Multivariate Independent Component Analysis Identifies Patients in Newborn Screening Equally to Adjusted Reference Ranges
Newborn screening (NBS) of inborn errors of metabolism (IEMs) is based on the reference ranges established on a healthy newborn population using quantile statistics of molar concentrations of biomarkers and their ratios. The aim of this paper is to investigate whether multivariate independent compon...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | International Journal of Neonatal Screening |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2409-515X/9/4/60 |
| _version_ | 1797380704920666112 |
|---|---|
| author | Štěpán Kouřil Julie de Sousa Kamila Fačevicová Alžběta Gardlo Christoph Muehlmann Klaus Nordhausen David Friedecký Tomáš Adam |
| author_facet | Štěpán Kouřil Julie de Sousa Kamila Fačevicová Alžběta Gardlo Christoph Muehlmann Klaus Nordhausen David Friedecký Tomáš Adam |
| author_sort | Štěpán Kouřil |
| collection | DOAJ |
| description | Newborn screening (NBS) of inborn errors of metabolism (IEMs) is based on the reference ranges established on a healthy newborn population using quantile statistics of molar concentrations of biomarkers and their ratios. The aim of this paper is to investigate whether multivariate independent component analysis (ICA) is a useful tool for the analysis of NBS data, and also to address the structure of the calculated ICA scores. NBS data were obtained from a routine NBS program performed between 2013 and 2022. ICA was tested on 10,213/150 free-diseased controls and 77/20 patients (9/3 different IEMs) in the discovery/validation phases, respectively. The same model computed during the discovery phase was used in the validation phase to confirm its validity. The plots of ICA scores were constructed, and the results were evaluated based on 5sd levels. Patient samples from 7/3 different diseases were clearly identified as 5sd-outlying from control groups in both phases of the study. Two IEMs containing only one patient each were separated at the 3sd level in the discovery phase. Moreover, in one latent variable, the effect of neonatal birth weight was evident. The results strongly suggest that ICA, together with an interpretation derived from values of the “average member of the score structure”, is generally applicable and has the potential to be included in the decision process in the NBS program. |
| first_indexed | 2024-03-08T20:40:55Z |
| format | Article |
| id | doaj.art-89ccb69f7eae4ccfb60f038c4c3f3a3f |
| institution | Directory Open Access Journal |
| issn | 2409-515X |
| language | English |
| last_indexed | 2024-03-08T20:40:55Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | International Journal of Neonatal Screening |
| spelling | doaj.art-89ccb69f7eae4ccfb60f038c4c3f3a3f2023-12-22T14:15:28ZengMDPI AGInternational Journal of Neonatal Screening2409-515X2023-10-01946010.3390/ijns9040060Multivariate Independent Component Analysis Identifies Patients in Newborn Screening Equally to Adjusted Reference RangesŠtěpán Kouřil0Julie de Sousa1Kamila Fačevicová2Alžběta Gardlo3Christoph Muehlmann4Klaus Nordhausen5David Friedecký6Tomáš Adam7Department of Clinical Biochemistry, University Hospital Olomouc, 779 00 Olomouc, Czech RepublicLaboratory of Metabolomics, Institute of Molecular and Translational Medicine, Palacký University Olomouc, 779 00 Olomouc, Czech RepublicDepartment of Mathematical Analysis and Applications of Mathematics, Faculty of Science, Palacký University Olomouc, 779 00 Olomouc, Czech RepublicDepartment of Clinical Biochemistry, University Hospital Olomouc, 779 00 Olomouc, Czech RepublicInstitute of Statistics & Mathematical Methods in Economics, Vienna University of Technology, 1040 Vienna, AustriaDepartment of Mathematics and Statistics, University of Jyväskylä, 40014 Jyväskylä, FinlandDepartment of Clinical Biochemistry, University Hospital Olomouc, 779 00 Olomouc, Czech RepublicDepartment of Clinical Biochemistry, University Hospital Olomouc, 779 00 Olomouc, Czech RepublicNewborn screening (NBS) of inborn errors of metabolism (IEMs) is based on the reference ranges established on a healthy newborn population using quantile statistics of molar concentrations of biomarkers and their ratios. The aim of this paper is to investigate whether multivariate independent component analysis (ICA) is a useful tool for the analysis of NBS data, and also to address the structure of the calculated ICA scores. NBS data were obtained from a routine NBS program performed between 2013 and 2022. ICA was tested on 10,213/150 free-diseased controls and 77/20 patients (9/3 different IEMs) in the discovery/validation phases, respectively. The same model computed during the discovery phase was used in the validation phase to confirm its validity. The plots of ICA scores were constructed, and the results were evaluated based on 5sd levels. Patient samples from 7/3 different diseases were clearly identified as 5sd-outlying from control groups in both phases of the study. Two IEMs containing only one patient each were separated at the 3sd level in the discovery phase. Moreover, in one latent variable, the effect of neonatal birth weight was evident. The results strongly suggest that ICA, together with an interpretation derived from values of the “average member of the score structure”, is generally applicable and has the potential to be included in the decision process in the NBS program.https://www.mdpi.com/2409-515X/9/4/60newborn screeningindependent component analysismass spectrometrymultivariate statistical analysisinborn errors of metabolismcompositional data analysis |
| spellingShingle | Štěpán Kouřil Julie de Sousa Kamila Fačevicová Alžběta Gardlo Christoph Muehlmann Klaus Nordhausen David Friedecký Tomáš Adam Multivariate Independent Component Analysis Identifies Patients in Newborn Screening Equally to Adjusted Reference Ranges International Journal of Neonatal Screening newborn screening independent component analysis mass spectrometry multivariate statistical analysis inborn errors of metabolism compositional data analysis |
| title | Multivariate Independent Component Analysis Identifies Patients in Newborn Screening Equally to Adjusted Reference Ranges |
| title_full | Multivariate Independent Component Analysis Identifies Patients in Newborn Screening Equally to Adjusted Reference Ranges |
| title_fullStr | Multivariate Independent Component Analysis Identifies Patients in Newborn Screening Equally to Adjusted Reference Ranges |
| title_full_unstemmed | Multivariate Independent Component Analysis Identifies Patients in Newborn Screening Equally to Adjusted Reference Ranges |
| title_short | Multivariate Independent Component Analysis Identifies Patients in Newborn Screening Equally to Adjusted Reference Ranges |
| title_sort | multivariate independent component analysis identifies patients in newborn screening equally to adjusted reference ranges |
| topic | newborn screening independent component analysis mass spectrometry multivariate statistical analysis inborn errors of metabolism compositional data analysis |
| url | https://www.mdpi.com/2409-515X/9/4/60 |
| work_keys_str_mv | AT stepankouril multivariateindependentcomponentanalysisidentifiespatientsinnewbornscreeningequallytoadjustedreferenceranges AT juliedesousa multivariateindependentcomponentanalysisidentifiespatientsinnewbornscreeningequallytoadjustedreferenceranges AT kamilafacevicova multivariateindependentcomponentanalysisidentifiespatientsinnewbornscreeningequallytoadjustedreferenceranges AT alzbetagardlo multivariateindependentcomponentanalysisidentifiespatientsinnewbornscreeningequallytoadjustedreferenceranges AT christophmuehlmann multivariateindependentcomponentanalysisidentifiespatientsinnewbornscreeningequallytoadjustedreferenceranges AT klausnordhausen multivariateindependentcomponentanalysisidentifiespatientsinnewbornscreeningequallytoadjustedreferenceranges AT davidfriedecky multivariateindependentcomponentanalysisidentifiespatientsinnewbornscreeningequallytoadjustedreferenceranges AT tomasadam multivariateindependentcomponentanalysisidentifiespatientsinnewbornscreeningequallytoadjustedreferenceranges |