Publications by authors named "Austin A Antoniou"
The precise classification of copy number variants (CNVs) presents a significant challenge in genomic medicine, primarily due to the complex nature of CNVs and their diverse impact on rare genetic diseases (RGDs). This complexity is compounded by the limitations of existing methods in accurately distinguishing between benign, uncertain, and pathogenic CNVs. Addressing this gap, we introduce CNVoyant, a machine learning-based multi-class framework designed to enhance the clinical significance classification of CNVs.
View Article and Find Full Text PDFArticle Synopsis
- Genetic diseases are common in Level IV NICUs, but providers often struggle to identify when genetic evaluations are needed; a machine learning algorithm was developed to predict this need within the first 18 months.
- Using Natural Language Processing, researchers extracted health data and trained the algorithm, achieving strong predictive results with ROC AUC of 0.87 and PR AUC of 0.73 for NICU patients.
- The use of this machine learning approach significantly reduced the median time to genetic testing from 10 days to 1 day and greatly improved the resolution of diagnostic odysseys within 14 days, highlighting the potential for better patient outcomes.
The precise classification of copy number variants () presents a significant challenge in genomic medicine, primarily due to the complex nature of CNVs and their diverse impact on genetic disorders. This complexity is compounded by the limitations of existing methods in accurately distinguishing between benign, uncertain, and pathogenic CNVs. Addressing this gap, we introduce CNVoyant, a machine learning-based multi-class framework designed to enhance the clinical significance classification of CNVs.
View Article and Find Full Text PDF