An Israeli startup is developing a non-invasive early detection method using artificial intelligence (AI) to identify genetic disorders in human embryos.
Via a simple blood test taken from the pregnant mother during the first trimester, IdentifAI Genetics can read the embryo’s entire DNA and provide in-depth analysis to detect genetic disorders.
Prof. Noam Shomron is the chief scientific officer and co-founder of IdentifAI, and he also heads the Functional Genomic Team at Tel Aviv University’s Faculty of Medicine.
Prof. Noam Shomron, chief scientific officer and co-founder of IdentifAI, and head of the Functional Genomic Team at Tel Aviv University’s Faculty of Medicine, Sept. 24, 2019. (Corinna Kern)
“In the pregnant mother there are tiny bits of DNA that come from the embryo, from the placenta,” Shomron told The Media Line. “If we look at a developing embryo, we can see tiny pieces of the placenta or embryonic DNA and if we could segregate it well enough and separate it then we’ll be able to read the entire DNA of the embryo.”
The AI could be used to identify any genetic disease that is caused by a minute number of changes in the DNA.
According to Shomron, there are several benefits to using this new tool over existing methods. Firstly, the procedure is non-invasive and therefore carries no risk for the pregnancy, unlike amniocentesis, in which a small amount of amniotic fluid is taken from the amniotic sac of a developing fetus. Secondly, while amniocentesis is usually carried out from weeks 15 to 20 of pregnancy, IdentifAI relies on a blood test taken already in the first trimester.
“You do it very early in the development of the embryo, in week 10 [of the pregnancy],” he said. “It’s comprehensive: it reads the DNA from beginning to end.”
IdentifAI relies on a new AI-based software tool known as Hoobari that was first developed by Tel Aviv University.
In addition to detecting genetic disorders in embryos, the technology might have important applications with regard to early cancer detection.
“If we’re talking about cancer, we’re probably a few years away but if we’re talking about embryonic development then we have already implicated it on real samples from genetic institutes,” Shomron said. “That means that we are now developing a product out of it and it should reach the market in one to two years.”
Shomron and researchers from Tel Aviv University also recently used the state-of-the-art technology to help study the electronic medical records of roughly 8,000 patients with blood infections at Tel Aviv’s Ichilov Hospital. In that study, researchers were able to determine with 82 percent accuracy which patients were at greater risk of serious illness as a result of blood infections.
The groundbreaking study was carried out by Yazeed Zoabi and Dan Lahav, students in Shomron’s lab, in collaboration with Dr. Ahuva Weiss Meilik, head of the I-Medata AI Center at Ichilov Hospital, Prof. Amos Adler, and Dr. Orli Kehat. The results were published in the journal Scientific Reports.
In the study, the AI was able to uncover patterns of information in the medical files to determine which ones were at greater risk of serious illness or death as a result of their blood infection. The system is now being assimilated into Ichilov Hospital and will be used to help doctors assess and rank patients according to risk.
Shomron spoke to The Media Line on the sidelines of AI Week 2022, a three-day conference from the Blavatnik Interdisciplinary Cyber Research Center and the Tel Aviv Center for AI and Data Science at Tel Aviv University that began earlier this week.
AI and big data are playing a growing role when it comes to healthcare. Because the technologies can speed up the process with which healthcare professionals can process and analyze large amounts of data, they can help with everything from medical records and imaging, to diagnostics and developing more advanced medicines.
Prof. Meir Feder, head of the newly established Tel Aviv University Center for Artificial Intelligence & Data Science (TAD), told The Media Line that AI has already surpassed trained radiologists when it comes to medical imaging.
“When you have a better understanding of the images then you can detect disease and make good decisions about the treatment,” Feder said. “In general, personalized medicine can only be done with AI. AI systems can do it much more accurately and reliably.”
Though much of the technology is still relatively new, Feder believes that it will make things that once appeared to be medically impossible a reality in the near future.
“Anywhere you [look], AI can help in healthcare and biomed,” he related. “It’s already helping and its effect will be ten-fold in the coming years.”