Clinical Evaluation of an AI System for Streamlined Variant Interpretation in Genetic Testing
Listed in
This article is not in any list yet, why not save it to one of your lists.Abstract
Background
The growing use of whole exome/genome sequencing for diagnosing hereditary diseases has increased the interpretive workload for clinical laboratories. Efficient methods are needed to identify pathogenic variants and maximize diagnostic yield without overwhelming resources.
Methods
We developed DiagAI, an AI-powered system trained on 2.5 million ClinVar variants to predict ACMG pathogenicity classes. DiagAI ranks variants, proposes diagnostic shortlists, and identifies probands likely to receive molecular diagnoses. It integrates molecular features, inheritance patterns, and phenotypic data when available. We retrospectively analyzed 966 exomes from a nephrology cohort, including 196 with causal variants and 770 undiagnosed cases.
Results
DiagAI identified 94.9% of causal variants in diagnostic exomes with HPO terms, compared to 90.8% without, with median shortlist sizes of 12 and 9 variants, respectively. It achieved a sensitivity of 57.1% and a specificity of 92.6% in tagging exomes likely to contain a diagnostic variant. With HPO terms, 74% of top-ranked (top 1) variants were diagnostic, versus 42% without, and DiagAI outperformed Exomiser and AIMARRVEL in this setting.
Conclusion
DiagAI generates accurate shortlists of variants that streamline the variant interpretation process. It provides a scalable solution for managing growing diagnostic test volumes without compromising quality.
