Summary: By combining pregnancy and childbirth data with machine learning technology, the researchers identified 17 out of 40 factors that are particularly important in predicting the number of ADHD symptoms in childhood.
Information available at birth can help identify children most likely to develop ADHD, according to a new study from the University of Medicine and Health Sciences RCSI.
The study, published in Development and psychopathologyexamined data from nearly 10,000 children in the United States, showing information about pregnancy and birth can help predict the extent of ADHD symptoms in childhood.
The Adolescent Brain Cognitive Development (ABCD) Study is an ongoing study of children in the United States, born between 2005 and 2009. Children were enrolled in the study at ages 9 to 10 and their parents were asked about aspects of pregnancy and childbirth, as well as the current mental health of their child.
RCSI researchers identified 40 factors that would typically be known at birth, including the sex of the baby, the age of the parents, any complications during pregnancy or delivery, and the baby’s exposure in the womb to factors such as cigarette smoke.
Using machine learning and statistical techniques, the researchers found that 17 of 40 factors were particularly good at predicting the number of ADHD symptoms in childhood.
Co-Principal Investigator Dr Niamh Dooley from RCSI’s Department of Psychiatry explained that few studies to date have looked at how prenatal and birth information might be useful in predicting ADHD: “We know that some events during our time in the womb can have lasting consequences on our health, but few studies have attempted to quantify how useful prenatal information could be to predict ADHD symptoms in children.
“We focused on readily available information about pregnancies and births, the kind that would be found in prenatal records. This ensures that our results can be compared to other studies using medical records and are relevant to public health.
“The other key element of this study was the recognition of the contribution of social, economic and demographic factors to maternal and child health. For example, prenatal information did not predict ADHD symptoms equally across gender, family income brackets, or racial/ethnic groups,” Dr. Dooley said.
Professor Mary Cannon, Professor of Psychiatric Epidemiology and Youth Mental Health at RCSI and co-lead of the study, commented: “Although we have only explained up to 10% of the variation in symptoms of Childhood ADHD was with information generally available at birth.
“We cannot predict who will develop ADHD in childhood with birth information alone, but it can help identify children who need support the most, especially when combined with other factors. such as genetics or family history and early childhood environment.
“In our study, mothers were asked about their pregnancy and the birth of their child, 9 to 10 years earlier. The next step would be to conduct a study in a group that was followed in real time during pregnancy, birth and childhood. This would build our confidence in this prenatal information and our confidence that it can help identify children at risk of developing ADHD, at a very early stage in life.
Factors that stood out in the study as being helpful in predicting ADHD symptoms in childhood included being male, as well as exposure to factors in the womb such as cigarette smoke. , recreational drugs and the mother having urinary tract infections or low iron levels.
Funding: This research was supported by a StAR International PhD Fellowship, Health Research Board, European Research Council, Wellcome Trust and Science Foundation Ireland. The ABCD study is supported by the National Institutes of Health (NIH) and other federal partners (abcdstudy.org).
About this ADHD research news
Author: Rosie Duffy
Contact: Rosie Duffy – RCSI
Picture: Image is in public domain
Original research: Access closed.
“Predicting Childhood ADHD-Related Symptoms from Prenatal and Perinatal Data in the ABCD Cohort” by Niamh Dooley et al. Development and psychopathology
Predicting Childhood ADHD-Related Symptoms from Prenatal and Perinatal Data in the ABCD Cohort
This study examines the ability of pre/perinatal factors to predict symptoms of attention deficit/hyperactivity disorder (ADHD) in childhood. It also explores whether the predictive accuracy of a pre/perinatal model varies across different population groups.
We used the Adolescent Brain Cognitive Development (ABCD) cohort from the United States (NOT = 9975). The pre/perinatal information and child behavior checklist were reported by the parent when the child was 9-10 years old.
Forty variables that are commonly known at birth were captured as potential predictors, including maternal substance use, obstetric complications, and child demographics. Net elastic regression with 5-fold validation was performed and then stratified by gender, race/ethnicity, household income, and parental psychopathology.
Seventeen pre/perinatal variables were identified as robust predictors of ADHD symptoms in this cohort.
The model explained only 8.13% of the variance in ADHD symptoms on average (95% CI = 5.6% to 11.5%). The predictive accuracy of the model varied considerably by subgroup, particularly across income groups, and several pre/perinatal factors appeared to be gender-specific.
The results suggest that we may be able to predict ADHD symptoms in children with modest accuracy from birth. This study should be replicated using prospectively measured pre/perinatal data.