The advents of AI have taken over the healthcare sector by boom and its quest for replicating human intelligence has placed a number of great innovations to drive better care delivery practices across the industry. From providing better opportunities to researchers for medical innovation to aiding doctors and clinicians with its services the technology has revamped the entire healthcare platform.
Recently, another use of AI has been discovered in the domain of diagnosis for maternity care. Besides the traditional sonography technique that still exists, the world was in need of better analysis to understand child development in a fetus. This analysis would help in understanding any undiscovered situations in pregnancy that might need immediate action.
Pennsylvania State University’s recent research explored the interesting use case of AI in analyzing placentas that provides all the key information related to the mother and the baby, once the child is conceived. According to Alison Gernand, the Assistant Professor of Nutritional Sciences at the Penn State’s College of Health and Human Development, the placentas drive everything to do with pregnancy for the mother and the progeny. But, unfortunately, as the situation is today, the world is missing out on placenta data for as many as 95 percent of the births.
This compelled and pushed the urgent need to create a process that requires fewer resources and allows researchers to gather more comprehensive data regarding pregnancy. As quoted by James Warner in an article, the data would help in examining how placentas are directly linked to maternal and fetal health outcomes. The procedure will also aid better diagnosis of placentas in minutes rather than days and without the need for any special equipment.
AI can produce a more accurate, automated and near-immediate placental diagnosis through computerized photographic image analysis. This would further allow the hassle-free examination of placentas in the least amount of time making it accessible to everyone out there.
The computerized image analysis technology analyzes an image of each side of the placenta after delivery and produces a report with information that could inform the clinical care of the mother and child including whether the fetus was getting enough oxygen in the womb.
The research was based on the analysis of 13,000 high-quality images of placentas and the corresponding pathology reports from Northwestern Memorial Hospital in Chicago. The team of researchers, then, labeled a training set of images with data points critical to understanding the placenta, which was used to train neural networks to automatically analyze unlabeled placental images to detect features linked to abnormalities and potential health risks.
Further, the predictions by Penn State system and the original pathology reports were compared which demonstrated the system’s high accuracy and clinical potential.
According to James Wang, a professor in Penn State’s College of Information Sciences and Technology, “past analyses have typically examined features independently and used a limited number of images. Our tool leverages artificial intelligence and a large and comprehensive data set to make multiple decisions at the same time by treating the different parts of the placenta as complementary. To our knowledge, this is the first system for comprehensive, automated placental analysis.”
Professor Alison Gernand said, “Even in very low-resource areas, someone typically has a smartphone. Our goal is for a medical professional or trained birth attendant to take a photo which, after analysis through licensed software, could provide immediate information that aids in the care of the mother and baby.”