Machine learning analysis of pregnancy data enables early identification of a subpopulation of newborns with ASD
Abstract To identify newborns at risk of developing ASD and to detect ASD biomarkers early after birth, we compared retrospectively ultrasound and biological measurements of babies diagnosed later with ASD or neurotypical (NT) that are collected routinely during pregnancy and birth. We used a superv...
Guardado en:
Autores principales: | , , , , , , , , , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Nature Portfolio
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/aa746bd949174332adf32d8f2626063e |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:aa746bd949174332adf32d8f2626063e |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:aa746bd949174332adf32d8f2626063e2021-12-02T17:04:06ZMachine learning analysis of pregnancy data enables early identification of a subpopulation of newborns with ASD10.1038/s41598-021-86320-02045-2322https://doaj.org/article/aa746bd949174332adf32d8f2626063e2021-03-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-86320-0https://doaj.org/toc/2045-2322Abstract To identify newborns at risk of developing ASD and to detect ASD biomarkers early after birth, we compared retrospectively ultrasound and biological measurements of babies diagnosed later with ASD or neurotypical (NT) that are collected routinely during pregnancy and birth. We used a supervised machine learning algorithm with a cross-validation technique to classify NT and ASD babies and performed various statistical tests. With a minimization of the false positive rate, 96% of NT and 41% of ASD babies were identified with a positive predictive value of 77%. We identified the following biomarkers related to ASD: sex, maternal familial history of auto-immune diseases, maternal immunization to CMV, IgG CMV level, timing of fetal rotation on head, femur length in the 3rd trimester, white blood cell count in the 3rd trimester, fetal heart rate during labor, newborn feeding and temperature difference between birth and one day after. Furthermore, statistical models revealed that a subpopulation of 38% of babies at risk of ASD had significantly larger fetal head circumference than age-matched NT ones, suggesting an in utero origin of the reported bigger brains of toddlers with ASD. Our results suggest that pregnancy follow-up measurements might provide an early prognosis of ASD enabling pre-symptomatic behavioral interventions to attenuate efficiently ASD developmental sequels.Hugues CalyHamed RabieiPerrine Coste-MazeauSebastien HantzSophie AlainJean-Luc EyraudThierry ChianeaCatherine CalyDavid MakowskiNouchine HadjikhaniEric LemonnierYehezkel Ben-AriNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-14 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
Medicine R Science Q |
spellingShingle |
Medicine R Science Q Hugues Caly Hamed Rabiei Perrine Coste-Mazeau Sebastien Hantz Sophie Alain Jean-Luc Eyraud Thierry Chianea Catherine Caly David Makowski Nouchine Hadjikhani Eric Lemonnier Yehezkel Ben-Ari Machine learning analysis of pregnancy data enables early identification of a subpopulation of newborns with ASD |
description |
Abstract To identify newborns at risk of developing ASD and to detect ASD biomarkers early after birth, we compared retrospectively ultrasound and biological measurements of babies diagnosed later with ASD or neurotypical (NT) that are collected routinely during pregnancy and birth. We used a supervised machine learning algorithm with a cross-validation technique to classify NT and ASD babies and performed various statistical tests. With a minimization of the false positive rate, 96% of NT and 41% of ASD babies were identified with a positive predictive value of 77%. We identified the following biomarkers related to ASD: sex, maternal familial history of auto-immune diseases, maternal immunization to CMV, IgG CMV level, timing of fetal rotation on head, femur length in the 3rd trimester, white blood cell count in the 3rd trimester, fetal heart rate during labor, newborn feeding and temperature difference between birth and one day after. Furthermore, statistical models revealed that a subpopulation of 38% of babies at risk of ASD had significantly larger fetal head circumference than age-matched NT ones, suggesting an in utero origin of the reported bigger brains of toddlers with ASD. Our results suggest that pregnancy follow-up measurements might provide an early prognosis of ASD enabling pre-symptomatic behavioral interventions to attenuate efficiently ASD developmental sequels. |
format |
article |
author |
Hugues Caly Hamed Rabiei Perrine Coste-Mazeau Sebastien Hantz Sophie Alain Jean-Luc Eyraud Thierry Chianea Catherine Caly David Makowski Nouchine Hadjikhani Eric Lemonnier Yehezkel Ben-Ari |
author_facet |
Hugues Caly Hamed Rabiei Perrine Coste-Mazeau Sebastien Hantz Sophie Alain Jean-Luc Eyraud Thierry Chianea Catherine Caly David Makowski Nouchine Hadjikhani Eric Lemonnier Yehezkel Ben-Ari |
author_sort |
Hugues Caly |
title |
Machine learning analysis of pregnancy data enables early identification of a subpopulation of newborns with ASD |
title_short |
Machine learning analysis of pregnancy data enables early identification of a subpopulation of newborns with ASD |
title_full |
Machine learning analysis of pregnancy data enables early identification of a subpopulation of newborns with ASD |
title_fullStr |
Machine learning analysis of pregnancy data enables early identification of a subpopulation of newborns with ASD |
title_full_unstemmed |
Machine learning analysis of pregnancy data enables early identification of a subpopulation of newborns with ASD |
title_sort |
machine learning analysis of pregnancy data enables early identification of a subpopulation of newborns with asd |
publisher |
Nature Portfolio |
publishDate |
2021 |
url |
https://doaj.org/article/aa746bd949174332adf32d8f2626063e |
work_keys_str_mv |
AT huguescaly machinelearninganalysisofpregnancydataenablesearlyidentificationofasubpopulationofnewbornswithasd AT hamedrabiei machinelearninganalysisofpregnancydataenablesearlyidentificationofasubpopulationofnewbornswithasd AT perrinecostemazeau machinelearninganalysisofpregnancydataenablesearlyidentificationofasubpopulationofnewbornswithasd AT sebastienhantz machinelearninganalysisofpregnancydataenablesearlyidentificationofasubpopulationofnewbornswithasd AT sophiealain machinelearninganalysisofpregnancydataenablesearlyidentificationofasubpopulationofnewbornswithasd AT jeanluceyraud machinelearninganalysisofpregnancydataenablesearlyidentificationofasubpopulationofnewbornswithasd AT thierrychianea machinelearninganalysisofpregnancydataenablesearlyidentificationofasubpopulationofnewbornswithasd AT catherinecaly machinelearninganalysisofpregnancydataenablesearlyidentificationofasubpopulationofnewbornswithasd AT davidmakowski machinelearninganalysisofpregnancydataenablesearlyidentificationofasubpopulationofnewbornswithasd AT nouchinehadjikhani machinelearninganalysisofpregnancydataenablesearlyidentificationofasubpopulationofnewbornswithasd AT ericlemonnier machinelearninganalysisofpregnancydataenablesearlyidentificationofasubpopulationofnewbornswithasd AT yehezkelbenari machinelearninganalysisofpregnancydataenablesearlyidentificationofasubpopulationofnewbornswithasd |
_version_ |
1718381866756603904 |