Digital-Tier Strategy Improves Newborn Screening for Glutaric Aciduria Type 1

Area of Science:

• Biochemistry
• Genetics
• Computational Biology

Background:

• Glutaric aciduria type 1 (GA1) is a rare inherited metabolic disorder.
• It is increasingly incorporated into newborn screening (NBS) programs globally.
• Current NBS for GA1 faces challenges with high false-positive rates due to biochemical variability and lack of precise second-tier tests.

Purpose of the Study:

• To enhance the specificity of NBS for GA1.
• To reduce the high rate of false positives in GA1 newborn screening.
• To implement machine learning methods for improved diagnostic accuracy.

Main Methods:

• Analysis of NBS profiles from 1,025,953 newborns screened between 2014 and 2023.
• Application of machine learning algorithms including logistic regression, ridge regression, and support vector machine.
• Development of a digital-tier strategy for GA1 NBS.

Main Results:

• A significant sex difference was observed, with males having twice the false-positive rate compared to females.
• The proposed digital-tier strategy reduced the false-positive rate by over 90%.
• All confirmed GA1 cases were correctly identified, and high-cost false positives were significantly reduced.

Conclusions:

• Understanding the sources of false positives in NBS is crucial for improving screening protocols.
• Implementing a digital-tier strategy using machine learning can substantially increase the specificity of GA1 testing.
• This approach can alleviate the significant burden on newborns and families caused by false-positive NBS results.