Clinical Report: Rare Disease AI Puts Variants in Focus

Overview

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

Background

The diagnosis of rare diseases often involves lengthy and complex processes, with many cases remaining unsolved for years. AI technologies, such as aiDIVA, are being developed to assist in the interpretation of genomic data.

Data Highlights

Key Findings

• aiDIVA ranked causal variants within the top three in 97% of cases with variants in ClinVar.
• In an independent assessment, aiDIVA placed 93% of causal variants in the top three.
• The system outperformed existing tools like Exomiser and Lirical in variant ranking.
• aiDIVA identified 45 previously unsolved cases as newly solved through reanalysis.
• The system is designed to assist rather than replace expert review in variant classification.

Clinical Implications

Final variant classifications continue to rely on expert review and established clinical guidelines.

Conclusion

The aiDIVA system demonstrates high accuracy in variant identification.

Related Resources & Content

1. aiDIVA – hybrid AI for rare disease diagnostics using evidence-based, machine learning and language models | npj Genomic Medicine, 2026 -- Title
2. Can AI Shorten the Rare Disease Odyssey? | The Pathologist, 2026 -- Title
3. AI Models Could Improve Diagnosis and Care for Rare Diseases | Journal of Medical Internet Research, 2026 -- Title
4. Accelerating Rare Disease Diagnosis: The Role of AI in Streamlining Clinical Assessments | Journal of Medical Internet Research, 2026 -- Title
5. Genetic Evaluation of the Child With Intellectual Disability or Global Developmental Delay: Clinical Report | Pediatrics | American Academy of Pediatrics, 2025 -- Title
6. aace endocrine ai — Agentic AI system may improve rare disease diagnosis
7. Genetic Evaluation of the Child With Intellectual Disability or Global Developmental Delay: Clinical Report | Pediatrics | American Academy of Pediatrics
8. Points to consider for the reporting of variants of uncertain significance in germline genetic and genomic testing: A statement of the American College of Medical Genetics and Genomics (ACMG) - Genetics in Medicine
9. aiDIVA – hybrid AI for rare disease diagnostics using evidence-based, machine learning and language models | npj Genomic Medicine