5 Key Takeaways

• 1

  The aiDIVA system ranked disease-causing variants among its top three candidates in over 90% of assessed rare disease cases.

• 2

  aiDIVA combines evidence-based scoring, machine learning, phenotype matching, and large language models for clinical assessment.

• 3

  In a benchmark study, aiDIVA placed causal variants within the top three in 97% of cases with variants in ClinVar.

• 4

  The system is a decision-support tool that requires expert review and does not autonomously diagnose rare diseases.

• 5

  aiDIVA's performance for structural variants and in-frame insertions and deletions is currently lower than for single-nucleotide variants.