filed patents to protect intellectual property.

The work is part of Purdue's President's One Health Initiative, which includes research at the intersection of human, animal and plant health and well-being.

About preeclampsia

Preeclampsia is one of the most common pregnancy complications in which persistent hypertension develops during pregnancy, usually after 20 weeks; it can also develop in the postnatal period. Early diagnosis and treatment are crucial to prevent serious complications for mother and child.

The World Health Organization reports that preeclampsia affects up to 8% of all pregnancies worldwide. Approximately 46,000 mothers and approximately half a million fetuses or newborns die each year due to preeclampsia.

Preeclampsia begins gradually and the diagnosis can either be missed or made too late. If left untreated, preeclampsia can be fatal for both mother and child. A woman with preeclampsia may have high blood pressure, high protein levels in the urine that indicate kidney damage, or other signs of organ damage.

About the innovation of photo analysis

During a two-year study of ongoing clinical work, researchers at Purdue will use computer and color vision methods developed to analyze smartphone photos. Through a partnership called AMPATH Kenya, which works extensively with local communities, they will recruit 1,600 pregnant women in western Kenya for the study at Moi University.

By combining radiomics with supervised learning, we extract microvascular patterns that may be clinically relevant from unmodified photos of the conjunctiva rather than directly imaging the retina. Our team is among the first to identify the conjunctiva as a promising imaging site that offers an alternative insight into health conditions and diseases, as reported in the journals npj Digital Medicine, Science Advances and IEEE Transactions on Image Processing.”

Young Kim, Professor of Biomedical Engineering, Purdue University

Kim said numerous studies support the connection between microvascular abnormalities such as narrowing and constructions with high blood pressure.

“Several previous studies found that the changes preceded the clinical onset of preeclampsia,” he said. “Microvascular changes in the retina were observed in the first weeks of pregnancy and were associated with increased peripheral resistance before blood pressure increased.”

Kim said traditional computer vision analysis is limited because it requires specialized equipment such as retinal fundus imaging systems. But Purdue's mobile health method of analyzing smartphone photos removes this significant obstacle.

“Our non-invasive solution eliminates the need for specialized equipment,” he said. “Smartphones have recently transformed healthcare in resource-limited settings, where community health workers are often equipped with mobile health apps to connect with healthcare professionals even from remote areas.”

Kim said several milestones have been set to advance the work.

“Our first step will be to refine the prediction model to specifically target preeclampsia rather than general maternal hypertension,” he said. “Next, we will develop a minimum viable mobile app to support scalable validation.”

Sources: