Improving the Diagnosis of Phenylketonuria by Using a Machine Learning–Based Screening Model of Neonatal MRM Data
Open Access
- 7 July 2020
- journal article
- research article
- Published by Frontiers Media SA in Frontiers in Molecular Biosciences
- Vol. 7, 115
Abstract
Phenylketonuria (PKU) is a common genetic metabolic disorder that affects the infant's nerve development and manifests as abnormal behavior and developmental delay as the child grows. Currently, a triple–quadrupole mass spectrometer (TQ-MS) is a common high-accuracy clinical PKU screening method. However, there is high false-positive rate associated with this modality, and its reduction can provide a diagnostic and economic benefit to both pediatric patients and health providers. Machine learning methods have the advantage of utilizing high-dimensional and complex features, which can be obtained from the patient's metabolic patterns and interrogated for clinically relevant knowledge. In this study, using TQ-MS screening data of more than 600,000 patients collected at the Newborn Screening Center of Shanghai Children's Hospital, we derived a dataset containing 256 PKU-suspected cases. We then developed a machine learning logistic regression analysis model with the aim to minimize false-positive rates in the results of the initial PKU test. The model attained a 95–100% sensitivity, the specificity was improved 53.14%, and positive predictive value increased from 19.14 to 32.16%. Our study shows that machine learning models may be used as a pediatric diagnosis aid tool to reduce the number of suspected cases and to help eliminate patient recall. Our study can serve as a future reference for the selection and evaluation of computational screening methods.Keywords
This publication has 25 references indexed in Scilit:
- Web-Based Newborn Screening System for Metabolic Diseases: Machine Learning Versus CliniciansJournal of Medical Internet Research, 2013
- Newborn Screening for Inborn Errors of Metabolism in Mainland China: 30 Years of Experience2012
- Variable selection: current practice in epidemiological studiesEuropean Journal of Epidemiology, 2009
- A review of feature selection techniques in bioinformaticsBioinformatics, 2007
- The Birth Prevalence of PKU in Populations of European, South Asian and Sub‐Saharan African Ancestry Living in South East EnglandAnnals of Human Genetics, 2007
- Modelling of classification rules on metabolic patterns including machine learning and expert knowledgeJournal of Biomedical Informatics, 2005
- Supervised machine learning techniques for the classification of metabolic disorders in newbornsBioinformatics, 2004
- Emerging bioinformatics for the metabolomeBriefings in Bioinformatics, 2002
- Phenylketonuria: screening, treatment and maternal PKUClinical Biochemistry, 1991
- VII. Note on regression and inheritance in the case of two parentsProceedings of the Royal Society of London, 1895