Predicting low cognitive ability at age 5 years using perinatal data and machine learning

BACKGROUND

There are no early, accurate, scalable methods for identifying infants at high risk of poor cognitive outcomes in childhood. We aim to develop an explainable predictive model, using machine learning and population-based cohort data, for this purpose.

METHODS

Data were from 8858 participants in the Growing Up in Ireland cohort, a nationally representative study of infants and their primary caregivers (PCGs). Maternal, infant, and socioeconomic characteristics were collected at 9-months and cognitive ability measured at age 5 years. Data preprocessing, synthetic minority oversampling, and feature selection were performed prior to training a variety of machine learning models using ten-fold cross validated grid search to tune hyperparameters. Final models were tested on an unseen test set.

RESULTS

A random forest (RF) model containing 15 participant-reported features in the first year of infant life, achieved an area under the receiver operating characteristic curve (AUROC) of 0.77 for predicting low cognitive ability at age 5. This model could detect 72% of infants with low cognitive ability, with a specificity of 66%.

CONCLUSIONS

Model performance would need to be improved before consideration as a population-level screening tool. However, this is a first step towards early, individual, risk stratification to allow targeted childhood screening.

IMPACT

This study is among the first to investigate whether machine learning methods can be used at a population-level to predict which infants are at high risk of low cognitive ability in childhood. A random forest model using 15 features which could be easily collected in the perinatal period achieved an AUROC of 0.77 for predicting low cognitive ability. Improved predictive performance would be required to implement this model at a population level but this may be a first step towards early, individual, risk stratification.

Prediction of 2-Year Cognitive Outcomes in Very Preterm Infants Using Machine Learning Methods

Importance

Early intervention can improve cognitive outcomes for very preterm infants but is resource intensive. Identifying those who need early intervention most is important.

Objective

To evaluate a model for use in very preterm infants to predict cognitive delay at 2 years of age using routinely available clinical and sociodemographic data.

Design, Setting, and Participants

This prognostic study was based on the Swedish Neonatal Quality Register. Nationwide coverage of neonatal data was reached in 2011, and registration of follow-up data opened on January 1, 2015, with inclusion ending on September 31, 2022. A variety of machine learning models were trained and tested to predict cognitive delay. Surviving infants from neonatal units in Sweden with a gestational age younger than 32 weeks and complete data for the Bayley Scales of Infant and Toddler Development, Third Edition cognitive index or cognitive scale scores at 2 years of corrected age were assessed. Infants with major congenital anomalies were excluded.

Exposures

A total of 90 variables (containing sociodemographic and clinical information on conditions, investigations, and treatments initiated during pregnancy, delivery, and neonatal unit admission) were examined for predictability.

Main Outcomes and Measures

The main outcome was cognitive function at 2 years, categorized as screening positive for cognitive delay (cognitive index score <90) or exhibiting typical cognitive development (score ≥90).

Results

A total of 1062 children (median [IQR] birth weight, 880 [720-1100] g; 566 [53.3%] male) were included in the modeling process, of whom 231 (21.8%) had cognitive delay. A logistic regression model containing 26 predictive features achieved an area under the receiver operating curve of 0.77 (95% CI, 0.71-0.83). The 5 most important features for cognitive delay were non-Scandinavian family language, prolonged duration of hospitalization, low birth weight, discharge to other destination than home, and the infant not receiving breastmilk on discharge. At discharge from the neonatal unit, the full model could correctly identify 605 of 650 infants who would have cognitive delay at 24 months (sensitivity, 0.93) and 1081 of 2350 who would not (specificity, 0.46).

Conclusions and Relevance

The findings of this study suggest that predictive modeling in neonatal care could enable early and targeted intervention for very preterm infants most at risk for developing cognitive impairment.

Big data, machine learning, and population health: predicting cognitive outcomes in childhood

The application of machine learning (ML) to address population health challenges has received much less attention than its application in the clinical setting. One such challenge is addressing disparities in early childhood cognitive development-a complex public health issue rooted in the social determinants of health, exacerbated by inequity, characterised by intergenerational transmission, and which will continue unabated without novel approaches to address it. Early life, the period of optimal neuroplasticity, presents a window of opportunity for early intervention to improve cognitive development. Unfortunately for many, this window will be missed, and intervention may never occur or occur only when overt signs of cognitive delay manifest. In this review, we explore the potential value of ML and big data analysis in the early identification of children at risk for poor cognitive outcome, an area where there is an apparent dearth of research. We compare and contrast traditional statistical methods with ML approaches, provide examples of how ML has been used to date in the field of neurodevelopmental disorders, and present a discussion of the opportunities and risks associated with its use at a population level. The review concludes by highlighting potential directions for future research in this area. IMPACT: To date, the application of machine learning to address population health challenges in paediatrics lags behind other clinical applications. This review provides an overview of the public health challenge we face in addressing disparities in childhood cognitive development and focuses on the cornerstone of early intervention. Recent advances in our ability to collect large volumes of data, and in analytic capabilities, provide a potential opportunity to improve current practices in this field. This review explores the potential role of machine learning and big data analysis in the early identification of children at risk for poor cognitive outcomes.

Predicting Low Cognitive Ability at Age 5-Feature Selection Using Machine Learning Methods and Birth Cohort Data

Objectives: In this study, we applied the random forest (RF) algorithm to birth-cohort data to train a model to predict low cognitive ability at 5 years of age and to identify the important predictive features. Methods: Data was from 1,070 participants in the Irish population-based BASELINE cohort. A RF model was trained to predict an intelligence quotient (IQ) score ≤90 at age 5 years using maternal, infant, and sociodemographic features. Feature importance was examined and internal validation performed using 10-fold cross validation repeated 5 times. Results The five most important predictive features were the total years of maternal schooling, infant Apgar score at 1 min, socioeconomic index, maternal BMI, and alcohol consumption in the first trimester. On internal validation a parsimonious RF model based on 11 features showed excellent predictive ability, correctly classifying 95% of participants. This provides a foundation suitable for external validation in an unseen cohort. Conclusion: Machine learning approaches to large existing datasets can provide accurate feature selection to improve risk prediction. Further validation of this model is required in cohorts representative of the general population.

The predictive value of the ages and stages questionnaire in late infancy for low average cognitive ability at age 5

Aim

This retrospective, longitudinal study examined the predictive value of the ages and stages questionnaire (ASQ) in late infancy for identifying children who progressed to have low cognitive ability at 5 years of age.

Methods

The ASQ was performed on 755 participants from the Irish BASELINE birth cohort at 24 or 27 months of age. Intelligence quotient was measured at age 5 with the Kaufmann Brief Intelligence Test, Second Edition, and low cognitive ability was defined as a score more than 1 standard deviation below the mean. The ASQ’s predictive value was examined, together with other factors associated with low cognitive ability at 5 years.

Results

When the ASQ was performed at 24 or 27 months, the overall sensitivity for identifying low cognitive ability at 5 years was 20.8% and the specificity was 91.1%. Using a total score cut‐off point increased the sensitivity to 46.6% and 71.4% at 24 and 27 months, but specificity fell to 74.1% and 67.2%, respectively. After adjusting for ASQ performance, maternal education and family income were strongly associated with cognitive outcomes at 5 years.

Conclusion

The ASQ did not detect the majority of children with low cognitive ability at age 5. Alternative methods need investigation.

Below Average Cognitive Ability-An under Researched Risk Factor for Emotional-Behavioural Difficulties in Childhood

Children with below average cognitive ability represent a substantial yet under-researched population for whom cognitive and social demands, which increase in complexity year by year, may pose significant challenges. This observational study examines the longitudinal relationship between early cognitive ability and emotional-behavioral difficulties (EBDs) between the age of three and nine. Participants include 7134 children from the population-based cohort study growing up in Ireland. Cognitive ability was measured at age three using the Picture Similarities Scale. A t-score one to two standard deviations below the mean was defined as below average cognitive ability (n = 767). EBDs were measured using the Strengths and Difficulties Questionnaire (SDQ) at three, five, and nine years of age. Generalized linear mixed models and logistic regression were used to examine the relationship. Below average cognitive ability was an independent predictor of higher longitudinal SDQ scores. After adjustment, children with below average cognitive ability were 1.39 times more likely (AOR 1.39, 95% CI 1.17–1.66, p < 0.001) to experience a clinically significant EBD between the ages of three to nine years. This study demonstrates the increased risk of EBDs for children with below average cognitive ability. A scalable method of early identification of at-risk children should be a research priority for public health, enabling early intervention for cognitive and adaptive outcomes.

Physical activity and emotional-behavioural difficulties in young people: a longitudinal population-based cohort study

BACKGROUND

There is growing concern around youth mental health. A population health approach to improve mental health must address, among other issues, economic insecurity, access to housing and education, harm reduction from substance use. As a universal public health intervention, increasing physical activity at a population level may have an important role in our approach. The aim of this study was to examine the longitudinal association between physical activity patterns between childhood and early adolescence and emotional-behavioural difficulties in later adolescence.

METHODS

This study was based on data from the '98 Child cohort of the Growing Up in Ireland Study. Participants were categorized according to physical activity levels at ages 9 and 13. Emotional-behavioural difficulties at age 17 were measured using the parent-reported Strengths and Difficulties Questionnaire. Logistic regression was used to examine the association between physical activity and emotional-behavioural outcomes.

RESULTS

Among 4618 participants included in the regression model, those categorized as Inactive (n=1607) or Reducer (n=1662) were more than twice as likely to have emotional-behavioural difficulties at age 17 compared with those who were Active [adjusted odds ratio (AOR) 2.1, 95% CI 1.46-3.01, P<0.001; AOR 1.93, 95% CI 1.34-2.76, P<0.001, respectively]. Among those with emotional-behavioural difficulties at baseline (n=525), those categorized as Active had 2.3-fold reduced odds for emotional-behavioural problems at age 17 compared with those who were Inactive (AOR 0.43, 95% CI 0.23-0.78, P=0.006).

CONCLUSIONS

Increasing physical activity among adolescents is a safe and sustainable public health intervention associated with improved mental health.

Physical activity and mental health in an Irish population

BACKGROUND

Physical activity represents a modifiable behaviour which may be associated with increased likelihood of experiencing positive mental health.

AIMS

The aim of this study was to examine the association between self-rated physical activity and subjective indicators of both positive and negative mental health in an Irish adult population.

METHODS

Based on data from a population-based, observational, cross-sectional study, participants were categorised using the International Physical Activity Questionnaire (IPAQ) into those who reported that they did and did not meet recommended physical activity requirements. Self-reported positive and negative mental health indicators were assessed using the Energy and Vitality Index (EVI) and the Mental Health Index-5 (MHI-5) from the SF-36 Health Survey Instrument, respectively. Binary logistic regression was used to identify variables independently associated with self-reported positive and negative mental health.

RESULTS

A total of 7539 respondents were included in analysis. Overall, 32% reported that they met recommended minimal physical activity requirements. Self-reported positive and negative mental health were reported by 16 and 9% of respondents, respectively. Compared with those who reported meeting-recommended physical activity requirements, those performing no physical activity were three times less likely to report positive mental health (adjusted odds ratio (OR) 0.39, 95% confidence interval (CI) 0.28-0.55) and three times more likely to report negative mental health (OR 3.27, 95% CI 2.38-4.50).

CONCLUSION

Compared with those who do not, those who report meeting-recommended physical activity requirements are more and less likely to report experiencing positive and negative mental health, respectively. Future policy development around physical activity should take cognisance of the impact of this activity on both physical and mental health outcomes.