scholarly journals Language function following preterm birth: prediction using machine learning

Author(s):  
Evdoxia Valavani ◽  
Manuel Blesa ◽  
Paola Galdi ◽  
Gemma Sullivan ◽  
Bethan Dean ◽  
...  

Abstract Background Preterm birth can lead to impaired language development. This study aimed to predict language outcomes at 2 years corrected gestational age (CGA) for children born preterm. Methods We analysed data from 89 preterm neonates (median GA 29 weeks) who underwent diffusion MRI (dMRI) at term-equivalent age and language assessment at 2 years CGA using the Bayley-III. Feature selection and a random forests classifier were used to differentiate typical versus delayed (Bayley-III language composite score <85) language development. Results The model achieved balanced accuracy: 91%, sensitivity: 86%, and specificity: 96%. The probability of language delay at 2 years CGA is increased with: increasing values of peak width of skeletonized fractional anisotropy (PSFA), radial diffusivity (PSRD), and axial diffusivity (PSAD) derived from dMRI; among twins; and after an incomplete course of, or no exposure to, antenatal corticosteroids. Female sex and breastfeeding during the neonatal period reduced the risk of language delay. Conclusions The combination of perinatal clinical information and MRI features leads to accurate prediction of preterm infants who are likely to develop language deficits in early childhood. This model could potentially enable stratification of preterm children at risk of language dysfunction who may benefit from targeted early interventions. Impact A combination of clinical perinatal factors and neonatal DTI measures of white matter microstructure leads to accurate prediction of language outcome at 2 years corrected gestational age following preterm birth. A model that comprises clinical and MRI features that has potential to be scalable across centres. It offers a basis for enhancing the power and generalizability of diagnostic and prognostic studies of neurodevelopmental disorders associated with language impairment. Early identification of infants who are at risk of language delay, facilitating targeted early interventions and support services, which could improve the quality of life for children born preterm.

Author(s):  
Imac Maria Zambrana ◽  
Margarete E. Vollrath ◽  
Bo Jacobsson ◽  
Verena Sengpiel ◽  
Eivind Ystrom

Abstract We investigated whether children born preterm are at risk for language delay using a sibling-control design in the Norwegian Mother and Child Cohort Study (MoBa), conducted by the Norwegian Institute of Public Health. Participants included 26,769 siblings born between gestational weeks 23 and 42. Language delay was assessed when the children were 1.5, 3, and 5 years old. To adjust for familial risk factors, comparisons were conducted between preterm and full-term siblings. Pregnancy-specific risk factors were controlled for by means of observed variables. Findings showed that preterm children born before week 37 had increased risk for language delays at 1.5 years. At 3 and 5 years, only children born before week 34 had increased risk for language delay. Children born weeks 29–33 and before week 29 had increased risk for language delay at 1.5 years (RR = 4.51, 95% CI [3.45, 5.88]; RR = 10.32, 95% CI [6.7, 15.80]), 3 years (RR = 1.50, 95% CI [1.02, 2.21]; RR = 2.78, 95% CI [1.09, 7.07]), and 5 years (RR = 1.63, 95% CI [1.06, 2.51]; RR = 2.98, 95% CI [0.87, 10.26]), respectively. In conclusion, children born preterm are at risk for language delays, with familial confounders only explaining a moderate share of the association. This suggests a cause-effect relationship between early preterm birth and risk for language delay in preschool children.


2020 ◽  
Vol 75 (11) ◽  
pp. 659-662
Author(s):  
Devin D. Smith ◽  
Deepika Sagaram ◽  
Russell Miller ◽  
Cynthia Gyamfi-Bannerman

1994 ◽  
Vol 35 (3) ◽  
pp. 240-254
Author(s):  
Naomi Iizuka ◽  
Tsuneo Satake ◽  
Junko Itoh ◽  
Takeshi Tohkawa

Children ◽  
2021 ◽  
Vol 8 (3) ◽  
pp. 174
Author(s):  
Samira Samiee-Zafarghandy ◽  
Tamara van Donge ◽  
Karel Allegaert ◽  
John van den Anker

In methadone-exposed preterm neonates, early identification of those at risk of severe neonatal abstinence syndrome (NAS) and use of a methadone dosing regimen that can provide effective and safe drug exposure are two important aspects of optimal care. To this end, we reviewed 17 methadone dosing recommendations in the international guidelines and literature and explored their variability in key dosing strategies. We selected three of the reviewed dosing regimens for their pharmacokinetics (PK) characteristics and their exposure–response relationship in three gestational age groups of preterm neonates (28, 32 and 36 gestational age weeks) at risk for development of severe NAS (defined as an umbilical cord methadone concentration of ≤60 ng/mL, following fetal exposure). We applied early (12 h after birth) vs. typical (36 h after birth) initiation of treatment. We observed that use of universally recommended dosing regimens in preterm neonates can result in under- or over-exposure. Use of a PK-guided dosing regimen resulted in effective target exposures within 24 h after birth with early initiation of treatment (12 h after birth). Future prospective studies should explore the incorporation of umbilical cord methadone concentrations for early identification of preterm neonates at risk of developing severe NAS and investigate the use of a PK-guided methadone dosing regimen, so that treatment failure, prolonged length of stay and opioid over-exposure can be avoided.


2008 ◽  
Vol 199 (6) ◽  
pp. S215 ◽  
Author(s):  
Dana Figueroa ◽  
Melissa Mancuso ◽  
Merri Maddox Paden ◽  
Jeff Szychowski ◽  
John Owen

2018 ◽  
Vol 33 (12) ◽  
pp. 2059-2063 ◽  
Author(s):  
Devin D. Smith ◽  
Deepika Sagaram ◽  
Russell Miller ◽  
Cynthia Gyamfi-Bannerman

2019 ◽  
Vol 104 (6) ◽  
pp. e43.1-e43
Author(s):  
S M ◽  
L Lewis ◽  
S Mallayasamy

BackgroundCurrent dosage regimen of aminophylline is similar in both Appropriate for Gestational Age (AGA) and Small for Gestational Age (SGA) preterm neonates.1 In contrast with AGA babies, SGA babies handle drugs in different way. However, developing countries like India has significant proportion of Growth Restricted/SGA babies. Hence, there is a need to develop appropriate dosage regimen in this population. Objective of the current study was set to develop and qualify the Population-Pharmacokinetic (PPK) model for aminophylline in premature neonates in Indian population.2MethodsAminophylline-treated neonates with IV loading dose of 5 mg/kg followed by maintenance dose of 1.5 or 2 mg/kg 8th hourly for Apnoea of Prematurity (AOP) were included. Any other conditions for secondary causes were excluded. Blood samples were collected by adopting sparse sample scheme and estimated by LCMS-MS. PPK model was developed with appropriate covariates.3 Data was analysed by NONMEM vesion 7.3. Non-parametric bootstrap procedure and Visual Predictive Check (VPC) was used to qualify the developed model.ResultsOne compartment, first-order structured model was fitted to the dataset containing 454 observations from 107 neonates. PPK parameters were represented as model estimated values and variability was depicted as% Co-efficient of variation (%CV). Typical population value of CL was 0.011 L/hour with inter-individual variability (IIV) of 59% and V was 0.332 (L/kg) with 31% IIV. Residual error was found to be 19%. Only postnatal age (PNA) had significant effect on V which was assessed by forward addition and backword elimination regression model.ConclusionAGA and SGA had no influence on PK parameters. However, PNA showed to have significant influence on V. Developed nomogram based on the qualified model may be effective and safe for aminophylline therapy in preterm neonates with apnoea.ReferencesShivakumar M, Jayashree P, Najih M, Lewis LES, Bhat Y R, Kamath A, et al. Comparative Efficacy and Safety of Caffeine and Aminophylline for Apnea of Prematurity in Preterm (≤34 weeks) Neonates: A Randomized Controlled Trial. Indian Pediatr 2017 Apr 15;54(4):279–83.U S Department of Health and Human Services, FDA, Center for Drug Evaluation and Research (CDER), Center for Biologics Evaluation and Research (CBER): Guidance for Industry Population pharmacokinetics; 1991; Feb CP1, 35 pages.Ette EI, Sun H, Ludden TM, Balanced designs in longitudinal Population Pharmacokinetic studies. Journal of Clinical Pharmacology 1998 May; 38(5):417–423.Disclosure(s)Nothing to disclose


Author(s):  
Tamta Ivanashvili

Global progress in child survival and health cannot be achieved without addressing preterm birth, because every year an estimated 15 million babies are born preterm. Over 1 million children die each year due to complications of preterm birth. Complications highly associated with prematurity include acute respiratory, gastrointestinal, immunologic, central nervous system, as well as longer-term motor, cognitive, behavioral, social-emotional, health, growth and language problems. The aim of the study was assessment of language skills at school aged children born premature and identification of risk factors affecting language development outcomes. Case-control retrospective study was conducted in Child Developmental Center of M. Iashvili Children’s Central Hospital (Georgia, Tbilisi).We evaluate language skills in 72+3 months old children (n=134). Children were divided into study (n=80) and control (n=54) groups. Groups were homogenous based on child age, gender, maternal health, maternal education, household income, family structure. Statistical analysis was based on SPSS 20. The difference in language development assessment among the full-term and late preterm children shows low correlation and is not significant (Cramer’s V is 0,118; Pearson Chi-square data 0,098 (p>0,05). While the language assessment data in early and moderate preterm group compared to term infants show significant difference (Cramer’s V is 0,354, Pearson Chi-square data 0,004). Statistical analysis show medium correlation, value (p<0,05), which tell us, that language development is a significantly associated with gestational age. So, small gestational age is correlated with language development problems. Early detection of minimal delays and starting early intervention services can improve developmental outcomes of preterm children. High-quality and stable child care is important for all infants, but especially to those who may be at risk of prematurity.


2021 ◽  
Author(s):  
Xi Wang ◽  
Nora L Lee ◽  
Igor Burstyn

AbstractWe aimed to estimate exposure-response associations between smoking or vaping, and preterm and small-for-gestational age (SGA) births. We included 99,201 mothers who delivered live singletons in 2016-2018 from the Pregnancy Risk Assessment Monitoring System. We created exposure categories based on participants’ self-reported average number of cigarettes smoked per day and vaping frequency. Dual users in late pregnancy were a heterogeneous group: 36% heavily smoked and occasionally vaped; 29% lightly smoked and frequently vaped; 19% lightly smoked and frequently vaped; and 15% both heavily smoked and frequently vaped. While dual users who heavily smoked and occasionally vaped had the highest adjusted OR for SGA (3.4, 95% CI 1.7-6.6), all the dual users were on average at about twice the odds of having SGA than non-users. While the risks of preterm birth were higher among sole light smokers (adjusted OR 1.3, 95% CI 1.1-1.5) and sole heavy smokers (adjusted OR 1.4. 95 CI 1.2-1.8) than non-users, the adjusted odds of preterm births for dual users were not noticeably higher than those of non-users, unless they were also heavy smokers. Excess of preterm births among heavy vapers was suggested. Among younger non-Hispanic white women (where vaping is most common), only excess risk of SGA, not preterm, with vaping was apparent. Relative to non-users, both smoking and vaping during pregnancy appear to increase risk of SGA, but excess risk of preterm births appears to be primarily attributable to smoking alone. Higher levels of exposure tended to confer more risk.HighlightsNo observable change in prevalence of vaping during pregnancy from 2016 to 2018Both smoking and vaping during pregnancy appear to increase risk of SGA birthsExcess risk of preterm births appears to be primarily attributable to smoking alone


Sign in / Sign up

Export Citation Format

Share Document