AI Tool Could Enhance Placental Examination and Neonatal Care
Researchers at Northwestern Medicine (IL, U.S.) and Penn State (PA, U.S.) have developed an AI tool that could enhance placental examinations, potentially making them faster and improving neonatal and maternal care.
PlacentaCLIP+, an AI tool discussed in the journal Patterns, holds great potential to address placental infections and neonatal sepsis, while also improving the often-overlooked practice of placental examination. This is particularly important given the complexities of such examinations and the occasional constraints on resources for their thorough implementation.
The Importance of Placental Examination
Placental examination during pregnancy is crucial for the diagnosis of life-threatening conditions such as neonatal sepsis, which is a severe and widespread infection in newborns that can lead to organ failure or death, if not treated promptly. However, in most pregnancies around the world, placental examinations are rarely done, especially in resource-limited settings.
This is often due to several factors, including the inherent challenges of examining a complex organ, the unpleasant nature of gross anatomical examination, and the ongoing lack of consensus regarding disease classification associated with the placenta.
A more comprehensive and systematic analysis of the placenta could become a highly effective means of early detection for a range of pathologies and infections.
Additionally, many clinicians may undervalue the importance of placental examination and thus, it is often overlooked or inadequately performed.
“Discarding the placenta without examination is a common but often overlooked problem. It is a missed opportunity to identify concerns and provide early intervention that can reduce complications and improve outcomes for both the mother and the baby.”
Alison D. Gernand, Associate Professor in the Penn State College of Health and Human Development (HHD), Department of Nutritional Sciences and Contact Principal Investigator on the Project.
For this reason, PlacentaVision, a consortium of academic institutions focused on analyzing placentas with AI, has developed an innovative AI tool that uses machine learning to assess the placenta from a single photograph.
Designed to make placental examination more accessible, PlacentaClip+ enables early detection of placental infections, reducing the risk of undiagnosed conditions and improving the chances of timely intervention for both mother and baby.
How The Tool Works
PlacentaClip+ utilizes advanced AI algorithms and computer vision to analyze simple placental photographs, identifying potential abnormalities.
The tool is trained on a large and diverse dataset, which enhances its precision and robustness. Researchers gathered placental images and reports spanning 12 years, and this data was used for developing a model capable of analyzing new images.
The result was a system which, according to researchers, is user-friendly and could potentially be accessed via a smartphone app or integrated into medical record software. This app would allow doctors to receive prompt answers following delivery.
The early detection of placental infections using PlacentaCLIP+ could allow clinicians to administer antibiotics appropriately and closely monitor the infant for any signs of infection. This timely intervention could significantly improve outcomes by addressing potential health risks before they escalate.
Accessibility & Global Impact
PlacentaCLIP+ could also be particularly valuable in regions with limited medical resources, making placental examination more accessible to those with restricted access to adequate healthcare facilities.
“In low-resource areas; places where hospitals don’t have pathology labs or specialists; this tool could help doctors quickly spot issues like infections from a placenta. In well-equipped hospitals, the tool may eventually help doctors determine which placentas need further, detailed examination, making the process more efficient and ensuring the most important cases are prioritized.”
Yimu Pan, Doctoral Candidate in the Informatics Program from the College of Information Sciences and Technology (IST) and lead author of the study.
AI’s Potential in Neonatal Care
Recently, AI tools have shown significant promise in enhancing modern healthcare fields, including cancer research, vaccine production and intradialytic hypotension prediction among others.
By streamlining the placental examination process, PlacentaCLIP+ could aid in prioritizing cases that require immediate attention, improving overall efficiency in clinical practice. However, before the tool can be widely implemented, efforts must be directed towards further refining its adaptability to diverse clinical environments and ensuring its robustness under varied imaging conditions.
The next steps involve efficiently embedding the tool into the PlacentaVision project to provide healthcare systems with a mobile app designed to enhance neonatal health outcomes.
“Our next steps include developing a user-friendly mobile app that can be used by medical professionals; with minimal training; in clinics or hospitals with low resources. The user-friendly app would allow doctors and nurses to photograph placentas and get immediate feedback and improve care.”
Yimu Pan, Doctoral Candidate in the Informatics Program from the College of Information Sciences and Technology (IST) and lead author of the study.