Prediction of mental effort derived from an automated vocal biomarker using machine learning in a large-scale remote sample.

Introduction: Biomarkers of mental effort may help to identify subtle cognitive impairments in the absence of task performance deficits. Here, we aim to detect mental effort on a verbal task, using automated voice analysis and machine learning. Methods: Audio data from the digit span backwards task were recorded and scored with automated speech recognition using the online platform NeuroVocalixTM, yielding usable data from 2,764 healthy adults (1,022 male, 1,742 female; mean age 31.4 years). Acoustic features were aggregated across each trial and normalized within each subject. Cognitive load was dichotomized for each trial by categorizing trials at >0.6 of each participants' maximum span as "high load." Data were divided into training (60%), test (20%), and validate (20%) datasets, each containing different participants. Training and test data were used in model building and hyper-parameter tuning. Five classification models (Logistic Regression, Naive Bayes, Support Vector Machine, Random Forest, and Gradient Boosting) were trained to predict cognitive load ("high" vs. "low") based on acoustic features. Analyses were limited to correct responses. The model was evaluated using the validation dataset, across all span lengths and within the subset of trials with a four-digit span. Classifier discriminant power was examined with Receiver Operating Curve (ROC) analysis. Results: Participants reached a mean span of 6.34 out of 8 items (SD = 1.38). The Gradient Boosting classifier provided the best performing model on test data (AUC = 0.98) and showed excellent discriminant power for cognitive load on the validation dataset, across all span lengths (AUC = 0.99), and for four-digit only utterances (AUC = 0.95). Discussion: A sensitive biomarker of mental effort can be derived from vocal acoustic features in remotely administered verbal cognitive tests. The use-case of this biomarker for improving sensitivity of cognitive tests to subtle pathology now needs to be examined.

Altered Cortical Gyrification in Adults Who Were Born Very Preterm and Its Associations With Cognition and Mental Health.

BACKGROUND: The last trimester of pregnancy is a critical period for the establishment of cortical gyrification, and altered folding patterns have been reported following very preterm birth (< 33 weeks of gestation) in childhood and adolescence. However, research is scant on the persistence of such alterations in adulthood and their associations with cognitive and psychiatric outcomes. METHODS: We studied 79 very preterm and 81 age-matched full-term control adults. T1-weighted magnetic resonance images were used to measure a local gyrification index (LGI), indicating the degree of folding across multiple vertices of the reconstructed cortical surface. Group and group-by-sex LGI differences were assessed by means of per-vertex adjustment for cortical thickness and overall intracranial volume. Within-group correlations were also computed between LGI and functional outcomes, including general intelligence (IQ) and psychopathology. RESULTS: Very preterm adults had significantly reduced LGI in extensive cortical regions encompassing the frontal, anterior temporal, and occipitoparietal lobes. Alterations in lateral fronto-temporal-parietal and medial occipitoparietal regions were present in both men and women, although men showed more extensive alterations. In both very preterm and control adults, higher LGI was associated with higher IQ and lower psychopathology scores, with the spatial distribution of these associations substantially differing between the two groups. CONCLUSIONS: Very preterm adults' brains are characterized by significant and widespread local hypogyria, and these alterations might be implicated in cognitive and psychiatric outcomes. Gyrification reflects an early developmental process and provides a fingerprint for very preterm birth.

Verbal Fluency Is Affected by Altered Brain Lateralization in Adults Who Were Born Very Preterm.

Language difficulties have been reported in children and adolescents who were born very preterm (<32 weeks' gestation) and associated with an atypical lateralization of language processing, i.e., increased right-hemispheric engagement. This study used functional magnetic resonance imaging (fMRI) and spherical deconvolution tractography to study the hemodynamic responses associated with verbal fluency processing (easy and hard letter trials) and verbal fluency-related white matter fiber tracts in 64 very preterm born adults and 36 adult controls (mean age: 30 years). Tractography of the arcuate fasciculus (AF) and frontal aslant tract (FAT) was performed. Tracts were quantified in terms of mean volume, hindrance modulated orientational anisotropy, and lateralization, assessed using a laterality index (LI) to indicate hemispheric dominance. During verbal fluency fMRI, very preterm participants displayed decreased hemodynamic response suppression in both the Easy > Rest and Hard > Rest conditions, compared to controls, in superior temporal gyrus (STG), insula, thalamus, and sensorimotor cortex, particularly in the right hemisphere. At the whole-group level, decreased hemodynamic response suppression in the right sensorimotor cortex was associated with worse on-line performance on the hard letter trials. Increased left-laterality in the AF was present alongside increased right hemispheric hemodynamic response suppression in controls. When only right-handed participants were considered, decreased hemodynamic response suppression in the right STG during hard letter trials was related to weaker left and right FAT white matter integrity in the preterm group only. These results show that verbal fluency is affected by altered functional lateralization in adults who were born very preterm.

A dimensional approach to assessing psychiatric risk in adults born very preterm.

BACKGROUND: Individuals who were born very preterm have higher rates of psychiatric diagnoses compared with term-born controls; however, it remains unclear whether they also display increased sub-clinical psychiatric symptomatology. Hence, our objective was to utilize a dimensional approach to assess psychiatric symptomatology in adult life following very preterm birth. METHODS: We studied 152 adults who were born very preterm (before 33 weeks' gestation; gestational range 24-32 weeks) and 96 term-born controls. Participants' clinical profile was examined using the Comprehensive Assessment of At-Risk Mental States (CAARMS), a measure of sub-clinical symptomatology that yields seven subscales including general psychopathology, positive, negative, cognitive, behavioural, motor and emotional symptoms, in addition to a total psychopathology score. Intellectual abilities were examined using the Wechsler Abbreviated Scale of Intelligence. RESULTS: Between-group differences on the CAARMS showed elevated symptomatology in very preterm participants compared with controls in positive, negative, cognitive and behavioural symptoms. Total psychopathology scores were significantly correlated with IQ in the very preterm group only. In order to examine the characteristics of participants' clinical profile, a principal component analysis was conducted. This revealed two components, one reflecting a non-specific psychopathology dimension, and the other indicating a variance in symptomatology along a positive-to-negative symptom axis. K-means (k = 4) were used to further separate the study sample into clusters. Very preterm adults were more likely to belong to a high non-specific psychopathology cluster compared with controls.Conclusion and RelevanceVery preterm individuals demonstrated elevated psychopathology compared with full-term controls. Their psychiatric risk was characterized by a non-specific clinical profile and was associated with lower IQ.

The effect of perinatal brain injury on dopaminergic function and hippocampal volume in adult life.

Perinatal brain injuries, including hippocampal lesions, cause lasting changes in dopamine function in rodents, but it is not known if this occurs in humans. We compared adults who were born very preterm with perinatal brain injury to those born very preterm without perinatal brain injury, and age-matched controls born at full term using [18F]-DOPA PET and structural MRI. Dopamine synthesis capacity was reduced in the perinatal brain injury group relative to those without brain injury (Cohen's d = 1.36, p=0.02) and the control group (Cohen's d = 1.07, p=0.01). Hippocampal volume was reduced in the perinatal brain injury group relative to controls (Cohen's d = 1.17, p=0.01) and was positively correlated with striatal dopamine synthesis capacity (r = 0.344, p=0.03). This is the first evidence in humans linking neonatal hippocampal injury to adult dopamine dysfunction, and provides a potential mechanism linking early life risk factors to adult mental illness.

Volumetric grey matter alterations in adolescents and adults born very preterm suggest accelerated brain maturation.

Previous research investigating structural neurodevelopmental alterations in individuals who were born very preterm demonstrated a complex pattern of grey matter changes that defy straightforward summary. Here we addressed this problem by characterising volumetric brain alterations in individuals who were born very preterm from adolescence to adulthood at three hierarchically related levels - global, modular and regional. We demarcated structural components that were either particularly resilient or vulnerable to the impact of very preterm birth. We showed that individuals who were born very preterm had smaller global grey matter volume compared to controls, with subcortical and medial temporal regions being particularly affected. Conversely, frontal and lateral parieto-temporal cortices were relatively resilient to the effects of very preterm birth, possibly indicating compensatory mechanisms. Exploratory analyses supported this hypothesis by showing a stronger association between lateral parieto-temporal volume and IQ in the very preterm group compared to controls. We then related these alterations to brain maturation processes. Very preterm individuals exhibited a higher maturation index compared to controls, indicating accelerated brain maturation and this was specifically associated with younger gestational age. We discuss how the findings of accelerated maturation might be reconciled with evidence of delayed maturation at earlier stages of development.

Real-Life Impact of Executive Function Impairments in Adults Who Were Born Very Preterm.

OBJECTIVES: Children and adolescents who were born very preterm (≤32 weeks' gestation) are vulnerable to experiencing cognitive problems, including in executive function. However, it remains to be established whether cognitive deficits are evident in adulthood and whether these exert a significant effect on an individual's real-lifeachievement. METHODS: Using a cross-sectional design, we tested a range of neurocognitive abilities, with a focus on executive function, in a sample of 122 very preterm individuals and 89 term-born controls born between 1979 and 1984. Associations between executive function and a range of achievement measures, indicative of a successful transition to adulthood, were examined. RESULTS: Very preterm adults performed worse compared to controls on measures of intellectual ability and executive function with moderate to large effect sizes. They also demonstrated significantly lower achievement levels in terms of years spent in education, employment status, and on a measure of functioning in work and social domains. Results of regression analysis indicated a stronger positive association between executive function and real-life achievement in the very preterm group compared to controls. CONCLUSIONS: Very preterm born adults demonstrate executive function impairments compared to full-term controls, and these are associated with lower achievement in several real-life domains. (JINS, 2017, 23, 381-389).

A multimodal imaging study of recognition memory in very preterm born adults.

Very preterm (<32 weeks of gestation) birth is associated with structural brain alterations and memory impairments throughout childhood and adolescence. Here, we used functional MRI (fMRI) to study the neuroanatomy of recognition memory in 49 very preterm-born adults and 50 controls (mean age: 30 years) during completion of a task involving visual encoding and recognition of abstract pictures. T1-weighted and diffusion-weighted images were also collected. Bilateral hippocampal volumes were calculated and tractography of the fornix and cingulum was performed and assessed in terms of volume and hindrance modulated orientational anisotropy (HMOA). Online recognition memory task performance, assessed with A scores, was poorer in the very preterm compared with the control group. Analysis of fMRI data focused on differences in neural activity between the recognition and encoding trials. Very preterm born adults showed decreased activation in the right middle frontal gyrus and posterior cingulate cortex/precuneus and increased activation in the left inferior frontal gyrus and bilateral lateral occipital cortex (LOC) compared with controls. Hippocampi, fornix and cingulum volume was significantly smaller and fornix HMOA was lower in very preterm adults. Among all the structural and functional brain metrics that showed statistically significant group differences, LOC activation was the best predictor of online task performance (P = 0.020). In terms of association between brain function and structure, LOC activation was predicted by fornix HMOA in the preterm group only (P = 0.020). These results suggest that neuroanatomical alterations in very preterm born individuals may be underlying their poorer recognition memory performance. Hum Brain Mapp 38:644-655, 2017. © 2016 The Authors Human Brain Mapping Published by Wiley Periodicals, Inc.

Reinforcement of the Brain's Rich-Club Architecture Following Early Neurodevelopmental Disruption Caused by Very Preterm Birth.

The second half of pregnancy is a crucial period for the development of structural brain connectivity, and an abrupt interruption of the typical processes of development during this phase caused by the very preterm birth (<33 weeks of gestation) is likely to result in long-lasting consequences. We used structural and diffusion imaging data to reconstruct the brain structural connectome in very preterm-born adults. We assessed its rich-club organization and modularity as 2 characteristics reflecting the capacity to support global and local information exchange, respectively. Our results suggest that the establishment of global connectivity patterns is prioritized over peripheral connectivity following early neurodevelopmental disruption. The very preterm brain exhibited a stronger rich-club architecture than the control brain, despite possessing a relative paucity of white matter resources. Using a simulated lesion approach, we also investigated whether putative structural reorganization takes place in the very preterm brain in order to compensate for its anatomical constraints. We found that connections between the basal ganglia and (pre-) motor regions, as well as connections between subcortical regions, assumed an altered role in the structural connectivity of the very preterm brain, and that such alterations had functional implications for information flow, rule learning, and verbal IQ.

Very Early Brain Damage Leads to Remodeling of the Working Memory System in Adulthood: A Combined fMRI/Tractography Study.

The human brain can adapt to overcome injury even years after an initial insult. One hypothesis states that early brain injury survivors, by taking advantage of critical periods of high plasticity during childhood, should recover more successfully than those who suffer injury later in life. This hypothesis has been challenged by recent studies showing worse cognitive outcome in individuals with early brain injury, compared with individuals with later brain injury, with working memory particularly affected. We invited individuals who suffered perinatal brain injury (PBI) for an fMRI/diffusion MRI tractography study of working memory and hypothesized that, 30 years after the initial injury, working memory deficits in the PBI group would remain, despite compensatory activation in areas outside the typical working memory network. Furthermore we hypothesized that the amount of functional reorganization would be related to the level of injury to the dorsal cingulum tract, which connects medial frontal and parietal working memory structures. We found that adults who suffered PBI did not significantly differ from controls in working memory performance. They exhibited less activation in classic frontoparietal working memory areas and a relative overactivation of bilateral perisylvian cortex compared with controls. Structurally, the dorsal cingulum volume and hindrance-modulated orientational anisotropy was significantly reduced in the PBI group. Furthermore there was uniquely in the PBI group a significant negative correlation between the volume of this tract and activation in the bilateral perisylvian cortex and a positive correlation between this activation and task performance. This provides the first evidence of compensatory plasticity of the working memory network following PBI.