Children’s Hospital of Philadelphia Develops AI Tool to Guide Genetic Testing for Rare Diseases

Children's Hospital of Philadelphia has developed an artificial intelligence system called RareDAI to assist clinicians in selecting genetic tests for diagnosing rare diseases, announced in a press release.

The research team fine tuned large language models to evaluate clinical data and recommend suitable testing methods such as gene panels, whole exome sequencing, or whole genome sequencing. RareDAI follows a clinician's reasoning through standardized questions that address factors like suspected congenital abnormalities, family history, and cost or accessibility considerations.

The system provides transparency by displaying the reasoning behind each recommendation, allowing medical professionals to review the decision process. In testing, RareDAI improved accuracy and precision by up to 20 percent compared to traditional model fine tuning.

The study was supported by grants from the National Institutes of Health and conducted in collaboration with researchers from Columbia University and Boston Children's Hospital. The findings were published in NPJ Digital Medicine.