A machine learning investigation of volumetric and functional MRI abnormalities in adults born preterm

Abstract

Imaging studies have characterized functional and structural brain abnormalities in adults after premature birth, but these investigations have mostly used univariate methods that do not account for hypothesized interdependencies between brain regions or quantify accuracy in identifying individuals. To overcome these limitations, we used multivariate machine learning to identify gray matter volume (GMV) and amplitude of low frequency fluctuations (ALFF) brain patterns that best classify young adults born very preterm/very low birth weight (VP/VLBW; n = 94) from those born full‐term (FT; n = 92). We then compared the spatial maps of the structural and functional brain signatures and validated them by assessing associations with clinical birth history and basic cognitive variables. Premature birth could be predicted with a balanced accuracy of 80.7% using GMV and 77.4% using ALFF. GMV predictions were mediated by a pattern of subcortical and middle temporal reductions and volumetric increases of the lateral prefrontal, medial prefrontal, and superior temporal gyrus regions. ALFF predictions were characterized by a pattern including increases in the thalamus, pre‐ and post‐central gyri, and parietal lobes, in addition to decreases in the superior temporal gyri bilaterally. Decision scores from each classification, assessing the degree to which an individual was classified as a VP/VLBW case, were predicted by the number of days in neonatal hospitalization and birth weight. ALFF decision scores also contributed to the prediction of general IQ, which highlighted their potential clinical significance. Combined, the results clarified previous research and suggested that primary subcortical and temporal damage may be accompanied by disrupted neurodevelopment of the cortex.

Distinct effects of prematurity on MRI metrics of brain functional connectivity, activity, and structure: Univariate and multivariate analyses

“…To our knowledge, this is the first study to show that GA at birth can be inferred at 40 weeks of PMA using measures of regional activity (i.e., fALFF). This result extends the findings of a recent study (Shang 2019) that reported a similar classification performance using fALFF in adults born preterm. Here we further demonstrated that regional negative associations between activity and GA at birth (greater activity in early preterm infants), which has been previously thought to reflect compensatory effects taking place in later phases of brain development (e.g., Shang 2019, see also Karolis 2017 for results on regional volume), can already be detected around birth, simultaneously with positive effects (greater activity in late preterm) in other regions.…”

Birth weight is associated with adolescent brain development: A multimodal imaging study in monozygotic twins

“…For example, individuals with very low BW have been found to have smaller brains overall and alterations in cortical morphology, as compared to individuals with normal BW (Martinussen et al, 2005; Nagy et al, 2009; Shang et al, 2019). Notably, even when BW is within the normal range, structural associations with BW have been found throughout the brain, particularly in midline structures such as the anterior cingulate cortex, paracentral lobule, and precuneus, along with the orbitofrontal, inferior parietal, and temporal cortices (Haukvik et al, 2014; Shang et al, 2019; Walhovd et al, 2012). Additionally, a recent study found that adolescents born very preterm showed altered rs‐FC between the amygdala and various regions (e.g., hippocampus, prefrontal cortex), relative to adolescents born at term with normal weight (Johns, Lacadie, Ment, & Scheinost, 2019).…”

“…In addition to behavioral and cognitive outcomes, several studies conducted in children, adolescents, and adults have found that BW is linked to brain development. For example, individuals with very low BW have been found to have smaller brains overall and alterations in cortical morphology, as compared to individuals with normal BW (Martinussen et al, 2005; Nagy et al, 2009; Shang et al, 2019). Notably, even when BW is within the normal range, structural associations with BW have been found throughout the brain, particularly in midline structures such as the anterior cingulate cortex, paracentral lobule, and precuneus, along with the orbitofrontal, inferior parietal, and temporal cortices (Haukvik et al, 2014; Shang et al, 2019; Walhovd et al, 2012).…”

Interaction of the salience network, ventral attention network, dorsal attention network and default mode network in neonates and early development of the bottom-up attention system

“…Recent studies adopting machine learning methods, have shown that the functional connectivity data (expressed by different metrics) and volume data are able to predict prematurity both in cohorts of newborns (Smyser et al 2016;G et al 2016;Chiarelli et al 2021) and adults (Shang et al 2019) and to classify age in infants aged between 6 and 12 months (Pruett et al 2015).These studies support the view that a functional architecture of the brain exists before birth and constantly evolves, especially during the rst year of life. Changes in functional connectivity of prematurity also manifest in adults, which supports the hypothesis that neurocognitive disorders associated with preterm birth might represent a disease of brain connectivity (J et al 2011).…”

“…By adopting the same SVM method Pruett et al (Pruett et al 2015) were able to classify, above chance, 6 versus 12 months old infants on FC data. Shang et al (Shang et al 2019) used multivariate machine learning methods to classify young adults born prematurely when compared to full-term on the basis of volumetric data and by measuring the amplitude of low frequency uctuations (ALIFF) within a repeated and nested cross-validation design. The authors compared the structural and functional preterm features, validated them by assessing the clinical history and assessed their contribution to the prediction of IQ.…”