September, 2019 – Palo Alto, California — Greenwood Genetic Center utilizes Emedgene’s AI to slash turnaround times, improve diagnostic yield and return answers to patients faster. Emedgene’s platform automates much of the genomic analysis workflow, allowing Greenwood to reduce time-per-test by 75%.
Greenwood Genetic Center is a nonprofit organization advancing the field of medical genetics and caring for families impacted by genetic disease and birth defects based in South Carolina. The center is actively investing in technology initiatives that faculty have deemed critical to improving patient care and remaining at the forefront of genomic medicine, with the ultimate goal of increasing diagnostic yield and ending the diagnostic odyssey for more patients. Their diagnostic lab offers an extensive menu of genetic tests, among others, diagnosing patients served by South Carolina’s Department of Disabilities and Special Needs.
Analyzing genetic tests, and in particular, exome tests, was a time consuming and labor-intensive effort performed by Greenwood’s highly skilled personnel. The analysis process required them to review dozens of variants. Specifically challenging was searching for recently discovered gene-disease connections in databases and the literature. Facing longer turnaround times, Greenwood’s lab directors set out to incorporate advanced technology that would help prioritize variants, provide access to an up-to-date database of gene-disease associations, and shorten analysis time.
Emedgene’s AI Solves All Test Cases During Evaluation
The team evaluated a dozen genomic analysis platforms according to a stringent set of criteria, and 4 platforms were selected for a performance assessment on a set of 10 previously solved cases, some of which were intentionally complex. “Emedgene was the only vendor able to automatically solve all 10 cases,” says Julie Jones, PhD, Greenwood’s Clinical Genomic Sequencing Program Director. “Other vendors’ prioritization algorithms were successful in roughly 30% of cases.”
Emedgene’s interpretable machine learning algorithms provide a short-list of causative variants, along with supporting evidence. The evidence includes current information curated from the literature using Natural Language Processing, as well as information from databases, animal models and pathways, providing a comprehensive – yet completely automated – review. “Emedgene’s machine learning simplifies the highly complex task of variant analysis, allowing us to handle more tests every day,” says Ray Louie, PhD, Assistant Director in the Center’s Molecular Diagnostic Laboratory.
“It’s been a pleasure to collaborate with such an excellent team of scientists, supporting the advanced work they are doing in clinical interpretation, and constantly pushing the boundaries to meet a higher diagnostic yield. We consider scaling genomic interpretation a key factor in enabling advanced genomic medicine to patients in need, and have found with Greenwood a true partnership for advancing this goal,” says Einat Metzer, CEO of Emedgene.