Machine Learning Methods Improve Specificity in Newborn Screening for Isovaleric Aciduria
Isovaleric aciduria (IVA) is a rare disorder of leucine metabolism and part of newborn screening (NBS) programs worldwide. However, NBS for IVA is hampered by, first, the increased birth prevalence due to the identification of individuals with an attenuated disease variant (so-called “mild” IVA) and...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Metabolites |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2218-1989/13/2/304 |
| _version_ | 1797619340035489792 |
|---|---|
| author | Elaine Zaunseder Ulrike Mütze Sven F. Garbade Saskia Haupt Patrik Feyh Georg F. Hoffmann Vincent Heuveline Stefan Kölker |
| author_facet | Elaine Zaunseder Ulrike Mütze Sven F. Garbade Saskia Haupt Patrik Feyh Georg F. Hoffmann Vincent Heuveline Stefan Kölker |
| author_sort | Elaine Zaunseder |
| collection | DOAJ |
| description | Isovaleric aciduria (IVA) is a rare disorder of leucine metabolism and part of newborn screening (NBS) programs worldwide. However, NBS for IVA is hampered by, first, the increased birth prevalence due to the identification of individuals with an attenuated disease variant (so-called “mild” IVA) and, second, an increasing number of false positive screening results due to the use of pivmecillinam contained in the medication. Recently, machine learning (ML) methods have been analyzed, analogous to new biomarkers or second-tier methods, in the context of NBS. In this study, we investigated the application of machine learning classification methods to improve IVA classification using an NBS data set containing 2,106,090 newborns screened in Heidelberg, Germany. Therefore, we propose to combine two methods, linear discriminant analysis, and ridge logistic regression as an additional step, a digital-tier, to traditional NBS. Our results show that this reduces the false positive rate by <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>69.9</mn><mo>%</mo></mrow></semantics></math></inline-formula> from 103 to 31 while maintaining <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>100</mn><mo>%</mo></mrow></semantics></math></inline-formula> sensitivity in cross-validation. The ML methods were able to classify mild and classic IVA from normal newborns solely based on the NBS data and revealed that besides isovalerylcarnitine (C5), the metabolite concentration of tryptophan (Trp) is important for improved classification. Overall, applying ML methods to improve the specificity of IVA could have a major impact on newborns, as it could reduce the newborns’ and families’ burden of false positives or over-treatment. |
| first_indexed | 2024-03-11T08:26:43Z |
| format | Article |
| id | doaj.art-e205bc7f594a4cc3902c083f6fa9d2d4 |
| institution | Directory Open Access Journal |
| issn | 2218-1989 |
| language | English |
| last_indexed | 2024-03-11T08:26:43Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Metabolites |
| spelling | doaj.art-e205bc7f594a4cc3902c083f6fa9d2d42023-11-16T22:05:42ZengMDPI AGMetabolites2218-19892023-02-0113230410.3390/metabo13020304Machine Learning Methods Improve Specificity in Newborn Screening for Isovaleric AciduriaElaine Zaunseder0Ulrike Mütze1Sven F. Garbade2Saskia Haupt3Patrik Feyh4Georg F. Hoffmann5Vincent Heuveline6Stefan Kölker7Engineering Mathematics and Computing Lab (EMCL), Interdisciplinary Center for Scientific Computing (IWR), Heidelberg University, 69120 Heidelberg, GermanyDivision of Child Neurology and Metabolic Medicine, Center for Child and Adolescent Medicine, Heidelberg University Hospital, 69120 Heidelberg, GermanyDivision of Child Neurology and Metabolic Medicine, Center for Child and Adolescent Medicine, Heidelberg University Hospital, 69120 Heidelberg, GermanyEngineering Mathematics and Computing Lab (EMCL), Interdisciplinary Center for Scientific Computing (IWR), Heidelberg University, 69120 Heidelberg, GermanyDivision of Child Neurology and Metabolic Medicine, Center for Child and Adolescent Medicine, Heidelberg University Hospital, 69120 Heidelberg, GermanyDivision of Child Neurology and Metabolic Medicine, Center for Child and Adolescent Medicine, Heidelberg University Hospital, 69120 Heidelberg, GermanyEngineering Mathematics and Computing Lab (EMCL), Interdisciplinary Center for Scientific Computing (IWR), Heidelberg University, 69120 Heidelberg, GermanyDivision of Child Neurology and Metabolic Medicine, Center for Child and Adolescent Medicine, Heidelberg University Hospital, 69120 Heidelberg, GermanyIsovaleric aciduria (IVA) is a rare disorder of leucine metabolism and part of newborn screening (NBS) programs worldwide. However, NBS for IVA is hampered by, first, the increased birth prevalence due to the identification of individuals with an attenuated disease variant (so-called “mild” IVA) and, second, an increasing number of false positive screening results due to the use of pivmecillinam contained in the medication. Recently, machine learning (ML) methods have been analyzed, analogous to new biomarkers or second-tier methods, in the context of NBS. In this study, we investigated the application of machine learning classification methods to improve IVA classification using an NBS data set containing 2,106,090 newborns screened in Heidelberg, Germany. Therefore, we propose to combine two methods, linear discriminant analysis, and ridge logistic regression as an additional step, a digital-tier, to traditional NBS. Our results show that this reduces the false positive rate by <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>69.9</mn><mo>%</mo></mrow></semantics></math></inline-formula> from 103 to 31 while maintaining <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>100</mn><mo>%</mo></mrow></semantics></math></inline-formula> sensitivity in cross-validation. The ML methods were able to classify mild and classic IVA from normal newborns solely based on the NBS data and revealed that besides isovalerylcarnitine (C5), the metabolite concentration of tryptophan (Trp) is important for improved classification. Overall, applying ML methods to improve the specificity of IVA could have a major impact on newborns, as it could reduce the newborns’ and families’ burden of false positives or over-treatment.https://www.mdpi.com/2218-1989/13/2/304data analysisartificial intelligencedata miningisovaleric acidemianeonatal screeninginborn error of metabolism |
| spellingShingle | Elaine Zaunseder Ulrike Mütze Sven F. Garbade Saskia Haupt Patrik Feyh Georg F. Hoffmann Vincent Heuveline Stefan Kölker Machine Learning Methods Improve Specificity in Newborn Screening for Isovaleric Aciduria Metabolites data analysis artificial intelligence data mining isovaleric acidemia neonatal screening inborn error of metabolism |
| title | Machine Learning Methods Improve Specificity in Newborn Screening for Isovaleric Aciduria |
| title_full | Machine Learning Methods Improve Specificity in Newborn Screening for Isovaleric Aciduria |
| title_fullStr | Machine Learning Methods Improve Specificity in Newborn Screening for Isovaleric Aciduria |
| title_full_unstemmed | Machine Learning Methods Improve Specificity in Newborn Screening for Isovaleric Aciduria |
| title_short | Machine Learning Methods Improve Specificity in Newborn Screening for Isovaleric Aciduria |
| title_sort | machine learning methods improve specificity in newborn screening for isovaleric aciduria |
| topic | data analysis artificial intelligence data mining isovaleric acidemia neonatal screening inborn error of metabolism |
| url | https://www.mdpi.com/2218-1989/13/2/304 |
| work_keys_str_mv | AT elainezaunseder machinelearningmethodsimprovespecificityinnewbornscreeningforisovalericaciduria AT ulrikemutze machinelearningmethodsimprovespecificityinnewbornscreeningforisovalericaciduria AT svenfgarbade machinelearningmethodsimprovespecificityinnewbornscreeningforisovalericaciduria AT saskiahaupt machinelearningmethodsimprovespecificityinnewbornscreeningforisovalericaciduria AT patrikfeyh machinelearningmethodsimprovespecificityinnewbornscreeningforisovalericaciduria AT georgfhoffmann machinelearningmethodsimprovespecificityinnewbornscreeningforisovalericaciduria AT vincentheuveline machinelearningmethodsimprovespecificityinnewbornscreeningforisovalericaciduria AT stefankolker machinelearningmethodsimprovespecificityinnewbornscreeningforisovalericaciduria |