Evidence Aggregator: AI reasoning applied to rare disease diagnostics

Retrieving, reviewing, and synthesizing technical information can be time-consuming and challenging, particularly when requiring specialized expertise, as is the case of variant assessment for rare disease diagnostics. To address this challenge, we developed the Evidence Aggregator (EvAgg), a generative AI tool designed for rare disease diagnosis that systematically extracts relevant information from the scientific literature for any human gene. EvAgg provides a thorough and current summary of observed genetic variants and their associated clinical features, enabling rapid synthesis of evidence concerning gene-disease relationships. EvAgg demonstrates strong benchmark performance, achieving 97% recall in identifying relevant papers, 92% recall in detecting instances of genetic variation within those papers, and ∼80% accuracy in extracting individual case and variant-level content (e.g. zygosity, inheritance, variant type, and phenotype). Further, EvAgg complemented the process of manual literature review by identifying a substantial number of additional relevant pieces of information. When tested with analysts in rare disease case analysis, EvAgg reduced review time by 34% (p-value < 0.002) and increased the number of papers, variants, and cases evaluated per unit time. These savings have the potential to reduce diagnostic latency and increase solve rates for challenging rare disease cases.