Epigenome-wide analysis identifies genes and pathways linked to acoustic cry variation in preterm infants

Epigenome-wide association study identifies neonatal DNA methylation associated with two-year attention problems in children born very preterm

Prior research has identified epigenetic predictors of attention problems in school-aged children but has not yet investigated these in young children, or children at elevated risk of attention problems due to preterm birth. The current study evaluated epigenome-wide associations between neonatal DNA methylation and attention problems at age 2 years in children born very preterm. Participants included 441 children from the Neonatal Neurobehavior and Outcomes in Very Preterm Infants (NOVI) Study, a multi-site study of infants born < 30 weeks gestational age. DNA methylation was measured from buccal swabs collected at NICU discharge using the Illumina MethylationEPIC Bead Array. Attention problems were assessed at 2 years of adjusted age using the attention problems subscale of the Child Behavior Checklist (CBCL). After adjustment for multiple testing, DNA methylation at 33 CpG sites was associated with child attention problems. Differentially methylated CpG sites were located in genes previously linked to physical and mental health, including several genes associated with ADHD in prior epigenome-wide and genome-wide association studies. Several CpG sites were located in genes previously linked to exposure to prenatal risk factors in the NOVI sample. Neonatal epigenetics measured at NICU discharge could be useful in identifying preterm children at risk for long-term attention problems and related psychiatric disorders, who could benefit from early prevention and intervention efforts.

Environmental influences on child health outcomes: cohorts of individuals born very preterm

The National Institutes of Health's Environmental influences on Child Health Outcomes (ECHO) Program was designed to address solution-oriented research questions about the links between children's early life environment and their risks of pre-, peri-, and post-natal complications, asthma, obesity, neurodevelopmental disorders, and positive health. Children born very preterm are at increased risk for many of the outcomes on which ECHO focuses, but the contributions of environmental factors to this risk are not well characterized. Three ECHO cohorts consist almost exclusively of individuals born very preterm. Data provided to ECHO from cohorts can be used to address hypotheses about (1) differential risks of chronic health and developmental conditions between individuals born very preterm and those born at term; (2) health disparities across social determinants of health; and (3) mechanisms linking early-life exposures and later-life outcomes among individuals born very preterm. IMPACT: The National Institutes of Health's Environmental Influences on Child Health Outcomes Program is conducting solution-oriented research on the links between children's environment and health. Three ECHO cohorts comprise study participants born very preterm; these cohorts have enrolled, to date, 1751 individuals born in 14 states in the U.S. in between April 2002 and March 2020. Extensive data are available on early-life environmental exposures and child outcomes related to neurodevelopment, asthma, obesity, and positive health. Data from ECHO preterm cohorts can be used to address questions about the combined effects of preterm birth and environmental exposures on child health outcomes.

Newborn Cry Acoustics in the Assessment of Neonatal Opioid Withdrawal Syndrome Using Machine Learning

IMPORTANCE

The assessment of opioid withdrawal in the neonate, or neonatal opioid withdrawal syndrome (NOWS), is problematic because current assessment methods are based on subjective observer ratings. Crying is a distinctive component of NOWS assessment tools and can be measured objectively using acoustic analysis.

OBJECTIVE

To evaluate the feasibility of using newborn cry acoustics (acoustics referring to the physical properties of sound) as an objective biobehavioral marker of NOWS.

DESIGN, SETTING, AND PARTICIPANTS

This prospective controlled cohort study assessed whether acoustic analysis of neonate cries could predict which infants would receive pharmacological treatment for NOWS. A total of 177 full-term neonates exposed and not exposed to opioids were recruited from Women & Infants Hospital of Rhode Island between August 8, 2016, and March 18, 2020. Cry recordings were processed for 118 neonates, and 65 neonates were included in the final analyses. Neonates exposed to opioids were monitored for signs of NOWS using the Finnegan Neonatal Abstinence Scoring Tool administered every 3 hours as part of a 5-day observation period during which audio was recorded continuously to capture crying. Crying of healthy neonates was recorded before hospital discharge during routine handling (eg, diaper changes).

EXPOSURES

The primary exposure was prenatal opioid exposure as determined by maternal receipt of medication-assisted treatment with methadone or buprenorphine.

MAIN OUTCOMES AND MEASURES

Neonates were stratified by prenatal opioid exposure and receipt of pharmacological treatment for NOWS before discharge from the hospital. In total, 775 hours of audio were collected and trimmed into 2.5 hours of usable cries, then acoustically analyzed (using 2 separate acoustic analyzers). Cross-validated supervised machine learning methods (combining the Boruta algorithm and a random forest classifier) were used to identify relevant acoustic parameters and predict pharmacological treatment for NOWS.

RESULTS

Final analyses included 65 neonates (mean [SD] gestational age at birth, 36.6 [1.1] weeks; 36 [55.4%] female; 50 [76.9%] White) with usable cry recordings. Of those, 19 neonates received pharmacological treatment for NOWS, 7 neonates were exposed to opioids but did not receive pharmacological treatment for NOWS, and 39 healthy neonates were not exposed to opioids. The mean of the predictions of random forest classifiers predicted receipt of pharmacological treatment for NOWS with high diagnostic accuracy (area under the curve, 0.90 [95% CI, 0.83-0.98]; accuracy, 0.85 [95% CI, 0.74-0.92]; sensitivity, 0.89 [95% CI, 0.67-0.99]; specificity, 0.83 [95% CI, 0.69-0.92]).

CONCLUSIONS AND RELEVANCE

In this study, newborn acoustic cry analysis had potential as an objective measure of opioid withdrawal. These findings suggest that acoustic cry analysis using machine learning could improve the assessment, diagnosis, and management of NOWS and facilitate standardized care for these infants.