Literature DB >> 32279900

Neonatal Brain Microstructure and Machine-Learning-Based Prediction of Early Language Development in Children Born Very Preterm.

Rachel Vassar1, Kornél Schadl2, Katelyn Cahill-Rowley3, Kristen Yeom4, David Stevenson5, Jessica Rose6.   

Abstract

BACKGROUND: Very-low-birth-weight preterm infants have a higher rate of language impairments compared with children born full term. Early identification of preterm infants at risk for language delay is essential to guide early intervention at the time of optimal neuroplasticity. This study examined near-term structural brain magnetic resonance imaging (MRI) and white matter microstructure assessed on diffusion tensor imaging (DTI) in relation to early language development in children born very preterm.
METHODS: A total of 102 very-low-birth-weight neonates (birthweight≤1500g, gestational age ≤32-weeks) were recruited to participate from 2010 to 2011. Near-term structural MRI was evaluated for white matter and cerebellar abnormalities. DTI fractional anisotropy, mean diffusivity, axial diffusivity, and radial diffusivity were assessed. Language development was assessed with Bayley Scales of Infant-Toddler Development-III at 18 to 22 months adjusted age. Multivariate models with leave-one-out cross-validation and exhaustive feature selection identified three brain regions most predictive of language function. Distinct logistic regression models predicted high-risk infants, defined by language scores >1 S.D. below average.
RESULTS: Of 102 children, 92 returned for neurodevelopmental testing. Composite language score mean ± S.D. was 89.0 ± 16.0; 31 of 92 children scored <85, including 15 of 92 scoring <70, suggesting moderate-to-severe delay. Children with cerebellar asymmetry had lower receptive language subscores (P = 0.016). Infants at high risk for language impairments were predicted based on regional white matter microstructure on DTI with high accuracy (sensitivity, specificity) for composite (89%, 86%), expressive (100%, 90%), and receptive language (100%, 90%).
CONCLUSIONS: Multivariate models of near-term structural MRI and white matter microstructure on DTI may assist in identification of preterm infants at risk for language impairment, guiding early intervention.
Copyright © 2020 Elsevier Inc. All rights reserved.

Entities:  

Keywords:  Diffusion tensor imaging; Early language development; Machine learning; Preterm infants

Mesh:

Year:  2020        PMID: 32279900     DOI: 10.1016/j.pediatrneurol.2020.02.007

Source DB:  PubMed          Journal:  Pediatr Neurol        ISSN: 0887-8994            Impact factor:   3.372


  4 in total

1.  A self-training deep neural network for early prediction of cognitive deficits in very preterm infants using brain functional connectome data.

Authors:  Redha Ali; Hailong Li; Jonathan R Dillman; Mekibib Altaye; Hui Wang; Nehal A Parikh; Lili He
Journal:  Pediatr Radiol       Date:  2022-09-22

Review 2.  Machine learning for understanding and predicting neurodevelopmental outcomes in premature infants: a systematic review.

Authors:  Stephanie Baker; Yogavijayan Kandasamy
Journal:  Pediatr Res       Date:  2022-05-31       Impact factor: 3.953

3.  Early Predictors of Poor Neurologic Outcomes in a Prospective Cohort of Infants With Antenatal Exposure to Zika Virus.

Authors:  Sophia Finn Tiene; Jessica S Cranston; Karin Nielsen-Saines; Tara Kerin; Trevon Fuller; Zilton Vasconcelos; Peter B Marschik; Dajie Zhang; Marcos Pone; Sheila Pone; Andrea Zin; Elizabeth Brickley; Dulce Orofino; Patricia Brasil; Kristina Adachi; Ana Carolina C da Costa; Maria Elisabeth Lopes Moreira
Journal:  Pediatr Infect Dis J       Date:  2022-03-01       Impact factor: 3.806

Review 4.  [Early detection of primary developmental language disorders-increasing relevance due to changes in diagnostic criteria?]

Authors:  Christiane Kiese-Himmel
Journal:  Bundesgesundheitsblatt Gesundheitsforschung Gesundheitsschutz       Date:  2022-07-21       Impact factor: 1.595

  4 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.