Rare Disease AI Puts Variants in Focus

aiDIVA combines genomic evidence, phenotype matching, machine learning, and language models

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.

1