Study Demonstrates Accuracy of AI in Rapidly Diagnosing Rare Diseases in Critically Ill Patients

A pivotal study led by Fabric Genomics and Rady Children’s Institute for Genomic Medicine shows that artificial intelligence can enable the accurate and rapid clinical diagnosis of rare diseases in critically ill newborns based on whole-genome or whole-exome analyses.

Photo: Stephen Kingsmore, a co-author of the study and the President and CEO of Rady Children’s Institute for Genomic Medicine

The publication of a retrospective study in Genome Medicine shows that across six leading genomic centers and hospitals, researchers were able to detect more than 90 percent of disease-causing variants in infants with rare diseases using the Fabric GEM AI algorithm and whole-genome and whole-exome data from previously diagnosed newborns and rare disease patients at Rady Children’s Hospital in San Diego and at other clinical sites.

Despite differences in case collection, sequencing methods, and bioinformatics pipelines across all sites, Fabric GEM’s performance demonstrated a new standard of accuracy, ranking the causative variant first or second more than 90 percent of the time. In addition, Fabric GEM ranked specific diseases and conditions associated with these genes to assist clinicians in the ultimate diagnosis of each case.

Fabric and Rady said these findings demonstrate how artificial intelligence can successfully reduce the burden of gene variant review by clinical geneticists.

“Fast and definitive genetic diagnosis is essential to providing the right treatment in a timely manner for critically ill newborns,” said Stephen Kingsmore, a co-author of the study and the president and CEO of Rady Children’s Institute for Genomic Medicine. “Fabric GEM has successfully demonstrated that it can automatically and quickly suggest a very short list of candidate genes for interpretation through whole-genome or whole-exome sequencing.”

The study shows how AI-powered decision support technology can empower clinicians, according to Mark Yandell, professor of Human Genetics at the University of Utah, founding scientific advisor to Fabric, and a co-author on the paper.

“It has the potential to significantly improve patient care with rapid insights distilled from clinical notes, medical databases, and genome sequences,” he said. “Human review of these critical, but ever-expanding data is becoming infeasible due to their size and complexity.”

Author: Rare Daily Staff