A Neurologist's Guide to Neonatal Neurodevelopmental Assessments and Preterm Brain Injury

An Attention-Based Hemispheric Relation Inference Network for Perinatal Brain Age Prediction

Brain anatomical age is an effective feature to assess the status of the brain, such as atypical development and aging. Although some deep learning models have been developed for estimating infant brain age, the performance of these models was unsatisfactory because few of them considered the developmental characteristics of brain anatomy during the perinatal period-the most rapid and complex developmental stage across the lifespan. The present study proposed an attention-based hemispheric relation inference network (HRINet) that takes advantage of the nature of brain structural lateralization during early development. This model captures the inter-hemispheric relationship using a graph attention mechanism and transmits lateralization information as features to describe the interactive development between bilateral hemispheres. The HRINet was used to estimate the brain age of 531 preterm and full-term neonates from the Developing Human Connectome Project (dHCP) database based on two metrics (mean curvature and sulcal depth) characterizing the folding morphology of the cortex. Our results showed that the HRINet outperformed other benchmark models in fitting the perinatal brain age, with mean absolute error of 0.53 and determination coefficient of 0.89. We also verified the generalizability of the HRINet on an extra independent dataset collected from the Gansu Provincial Maternity and Child-care Hospital. Furthermore, by applying the best-performing model to an independent dataset consisting of 47 scans of preterm infants at term-equivalent age, we showed that the predicted age was significantly lower than the chronological age, suggesting a delayed development of premature brains. Our results demonstrate the effectiveness and generalizability of the HRINet in estimating infant brain age, providing promising clinical applications for assessing neonatal brain maturity.

The reliability and predictive ability of the Test of Infant Motor Performance (TIMP) in a community-based study in Bhaktapur, Nepal

AIM

In a Nepalese setting, to measure the reliability of the Test of Infant Motor Performance (TIMP) and its ability to predict development scores at 6 months.

METHODS

Nepalese infants (n = 705) were assessed by the TIMP when they were 8-12 weeks old and the Bayley Scales of Infant and Toddler Development, 3rd edition (Bayley-III) at 6 months. Inter-rater agreement was expressed by intraclass correlation coefficients (ICCs), the internal consistency by Cronbach's alphas and Pearson correlation coefficients. Predictive ability was estimated in linear regression models.

RESULTS

Inter-rater agreement was excellent (ICCs > 0.93). Alphas for the TIMP total scores were 0.76 for infants born to term and 0.72 in those born preterm. Correlation coefficients between TIMP total and Bayley-III subscale-scores ranged from 0.05 to 0.28 for term infants and from 0.15 to 0.43 for preterm infants. Using American norms, 56.3 % had TIMP scores within average and 43.7 % below average range. Bayley-III subscale scores were lower in children with TIMP scores below the average range, with the strongest estimates for Gross motor and Socio-emotional development.

INTERPRETATION

The reliability of the TIMP was acceptable, and the TIMP could be a feasible tool to monitor infant motor development in low-resource settings. Properties of the TIMP differed according to gestational age.