Multi-feature concatenation and multi-classifier stacking: An interpretable and generalizable machine learning method for MDD discrimination with rsfMRI.

Major depressive disorder (MDD) is a serious and heterogeneous psychiatric disorder that needs accurate diagnosis. Resting-state functional MRI (rsfMRI), which captures multiple perspectives on brain structure, function, and connectivity, is increasingly applied in the diagnosis and pathological research of MDD. Different machine learning algorithms are then developed to exploit the rich information in rsfMRI and discriminate MDD patients from normal controls. Despite recent advances reported, the MDD discrimination accuracy has room for further improvement. The generalizability and interpretability of the discrimination method are not sufficiently addressed either. Here, we propose a machine learning method (MFMC) for MDD discrimination by concatenating multiple features and stacking multiple classifiers. MFMC is tested on the REST-meta-MDD data set that contains 2428 subjects collected from 25 different sites. MFMC yields 96.9% MDD discrimination accuracy, demonstrating a significant improvement over existing methods. In addition, the generalizability of MFMC is validated by the good performance when the training and testing subjects are from independent sites. The use of XGBoost as the meta classifier allows us to probe the decision process of MFMC. We identify 13 feature values related to 9 brain regions including the posterior cingulate gyrus, superior frontal gyrus orbital part, and angular gyrus, which contribute most to the classification and also demonstrate significant differences at the group level. The use of these 13 feature values alone can reach 87% of MFMC's full performance when taking all feature values. These features may serve as clinically useful diagnostic and prognostic biomarkers for MDD in the future.

Brain-age prediction: Systematic evaluation of site effects, and sample age range and size.

Structural neuroimaging data have been used to compute an estimate of the biological age of the brain (brain-age) which has been associated with other biologically and behaviorally meaningful measures of brain development and aging. The ongoing research interest in brain-age has highlighted the need for robust and publicly available brain-age models pre-trained on data from large samples of healthy individuals. To address this need we have previously released a developmental brain-age model. Here we expand this work to develop, empirically validate, and disseminate a pre-trained brain-age model to cover most of the human lifespan. To achieve this, we selected the best-performing model after systematically examining the impact of seven site harmonization strategies, age range, and sample size on brain-age prediction in a discovery sample of brain morphometric measures from 35,683 healthy individuals (age range: 5-90 years; 53.59% female). The pre-trained models were tested for cross-dataset generalizability in an independent sample comprising 2101 healthy individuals (age range: 8-80 years; 55.35% female) and for longitudinal consistency in a further sample comprising 377 healthy individuals (age range: 9-25 years; 49.87% female). This empirical examination yielded the following findings: (1) the accuracy of age prediction from morphometry data was higher when no site harmonization was applied; (2) dividing the discovery sample into two age-bins (5-40 and 40-90 years) provided a better balance between model accuracy and explained age variance than other alternatives; (3) model accuracy for brain-age prediction plateaued at a sample size exceeding 1600 participants. These findings have been incorporated into CentileBrain (https://centilebrain.org/#/brainAGE2), an open-science, web-based platform for individualized neuroimaging metrics.

Psychological resilience-related functional connectomes predict creative personality.

Both psychological resilience and creativity are complex concepts that have positive effects on individual adaptation. Previous studies have shown overlaps between the key brain regions or brain functional networks related to psychological resilience and creativity. However, no direct experimental evidence has been provided to support the assumption that psychological resilience and creativity share a common brain basis. Therefore, the present study investigated the relationship between psychological resilience and creativity using neural imaging method with a machine learning approach. At the behavioral level, we found that psychological resilience was positively related to creative personality. Predictive analysis based on static functional connectivity (FC) and dynamic FC demonstrated that FCs related to psychological resilience could effectively predict an individual's creative personality score. Both the static FC and dynamic FC were mainly located in the default mode network. These results prove that psychological resilience and creativity share a common brain functional basis. These findings also provide insights into the possibility of promoting individual positive adaptation from negative events or situations in a creative way.

Diverse functional interaction driven by control-default network hubs supports creative thinking.

Complex cognitive processes, like creative thinking, rely on interactions among multiple neurocognitive processes to generate effective and innovative behaviors on demand, for which the brain's connector hubs play a crucial role. However, the unique contribution of specific hub sets to creative thinking is unknown. Employing three functional magnetic resonance imaging datasets (total N = 1,911), we demonstrate that connector hub sets are organized in a hierarchical manner based on diversity, with "control-default hubs"-which combine regions from the frontoparietal control and default mode networks-positioned at the apex. Specifically, control-default hubs exhibit the most diverse resting-state connectivity profiles and play the most substantial role in facilitating interactions between regions with dissimilar neurocognitive functions, a phenomenon we refer to as "diverse functional interaction". Critically, we found that the involvement of control-default hubs in facilitating diverse functional interaction robustly relates to creativity, explaining both task-induced functional connectivity changes and individual creative performance. Our findings suggest that control-default hubs drive diverse functional interaction in the brain, enabling complex cognition, including creative thinking. We thus uncover a biologically plausible explanation that further elucidates the widely reported contributions of certain frontoparietal control and default mode network regions in creativity studies.

Being bold wisely: neural substrates underlying ability to exploit risk.

Nothing ventured, nothing gained. To succeed one must take risks, and more importantly, take risks wisely, which depends on individual ability to exploit risk. Here, we explore neural substrates for the ability to exploit risk by using voxel-based morphometry (VBM). First, we carried out structural magnetic resonance imaging and measured individual risk-taking propensity and corresponding earnings by administrating the Balloon Analogue Risk Task in 1,389 participants. Behavior analysis revealed an inverted-U-shaped relation between risk-taking propensity and earnings, that earnings initially increased and then decreased as risk-taking propensity increased. Then individual ability to exploit risk was estimated by calculating the difference between individual actual earnings and the average earnings of the group at the same level of risk-taking propensity. VBM analysis revealed that individual ability to exploit risk was positively correlated with the gray matter volumes of three clusters located in the right orbitofrontal cortex, left dorsolateral prefrontal cortex (dlPFC), and right dlPFC, respectively. These findings highlight the neural substrates for the ability to exploit risk and implicate that precise valuation, adaptive learning, and self-control may underpin the ability to exploit risk, which expand our understanding of the ability to exploit risk and its neural substrates.

Retrieval flexibility links to creativity: evidence from computational linguistic measure.

Creativity, the ability to generate original and valuable products, has long been linked to semantic retrieval processes. The associative theory of creativity posits flexible retrieval ability as an important basis for creative idea generation. However, there is insufficient research on how flexible memory retrieval acts on creative activities. This study aimed to capture different dynamic aspects of retrieval processes and examine the behavioral and neural associations between retrieval flexibility and creativity. We developed 5 metrics to quantify retrieval flexibility based on previous studies, which confirmed the important role of creativity. Our findings showed that retrieval flexibility was positively correlated with multiple creativity-related behavior constructs and can promote distinct search patterns in different creative groups. Moreover, high flexibility was associated with the lifetime of a specific brain state during rest, characterized by interactions among large-scale cognitive brain systems. The flexible functional connectivity within and between default mode, executive control, and salience provides further evidence on brain dynamics of creativity. Retrieval flexibility mediated the links between the lifetime of the related brain state and creativity. This new approach is expected to enhance our knowledge of the role of retrieval flexibility in creativity from a dynamic perspective.

Reduced hippocampal-cortical connectivity during memory suppression predicts the ability to forget unwanted memories.

The ability to suppress unwelcome memories is important for productivity and well-being. Successful memory suppression is associated with hippocampal deactivations and a concomitant disruption of this region's functionality. Much of the previous neuroimaging literature exploring such suppression-related hippocampal modulations has focused on the region's negative coupling with the prefrontal cortex. Task-based changes in functional connectivity between the hippocampus and other brain regions still need further exploration. In the present study, we utilize psychophysiological interactions and seed connectome-based predictive modeling to investigate the relationship between the hippocampus and the rest of the brain as 134 participants attempted to suppress unwanted memories during the Think/No-Think task. The results show that during retrieval suppression, the right hippocampus exhibited decreased functional connectivity with visual cortical areas (lingual and cuneus gyrus), left nucleus accumbens and the brain-stem that predicted superior forgetting of unwanted memories on later memory tests. Validation tests verified that prediction performance was not an artifact of head motion or prediction method and that the negative features remained consistent across different brain parcellations. These findings suggest that systemic memory suppression involves more than the modulation of hippocampal activity-it alters functional connectivity patterns between the hippocampus and visual cortex, leading to successful forgetting.

Risk of insomnia during COVID-19: effects of depression and brain functional connectivity.

Normal sleepers may be at risk for insomnia during COVID-19. Identifying psychological factors and neural markers that predict their insomnia risk, as well as investigating possible courses of insomnia development, could lead to more precise targeted interventions for insomnia during similar public health emergencies. Insomnia severity index of 306 participants before and during COVID-19 were employed to determine the development of insomnia, while pre-COVID-19 psychometric and resting-state fMRI data were used to explore corresponding psychological and neural markers of insomnia development. Normal sleepers as a group reported a significant increase in insomnia symptoms after COVID-19 outbreak (F = 4.618, P = 0.0102, df = 2, 609.9). Depression was found to significantly contribute to worse insomnia (ß = 0.066, P = 0.024). Subsequent analysis found that functional connectivity between the precentral gyrus and middle/inferior temporal gyrus mediated the association between pre-COVID-19 depression and insomnia symptoms during COVID-19. Cluster analysis identified that postoutbreak insomnia symptoms followed 3 courses (lessened, slightly worsened, and developed into mild insomnia), and pre-COVID-19 depression symptoms and functional connectivities predicted these courses. Timely identification and treatment of at-risk individuals may help avoid the development of insomnia in the face of future health-care emergencies, such as those arising from COVID-19 variants.

Multivariate resting-state functional connectomes predict and characterize obesity phenotypes.

The univariate obesity-brain associations have been extensively explored, while little is known about the multivariate associations between obesity and resting-state functional connectivity. We therefore utilized machine learning and resting-state functional connectivity to develop and validate predictive models of 4 obesity phenotypes (i.e. body fat percentage, body mass index, waist circumference, and waist-height ratio) in 3 large neuroimaging datasets (n = 2,992). Preliminary evidence suggested that the resting-state functional connectomes effectively predicted obesity/weight status defined by each obesity phenotype with good generalizability to longitudinal and independent datasets. However, the differences between resting-state functional connectivity patterns characterizing different obesity phenotypes indicated that the obesity-brain associations varied according to the type of measure of obesity. The shared structure among resting-state functional connectivity patterns revealed reproducible neuroimaging biomarkers of obesity, primarily comprising the connectomes within the visual cortex and between the visual cortex and inferior parietal lobule, visual cortex and orbital gyrus, and amygdala and orbital gyrus, which further suggested that the dysfunctions in the perception, attention and value encoding of visual information (e.g. visual food cues) and abnormalities in the reward circuit may act as crucial neurobiological bases of obesity. The recruitment of multiple obesity phenotypes is indispensable in future studies seeking reproducible obesity-brain associations.

Copper-Catalyzed Radical Allene C(sp2 )-H Cyanation.

While the hydrogen atom abstraction (HAA) from C(sp3 )-H bond has been well explored, the radical-mediated chemo- and regio-selective functionalization of allenic C(sp2 )-H bond via direct HAA from C(sp2 )-H bond of allene remains an unsolved challenge in synthetic chemistry. This is primarily due to inherent challenges with addition of radical intermediates to allenes, regioselectivity of HAA process, instability of allenyl radical toward propargyl radical et al. Herein, we report a copper catalyzed allenic C(sp2 )-H cyanation of an array of tri- and di-substituted allenes with exceptional site-selectivity, while mono-substituted allene was successfully cyanated, albeit with a low yield. In the developed strategy, steric N-fluoro-N-alkylsulfonamide, serving as precursor of hydrogen atom abstractor, plays a crucial role in achieving the desired regioselectivity and avoiding addition of N-centered radical to allene.

The unity and diversity of verbal and visuospatial creativity: Dynamic changes in hemispheric lateralisation.

The investigation of similarities and differences in the mechanisms of verbal and visuospatial creative thinking has long been a controversial topic. Prior studies found that visuospatial creativity was primarily supported by the right hemisphere, whereas verbal creativity relied on the interaction between both hemispheres. However, creative thinking also involves abundant dynamic features that may have been ignored in the previous static view. Recently, a new method has been developed that measures hemispheric laterality from a dynamic perspective, providing new insight into the exploration of creative thinking. In the present study, dynamic lateralisation index was calculated with resting-state fMRI data. We combined the dynamic lateralisation index with sparse canonical correlation analysis to examine similarities and differences in the mechanisms of verbal and visuospatial creativity. Our results showed that the laterality reversal of the default mode network, fronto-parietal network, cingulo-opercular network and visual network contributed significantly to both verbal and visuospatial creativity and consequently could be considered the common neural mechanisms shared by these creative modes. In addition, we found that verbal creativity relied more on the language network, while visuospatial creativity relied more on the somatomotor network, which can be considered a difference in their mechanism. Collectively, these findings indicated that verbal and visuospatial creativity may have similar mechanisms to support the basic creative thinking process and different mechanisms to adapt to the specific task conditions. These findings may have significant implications for our understanding of the neural mechanisms of different types of creative thinking.

Gene transcriptional expression of cortical thinning during childhood and adolescence.

The cognitive and behavioral development of children and adolescents is closely related to the maturation of brain morphology. Although the trajectory of brain development has been depicted in detail, the underlying biological mechanism of normal cortical morphological development in childhood and adolescence remains unclear. By combining the Allen Human Brain Atlas dataset with two single-site magnetic resonance imaging data including 427 and 733 subjects from China and the United States, respectively, we performed partial least squares regression and enrichment analysis to explore the relationship between the gene transcriptional expression and the development of cortical thickness in childhood and adolescence. We found that the spatial model of normal cortical thinning during childhood and adolescence is associated with genes expressed predominantly in astrocytes, microglia, excitatory and inhibitory neurons. Top cortical development-related genes are enriched for energy-related and DNA-related terms and are associated with psychological and cognitive disorders. Interestingly, there is a great deal of similarity between the findings derived from the two single-site datasets. This fills the gap between early cortical development and transcriptomes, which promotes an integrative understanding of the potential biological neural mechanisms.

Brain structural abnormalities in adult major depressive disorder revealed by voxel- and source-based morphometry: evidence from the REST-meta-MDD Consortium.

BACKGROUND: Neuroimaging studies on major depressive disorder (MDD) have identified an extensive range of brain structural abnormalities, but the exact neural mechanisms associated with MDD remain elusive. Most previous studies were performed with voxel- or surface-based morphometry which were univariate methods without considering spatial information across voxels/vertices. METHODS: Brain morphology was investigated using voxel-based morphometry (VBM) and source-based morphometry (SBM) in 1082 MDD patients and 990 healthy controls (HCs) from the REST-meta-MDD Consortium. We first examined group differences in regional grey matter (GM) volumes and structural covariance networks between patients and HCs. We then compared first-episode, drug-naïve (FEDN) patients, and recurrent patients. Additionally, we assessed the effects of symptom severity and illness duration on brain alterations. RESULTS: VBM showed decreased GM volume in various regions in MDD patients including the superior temporal cortex, anterior and middle cingulate cortex, inferior frontal cortex, and precuneus. SBM returned differences only in the prefrontal network. Comparisons between FEDN and recurrent MDD patients showed no significant differences by VBM, but SBM showed greater decreases in prefrontal, basal ganglia, visual, and cerebellar networks in the recurrent group. Moreover, depression severity was associated with volumes in the inferior frontal gyrus and precuneus, as well as the prefrontal network. CONCLUSIONS: Simultaneous application of VBM and SBM methods revealed brain alterations in MDD patients and specified differences between recurrent and FEDN patients, which tentatively provide an effective multivariate method to identify potential neurobiological markers for depression.

Connectome-based prediction of eating disorder-associated symptomatology.

BACKGROUND: Despite increasing knowledge on the neuroimaging patterns of eating disorder (ED) symptoms in non-clinical populations, studies using whole-brain machine learning to identify connectome-based neuromarkers of ED symptomatology are absent. This study examined the association of connectivity within and between large-scale functional networks with specific symptomatic behaviors and cognitions using connectome-based predictive modeling (CPM). METHODS: CPM with ten-fold cross-validation was carried out to probe functional networks that were predictive of ED-associated symptomatology, including body image concerns, binge eating, and compensatory behaviors, within the discovery sample of 660 participants. The predictive ability of the identified networks was validated using an independent sample of 821 participants. RESULTS: The connectivity predictive of body image concerns was identified within and between networks implicated in cognitive control (frontoparietal and medial frontal), reward sensitivity (subcortical), and visual perception (visual). Crucially, the set of connections in the positive network related to body image concerns identified in one sample was generalized to predict body image concerns in an independent sample, suggesting the replicability of this effect. CONCLUSIONS: These findings point to the feasibility of using the functional connectome to predict ED symptomatology in the general population and provide the first evidence that functional interplay among distributed networks predicts body shape/weight concerns.

Connectome gradient dysfunction in major depression and its association with gene expression profiles and treatment outcomes.

Patients with major depressive disorder (MDD) exhibit concurrent deficits in both sensory and higher-order cognitive processing. Connectome studies have suggested a principal primary-to-transmodal gradient in functional brain networks, supporting the spectrum from sensation to cognition. However, whether this gradient structure is disrupted in patients with MDD and how this disruption associates with gene expression profiles and treatment outcome remain unknown. Using a large cohort of resting-state fMRI data from 2227 participants (1148 MDD patients and 1079 healthy controls) recruited at nine sites, we investigated MDD-related alterations in the principal connectome gradient. We further used Neurosynth, postmortem gene expression, and an 8-week antidepressant treatment (20 MDD patients) data to assess the meta-analytic cognitive functions, transcriptional profiles, and treatment outcomes related to MDD gradient alterations, respectively. Relative to the controls, MDD patients exhibited global topographic alterations in the principal primary-to-transmodal gradient, including reduced explanation ratio, gradient range, and gradient variation (Cohen's d = 0.16-0.21), and focal alterations mainly in the primary and transmodal systems (d = 0.18-0.25). These gradient alterations were significantly correlated with meta-analytic terms involving sensory processing and higher-order cognition. The transcriptional profiles explained 53.9% variance of the altered gradient pattern, with the most correlated genes enriched in transsynaptic signaling and calcium ion binding. The baseline gradient maps of patients significantly predicted symptomatic improvement after treatment. These results highlight the connectome gradient dysfunction in MDD and its linkage with gene expression profiles and clinical management, providing insight into the neurobiological underpinnings and potential biomarkers for treatment evaluation in this disorder.

Visible-Light-Promoted Cyanoalkylation/Cyclization Cascade Reaction to Assemble Polyheterocycles in Continuous Flow.

This study describes a visible-light-induced cascade reaction for preparing cyanoalkyl-containing polyheterocycles initiated by the photoinduced radical cascade addition of N-arylacrylamide derivatives using cyclic oxime esters as radical sources followed by cyanoalkyl-mediated cyclization. This protocol features outstanding functional group compatibility, providing a variety of desired phenanthridine derivatives in moderate to good yields. Moreover, the application of a microflow technique enhanced these reactions compared with the equivalent batch reaction, significantly reducing reaction times to 10 min.

A Layered Aluminophosphate [C17H21N2]3[Al3(PO4)4]·5H2O with Fluorescent Property Derived from Carbazolyl-Modified Template.

Designing and innovating organic structure-directing agents is the key to synthesizing novel molecular sieve structures. Herein, we design a novel carbazolyl-modified template and further synthesize a two-dimensional layered aluminophosphate with [C17H21N2]3[Al3(PO4)4]·5H2O (denoted as ZHKU-2). ZHKU-2 is composed of AA-stacked [Al3P4O16]3- layers constructed from alternating AlO4 and PO3(=O) tetrahedrons to form a 4.6.8 network featured by capped six-ring secondary building units. Carbazolyl-templated ZHKU-2 exhibits strong purple fluorescence with a high quantum yield of 25.98%. This work expands aluminophosphate materials of the [Al3P4O16]3- family and provides a view for synthesizing new molecular sieves by exploring the organic luminescence structure-directing agents.

Amygdala-based functional connectivity mediates the relationship between thought control ability and trait anxiety.

Thought control ability (TCA) refers to the ability to exclude unwanted thoughts. There has been consistent evidence on the protective effect of TCA on anxiety, that higher TCA is associated with lower anxiety. However, the underlying neural mechanism remains unclear. In this study, with a large sample (N = 495), we investigated how seed-based resting-state functional connectivity (RSFC) mediates the relationship between TCA and anxiety. Our behaviour results replicated previous findings that TCA is negatively associated with trait anxiety after controlling for gender, age, and depression. More importantly, the RSFC results revealed that TCA is negatively associated with the left amygdala - left frontal pole (LA-LFP), left amygdala - left inferior temporal gyrus (LA-LITG), and left hippocampus - left inferior frontal gyrus (LH-LIFG) connectivity. In addition, a mediation analysis demonstrated that the LA-LFP and LA-LITG connectivity in particular mediated the influence of TCA on trait anxiety. Overall, our study extends previous research by revealing the neural bases underlying the protective effect of TCA on anxiety and pinpointing specific mediating RSFC pathways. Future studies could explore whether targeted TCA training (behavioural or neural) can help alleviate anxiety.

Linking functional connectome gradient to individual creativity.

INTRODUCTION: Human brain network is organized as a hierarchical organization, exhibiting various connectome gradients. The principal gradient is anchored by the modality-specific primary areas and the transmodal regions. Previous studies have suggested that the unimodal-transmodal gradient in the functional connectome may offer an overarching framework for high-order cognitions of human brain. However, there is still a lacking of direct evidence to associate these two. OBJECTIVES: Therefore, we aim to explore the association between creativity, a typical human high-order cognitive function, and unimodal-transmodal gradient, using two independent datasets of young adults. METHODS: For each individual, we identified the unimodal-transmodal gradient in functional connectome and calculated its global measures. Then we correlated the individual creativity score with measures of unimodal-transmodal gradient at global-brain, subsystem, and regional level. RESULTS: The results suggested that better creative performance was associated with greater distance between primary areas and transmodal regions in gradient axes, and less distance between ventral attention network and default mode network. Individual creativity was also found positively correlated with regional gradients in ventral attention network, and negatively correlated with gradients of regions in visual cortex. CONCLUSION: Together, these findings directly link the unimodal-transmodal gradient to individual creativity, providing empirical evidence for the cognitive implications of functional connectome gradient.

Predisposing Variations in Fear-Related Brain Networks Prospectively Predict Fearful Feelings during the 2019 Coronavirus (COVID-19) Pandemic.

The novel coronavirus (COVID-19) pandemic has led to a surge in mental distress and fear-related disorders, including posttraumatic stress disorder (PTSD). Fear-related disorders are characterized by dysregulations in fear and the associated neural pathways. In the present study, we examined whether individual variations in the fear neural connectome can predict fear-related symptoms during the COVID-19 pandemic. Using machine learning algorithms and back-propagation artificial neural network (BP-ANN) deep learning algorithms, we demonstrated that the intrinsic neural connectome before the COVID-19 pandemic could predict who would develop high fear-related symptoms at the peak of the COVID-19 pandemic in China (Accuracy rate = 75.00%, Sensitivity rate = 65.83%, Specificity rate = 84.17%). More importantly, prediction models could accurately predict the level of fear-related symptoms during the COVID-19 pandemic by using the prepandemic connectome state, in which the functional connectivity of lvmPFC (left ventromedial prefrontal cortex)-rdlPFC (right dorsolateral), rdACC (right dorsal anterior cingulate cortex)-left insula, lAMY (left amygdala)-lHip (left hippocampus) and lAMY-lsgACC (left subgenual cingulate cortex) was contributed to the robust prediction. The current study capitalized on prepandemic data of the neural connectome of fear to predict participants who would develop high fear-related symptoms in COVID-19 pandemic, suggesting that individual variations in the intrinsic organization of the fear circuits represent a neurofunctional marker that renders subjects vulnerable to experience high levels of fear during the COVID-19 pandemic.