Newborn Screening (NBS)
Improved second-tier tools are needed to reduce false-positive outcomes in newborn screening for inborn metabolic disorders on the Recommended Universal Screening Panel (RUSP). We have developed assays for multiplex sequencing of the Cystic Fibrosis gene (CFseq) and for 72 metabolic disease genes (RUSPseq) from newborn dried blood spots. Random Forest machine learning is being applied to newborn metabolic screening data to minimize false-positives and reduce diagnostic delays. Web-based software is available to aid the interpretation of screening data and to identify ethnicity-related differences in blood biomarkers of metabolic diseases.
- Ethnic Variability in Newborn Metabolic Screening Markers Associated With False-Positive Outcomes
- Reducing False-Positive Results in Newborn Screening Using Machine Learning
- Combining newborn metabolic and DNA analysis for second-tier testing of methylmalonic acidemia
- Elevated methylmalonic acidemia (MMA) screening markers in Hispanic and preterm newborns
- Next-Generation Molecular Testing of Newborn Dried Blood Spots for Cystic Fibrosis
- Timing of Newborn Blood Collection Alters Metabolic Disease Screening Performance