Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Diagnosing Acidosis and Alkalosis

Diagnosing Acidosis and Alkalosis

Diagnosing acid-base imbalances involves systematically analyzing arterial blood samples, focusing on three key measurements: pH, bicarbonate (HCO3−) concentration, and carbon dioxide partial pressure (PCO2). This analysis follows a four-step process that helps identify the imbalance's underlying cause and nature.
First, the pH level is assessed to determine whether the blood pH is normal (7.35–7.45), low (acidosis), or high (alkalosis).
Next, the PCO2 and...

Inborn Errors of Metabolism

Inborn Errors of Metabolism

Phenylketonuria (PKU) is a protein metabolism disorder characterized by high blood levels of the amino acid phenylalanine. This results from a mutation in the gene responsible for phenylalanine hydroxylase, an enzyme that converts phenylalanine into tyrosine. When this enzyme is deficient, phenylalanine builds up in the blood, leading to symptoms such as vomiting, rashes, seizures, growth deficiency, and severe mental retardation. An early diagnosis and a diet restricting phenylalanine intake...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Pathomechanism of Fever-Induced Liver Failure in NBAS Deficiency and Treatment Effect of NAC-Observations In Vitro and In Vivo.

Liver international : official journal of the International Association for the Study of the Liver·2026

Same author

Prevalence, Disease Onset and Clinical Outcome in Arginase 1 Deficiency: Cross-Border Surveillance in Germany, Austria, and Switzerland.

Journal of inherited metabolic disease·2026

Same author

Interpretation of Pharmacometabolomics Results: Fingerprint of Drug Exposure or Confounder Effects? Insights from a Urinary Metabolomics Study with Voriconazole in Healthy Participants.

International journal of molecular sciences·2026

Same author

Evaluation of extraction methods for the determination of urinary sulfatides by LC-MS/MS.

Journal of chromatography. B, Analytical technologies in the biomedical and life sciences·2026

Same author

Real-Life Application of a Point-of-Care Biosensor for Phenylalanine in Patients With Phenylketonuria.

Journal of inherited metabolic disease·2026

Same author

A Novel Multimodal LC-MS/MS Panel for the Comprehensive Diagnosis of Neurometabolic Disorders in CSF.

Journal of inherited metabolic disease·2026

Search research articles

Related Experiment Video

Updated: Aug 8, 2025

One-step Metabolomics: Carbohydrates, Organic and Amino Acids Quantified in a Single Procedure

One-step Metabolomics: Carbohydrates, Organic and Amino Acids Quantified in a Single Procedure

Published on: June 25, 2010

Machine Learning Methods Improve Specificity in Newborn Screening for Isovaleric Aciduria.

Elaine Zaunseder^1,2, Ulrike Mütze³, Sven F Garbade³

¹Engineering Mathematics and Computing Lab (EMCL), Interdisciplinary Center for Scientific Computing (IWR), Heidelberg University, 69120 Heidelberg, Germany.

|February 25, 2023

Summary

This summary is machine-generated.

Machine learning methods improve newborn screening for isovaleric aciduria (IVA) by reducing false positives. This digital-tier approach enhances classification accuracy, benefiting newborns and families by minimizing unnecessary follow-ups.

Keywords:

artificial intelligence data analysis data mining inborn error of metabolism isovaleric acidemia neonatal screening

More Related Videos

Determining the Likelihood of Variant Pathogenicity Using Amino Acid-level Signal-to-Noise Analysis of Genetic Variation

Determining the Likelihood of Variant Pathogenicity Using Amino Acid-level Signal-to-Noise Analysis of Genetic Variation

Published on: January 16, 2019

A Scalable, Cell-Based Method for the Functional Assessment of Ube3a Variants

A Scalable, Cell-Based Method for the Functional Assessment of Ube3a Variants

Published on: October 10, 2022

Related Experiment Videos

Last Updated: Aug 8, 2025

One-step Metabolomics: Carbohydrates, Organic and Amino Acids Quantified in a Single Procedure

One-step Metabolomics: Carbohydrates, Organic and Amino Acids Quantified in a Single Procedure

Published on: June 25, 2010

Determining the Likelihood of Variant Pathogenicity Using Amino Acid-level Signal-to-Noise Analysis of Genetic Variation

Determining the Likelihood of Variant Pathogenicity Using Amino Acid-level Signal-to-Noise Analysis of Genetic Variation

Published on: January 16, 2019

A Scalable, Cell-Based Method for the Functional Assessment of Ube3a Variants

A Scalable, Cell-Based Method for the Functional Assessment of Ube3a Variants

Published on: October 10, 2022

Area of Science:

Biochemistry
Genetics
Computational Biology

Background:

Isovaleric aciduria (IVA) is a rare leucine metabolism disorder included in newborn screening (NBS).
NBS for IVA faces challenges including increased prevalence of mild variants and false positives from medications like pivmecillinam.

Purpose of the Study:

To investigate the application of machine learning (ML) classification methods to enhance IVA classification in NBS.
To develop a digital-tier approach combining ML with traditional NBS methods to improve accuracy.

Main Methods:

Utilized a dataset of 2,106,090 newborns screened in Heidelberg, Germany.
Applied machine learning classification methods, specifically linear discriminant analysis and ridge logistic regression.
Integrated ML as a digital-tier step to traditional NBS for IVA screening.

Main Results:

Reduced the false positive rate for IVA screening by 69.9% (from 103 to 31) while maintaining 100% sensitivity in cross-validation.
ML methods successfully classified mild and classic IVA from normal newborns using NBS data.
Identified tryptophan (Trp) metabolite concentration as important for improved IVA classification, alongside isovalerylcarnitine (C5).

Conclusions:

Machine learning classification methods can significantly improve the specificity of IVA screening in newborns.
Implementing ML as a digital-tier can reduce the burden of false positives and over-treatment for newborns and families.
This approach offers a promising strategy for enhancing NBS programs globally.