Improving Diagnosis of Rare Genetic Disorders with AI

Rare Daily Staff                                                                                           

Scientists at Baylor College of Medicine have developed a machine learning system called AI-MARRVEL to improve the diagnosis of rare genetic disease.

In an article published in the New England Journal of Medicine, the researchers report on how AI-MARRVEL (AIM) helps prioritize causative variants for Mendelian disorders. They said AIM can contribute to predictions independent of clinical knowledge of the gene of interest, helping to advance the discovery of novel disease mechanisms.

“The diagnostic rate for rare genetic disorders is only about 30 percent, and on average, it is six years from the time of symptom onset to diagnosis,” said co-corresponding author Pengfei Liu, associate professor of molecular and human genetics and associate clinical director at Baylor Genetics. “There is an urgent need for new approaches to enhance the speed and accuracy of diagnosis.”

AIM is trained using a public database of known variants and genetic analysis called Model organism Aggregated Resources for Rare Variant ExpLoration (MARRVEL) previously developed by the Baylor team. The MARRVEL database includes more than 3.5 million variants from thousands of diagnosed cases. Researchers provide AIM with patients’ exome sequence data and symptoms, and AIM provides a ranking of the most likely gene candidates causing the rare disease.

Researchers compared AIM’s results to other algorithms used in recent benchmark papers. They tested the models using three data cohorts with established diagnoses from Baylor Genetics, the National Institutes of Health-funded Undiagnosed Diseases Network, and the Deciphering Developmental Disorders project. AIM consistently ranked diagnosed genes as the number one candidate in twice as many cases as all other benchmark methods using these real-world data sets.

“We trained AIM to mimic the way humans make decisions, and the machine can do it much faster, more efficiently and at a lower cost,” said co-corresponding author Zhandong Liu, associate professor of pediatrics – neurology at Baylor and investigator at the Jan and Dan Duncan Neurological Research Institute at Texas Children’s Hospital. “This method has effectively doubled the rate of accurate diagnosis.”

The researchers also found that AIM could help provide answers for patients who have long remained undiagnosed. They said hundreds of novel disease-causing variants that may be key to solving these cold cases are reported every year. Determining which cases warrant reanalysis, though, is challenging because of the high volume of cases. The researchers tested AIM’s clinical exome reanalysis on a dataset of Undiagnosed Diseases Network and the Deciphering Developmental Disorders project cases and found that it was able to correctly identify 57 percent of diagnosable cases.

“We can make the reanalysis process much more efficient by using AIM to identify a high-confidence set of potentially solvable cases and pushing those cases for manual review,” Zhandong Liu said. “We anticipate that this tool can recover an unprecedented number of cases that were not previously thought to be diagnosable.”

The researchers also tested AIM’s potential for discovery of novel gene candidates that have not been linked to a disease. It correctly predicted two newly reported disease genes as top candidates in two Undiagnosed Diseases Network cases.

“AIM is a major step forward in using AI to diagnose rare diseases,” said co-corresponding author Hugo Bellen, distinguished service professor in molecular and human genetics at Baylor and chair in neurogenetics at the Duncan NRI. “It narrows the differential genetic diagnoses down to a few genes and has the potential to guide the discovery of previously unknown disorders.”

Photo: Pengfei Liu, associate professor of molecular and human genetics and associate clinical director at Baylor Genetics