Roughly seven million children are born with serious genetic disorders around the world each year, and researchers have begun to enlist AI to expedite the diagnosis of rare disorders as well as earlier, more intensive care.
To wit, a collaborative research study from the University of Utah Health, Fabric Genomics, and Rady Children’s Hospital, has demonstrated the speed and accuracy with which AI can diagnose rare disorders in critically ill children, thus paving the way for determining the correct treatment as early as possible.
“This study is an exciting milestone demonstrating how rapid insights from AI-powered decision support technologies have the potential to significantly improve patient care,” co-corresponding author on the paper Mark Yandell, PhD, said in a press release.
Currently, it can take days or weeks for doctors to conduct a manual genetic analysis, and Yandell noted that for some infants, that’s not fast enough. Understanding the cause of newborns’ illnesses is vital to treating them, and arriving at a diagnosis within the first 24 to 48 hours after birth gives infants the best chance to improve their condition.
“The major challenge for genome-based diagnosis of rare genetic disease is to identify a putative disease-causing variant amid approximately four million benign variants in each genome, a problem akin to finding a needle in a haystack. Understanding that speed and accuracy are essential,” the researchers wrote in their report, which was published in Genome Medicine.
Knowing that speed and accuracy are essential, Yandell’s group worked with Fabric to develop the new Fabric GEM algorithm, which incorporates AI to find DNA errors that lead to disease. Scientists tested GEM by analyzing whole genomes from 179 previously diagnosed pediatric cases from Rady’s Children’s Hospital and five other medical centers worldwide. GEM found the causative gene as one of its top two candidates 92 percent of the time, outperforming existing tools.
“Dr. Yandell and the Utah team are at the forefront of applying AI research in genomics,” said Martin Reese, PhD, CEO of Fabric Genomics and a co-author on the paper. “Our collaboration has helped Fabric achieve an unprecedented level of accuracy, opening the door for broad use of AI-powered whole-genome sequencing in the NICU.”
GEM cross-references large databases of genomic sequencing from clinical disease information and other repositories of medical and scientific data and then combines this information with the patient’s genome sequencing and medical records. To sort through medical records, GEM can also be used with natural language processing tools.
While existing technologies can identify small genomic variants, GEM can find structural variants, which are larger and are often more complex, as causes of disease.According to researchers, it’s estimated that structural variants are responsible for 10 to 20 percent of genetic diseases.
Photo by Creativalmages/Getty Images