The potential of artificial intelligence (AI) in clinical genomics is causing some diagnostic labs to consider how the technology can improve time-consuming components of their workflow—especially variant curation. The primary bottleneck to achieving accurate and comprehensive variant curation is the need to manually locate, assess, annotate and document evidence from scientific and clinical literature. While AI is a logical solution to these challenges, can diagnostic labs trust it?

In this webinar, we examine a new study by Stanford University that analyzes the accuracy, consistency, and comprehensiveness of automated and manual germline variant curation. The study compares the quality of data from Stanford’s Automatic VAriant evidence DAtabase (AVADA) to the Human Gene Mutation Database (HGMD), an expert-curated resource for human inherited disease mutations.