The Brain's Topographical Organization Shapes Dynamic Interaction Patterns That Support Flexible Behavior Based on Rules and Long-Term Knowledge.

Adaptive behavior relies both on specific rules that vary across situations and stable long-term knowledge gained from experience. The frontoparietal control network (FPCN) is implicated in the brain's ability to balance these different influences on action. Here, we investigate how the topographical organization of the cortex supports behavioral flexibility within the FPCN. Functional properties of this network might reflect its juxtaposition between the dorsal attention network (DAN) and the default mode network (DMN), two large-scale systems implicated in top-down attention and memory-guided cognition, respectively. Our study tests whether subnetworks of FPCN are topographically proximal to the DAN and the DMN, respectively, and how these topographical differences relate to functional differences: the proximity of each subnetwork is anticipated to play a pivotal role in generating distinct cognitive modes relevant to working memory and long-term memory. We show that FPCN subsystems share multiple anatomical and functional similarities with their neighboring systems (DAN and DMN) and that this topographical architecture supports distinct interaction patterns that give rise to different patterns of functional behavior. The FPCN acts as a unified system when long-term knowledge supports behavior but becomes segregated into discrete subsystems with different patterns of interaction when long-term memory is less relevant. In this way, our study suggests that the topographical organization of the FPCN and the connections it forms with distant regions of cortex are important influences on how this system supports flexible behavior.

Brain structural and functional signatures of multi-generational family history of suicidal behaviors in preadolescent children.

Parent-child transmission of suicidal behaviors has been extensively studied, but the investigation of a three-generation family suicide risk paradigm remains limited. In this study, we aimed to explore the behavioral and brain signatures of multi-generational family history of suicidal behaviors (FHoS) in preadolescents, utilizing a longitudinal design and the dataset from Adolescent Brain and Cognitive DevelopmentSM Study (ABCD Study®), which comprised 4 years of data and includes a total of 9,653 preadolescents. Our findings revealed that multi-generational FHoS was significantly associated with an increased risk of problematic behaviors and suicidal behaviors (suicide ideation and suicide attempt) in offspring. Interestingly, the problematic behaviors were further identified as a mediator in the multi-generational transmission of suicidal behaviors. Additionally, we observed alterations in brain structure within superior temporal gyrus (STG), precentral/postcentral cortex, posterior parietal cortex (PPC), cingulate cortex (CC), and planum temporale (PT), as well as disrupted functional connectivity of default mode network (DMN), ventral attention network (VAN), dorsal attention network (DAN), fronto-parietal network (FPN), and cingulo-opercular network (CON) among preadolescents with FHoS. These results provide compelling longitudinal evidence at the population level, highlighting the associations between multi-generational FHoS and maladaptive behavioral and neurodevelopmental outcomes in offspring. These findings underscore the need for early preventive measures aimed at mitigating the familial transmission of suicide risk and reducing the global burden of deaths among children and adolescents.

Sex differences in the functional topography of association networks in youth.

Prior work has shown that there is substantial interindividual variation in the spatial distribution of functional networks across the cerebral cortex, or functional topography. However, it remains unknown whether there are sex differences in the topography of individualized networks in youth. Here, we leveraged an advanced machine learning method (sparsity-regularized non-negative matrix factorization) to define individualized functional networks in 693 youth (ages 8 to 23 y) who underwent functional MRI as part of the Philadelphia Neurodevelopmental Cohort. Multivariate pattern analysis using support vector machines classified participant sex based on functional topography with 82.9% accuracy (P < 0.0001). Brain regions most effective in classifying participant sex belonged to association networks, including the ventral attention, default mode, and frontoparietal networks. Mass univariate analyses using generalized additive models with penalized splines provided convergent results. Furthermore, transcriptomic data from the Allen Human Brain Atlas revealed that sex differences in multivariate patterns of functional topography were spatially correlated with the expression of genes on the X chromosome. These results highlight the role of sex as a biological variable in shaping functional topography.

Structural connectome quantifies tumour invasion and predicts survival in glioblastoma patients.

Glioblastoma is characterized by diffuse infiltration into the surrounding tissue along white matter tracts. Identifying the invisible tumour invasion beyond focal lesion promises more effective treatment, which remains a significant challenge. It is increasingly accepted that glioblastoma could widely affect brain structure and function, and further lead to reorganization of neural connectivity. Quantifying neural connectivity in glioblastoma may provide a valuable tool for identifying tumour invasion. Here we propose an approach to systematically identify tumour invasion by quantifying the structural connectome in glioblastoma patients. We first recruit two independent prospective glioblastoma cohorts: the discovery cohort with 117 patients and validation cohort with 42 patients. Next, we use diffusion MRI of healthy subjects to construct tractography templates indicating white matter connection pathways between brain regions. Next, we construct fractional anisotropy skeletons from diffusion MRI using an improved voxel projection approach based on the tract-based spatial statistics, where the strengths of white matter connection and brain regions are estimated. To quantify the disrupted connectome, we calculate the deviation of the connectome strengths of patients from that of the age-matched healthy controls. We then categorize the disruption into regional disruptions on the basis of the relative location of connectome to focal lesions. We also characterize the topological properties of the patient connectome based on the graph theory. Finally, we investigate the clinical, cognitive and prognostic significance of connectome metrics using Pearson correlation test, mediation test and survival models. Our results show that the connectome disruptions in glioblastoma patients are widespread in the normal-appearing brain beyond focal lesions, associated with lower preoperative performance (P < 0.001), impaired cognitive function (P < 0.001) and worse survival (overall survival: hazard ratio = 1.46, P = 0.049; progression-free survival: hazard ratio = 1.49, P = 0.019). Additionally, these distant disruptions mediate the effect on topological alterations of the connectome (mediation effect: clustering coefficient -0.017, P < 0.001, characteristic path length 0.17, P = 0.008). Further, the preserved connectome in the normal-appearing brain demonstrates evidence of connectivity reorganization, where the increased neural connectivity is associated with better overall survival (log-rank P = 0.005). In conclusion, our connectome approach could reveal and quantify the glioblastoma invasion distant from the focal lesion and invisible on the conventional MRI. The structural disruptions in the normal-appearing brain were associated with the topological alteration of the brain and could indicate treatment target. Our approach promises to aid more accurate patient stratification and more precise treatment planning.

Physical distance to sensory-motor landmarks predicts language function.

Auditory language comprehension recruits cortical regions that are both close to sensory-motor landmarks (supporting auditory and motor features) and far from these landmarks (supporting word meaning). We investigated whether the responsiveness of these regions in task-based functional MRI is related to individual differences in their physical distance to primary sensorimotor landmarks. Parcels in the auditory network, that were equally responsive across story and math tasks, showed stronger activation in individuals who had less distance between these parcels and transverse temporal sulcus, in line with the predictions of the "tethering hypothesis," which suggests that greater proximity to input regions might increase the fidelity of sensory processing. Conversely, language and default mode parcels, which were more active for the story task, showed positive correlations between individual differences in activation and sensory-motor distance from primary sensory-motor landmarks, consistent with the view that physical separation from sensory-motor inputs supports aspects of cognition that draw on semantic memory. These results demonstrate that distance from sensorimotor regions provides an organizing principle of functional differentiation within the cortex. The relationship between activation and geodesic distance to sensory-motor landmarks is in opposite directions for cortical regions that are proximal to the heteromodal (DMN and language network) and unimodal ends of the principal gradient of intrinsic connectivity.

Global diversity in individualized cortical network topography.

Individualized cortical network topography (ICNT) varies between people and exhibits great variability in the association networks in the human brain. However, these findings were mainly discovered in Western populations. It remains unclear whether and how ICNT is shaped by the non-Western populations. Here, we leveraged a multisession hierarchical Bayesian model to define individualized functional networks in White American and Han Chinese populations with data from both US and Chinese Human Connectome Projects. We found that both the size and spatial topography of individualized functional networks differed between White American and Han Chinese groups, especially in the heteromodal association cortex (including the ventral attention, control, language, dorsal attention, and default mode networks). Employing a support vector machine, we then demonstrated that ethnicity-related ICNT diversity can be used to identify an individual's ethnicity with high accuracy (74%, pperm < 0.0001), with heteromodal networks contributing most to the classification. This finding was further validated through mass-univariate analyses with generalized additive models. Moreover, we reveal that the spatial heterogeneity of ethnic diversity in ICNT correlated with fundamental properties of cortical organization, including evolutionary cortical expansion, brain myelination, and cerebral blood flow. Altogether, this case study highlights a need for more globally diverse and publicly available neuroimaging datasets.

Associations of bullying perpetration and peer victimization subtypes with preadolescent's suicidality, non-suicidal self-injury, neurocognition, and brain development.

BACKGROUND: Although both peer victimization and bullying perpetration negatively impact preadolescents' development, the underlying neurobiological mechanism of this adverse relationship remains unclear. Besides, the specific psycho-cognitive patterns of different bullying subtypes also need further exploration, warranting large-scale studies on both general bullying and specific bullying subtypes. METHODS: We adopted a retrospective methodology by utilizing the data from the Adolescent Brain and Cognitive DevelopmentSM Study (ABCD Study®) cohort collected between July 2018 and January 2021. Participants were preadolescents aged from 10 to 13 years. The main purpose of our study is to examine the associations of general and specific peer victimization/bullying perpetration with preadolescents' (1) suicidality and non-suicidal self-injury; (2) executive function and memory, including attention inhibition, processing speed, emotion working memory, and episodic memory; (3) brain structure abnormalities; and (4) brain network disturbances. Age, sex, race/ethnicity, body mass index (BMI), socioeconomic status (SES), and data acquisition site were included as covariates. RESULTS: A total of 5819 participants aged from 10 to 13 years were included in this study. Higher risks of suicide ideation, suicide attempt, and non-suicidal self-injury were found to be associated with both bullying perpetration/peer victimization and their subtypes (i.e., overt, relational, and reputational). Meanwhile, poor episodic memory was shown to be associated with general victimization. As for perpetration, across all four tasks, significant positive associations of relational perpetration with executive function and episodic memory consistently manifested, yet opposite patterns were shown in overt perpetration. Notably, distinct psycho-cognitive patterns were shown among different subtypes. Additionally, victimization was associated with structural brain abnormalities in the bilateral paracentral and posterior cingulate cortex. Furthermore, victimization was associated with brain network disturbances between default mode network and dorsal attention network, between default mode network and fronto-parietal network, and ventral attention network related connectivities, including default mode network, dorsal attention network, cingulo-opercular network, cingulo-parietal network, and sensorimotor hand network. Perpetration was also associated with brain network disturbances between the attention network and the sensorimotor hand network. CONCLUSIONS: Our findings offered new evidence for the literature landscape by emphasizing the associations of bullying experiences with preadolescents' clinical characteristics and cognitive functions, while distinctive psycho-cognitive patterns were shown among different subtypes. Additionally, there is evidence that these associations are related to neurocognitive brain networks involved in attention control and episodic retrieval. Given our findings, future interventions targeting ameliorating the deleterious effect of bullying experiences on preadolescents should consider their subtypes and utilize an ecosystemic approach involving all responsible parties.

Development of structure-function coupling in human brain networks during youth.

The protracted development of structural and functional brain connectivity within distributed association networks coincides with improvements in higher-order cognitive processes such as executive function. However, it remains unclear how white-matter architecture develops during youth to directly support coordinated neural activity. Here, we characterize the development of structure-function coupling using diffusion-weighted imaging and n-back functional MRI data in a sample of 727 individuals (ages 8 to 23 y). We found that spatial variability in structure-function coupling aligned with cortical hierarchies of functional specialization and evolutionary expansion. Furthermore, hierarchy-dependent age effects on structure-function coupling localized to transmodal cortex in both cross-sectional data and a subset of participants with longitudinal data (n = 294). Moreover, structure-function coupling in rostrolateral prefrontal cortex was associated with executive performance and partially mediated age-related improvements in executive function. Together, these findings delineate a critical dimension of adolescent brain development, whereby the coupling between structural and functional connectivity remodels to support functional specialization and cognition.

Dynamic integration and segregation of amygdala subregional functional circuits linking to physiological arousal.

The dynamical organization of brain networks is essential to support human cognition and emotion for rapid adaption to ever-changing environment. As the core nodes of emotion-related brain circuitry, the basolateral amygdala (BLA) and centromedial amygdala (CMA) as two major amygdalar nuclei, are recognized to play distinct roles in affective functions and internal states, via their unique connections with cortical and subcortical structures in rodents. However, little is known how the dynamical organization of emotion-related brain circuitry reflects internal autonomic responses in humans. Using resting-state functional magnetic resonance imaging (fMRI) with K-means clustering approach in a total of 79 young healthy individuals (cohort 1: 42; cohort 2: 37), we identified two distinct states of BLA- and CMA-based intrinsic connectivity patterns, with one state (integration) showing generally stronger BLA- and CMA-based intrinsic connectivity with multiple brain networks, while the other (segregation) exhibiting weaker yet dissociable connectivity patterns. In an independent cohort 2 of fMRI data with concurrent recording of skin conductance, we replicated two similar dynamic states and further found higher skin conductance level in the integration than segregation state. Moreover, machine learning-based Elastic-net regression analyses revealed that time-varying BLA and CMA intrinsic connectivity with distinct network configurations yield higher predictive values for spontaneous fluctuations of skin conductance level in the integration than segregation state. Our findings highlight dynamic functional organization of emotion-related amygdala nuclei circuits and networks and its links to spontaneous autonomic arousal in humans.

Prediction of trust propensity from intrinsic brain morphology and functional connectome.

Trust forms the basis of virtually all interpersonal relationships. Although significant individual differences characterize trust, the driving neuropsychological signatures behind its heterogeneity remain obscure. Here, we applied a prediction framework in two independent samples of healthy participants to examine the relationship between trust propensity and multimodal brain measures. Our multivariate prediction analyses revealed that trust propensity was predicted by gray matter volume and node strength across multiple regions. The gray matter volume of identified regions further enabled the classification of individuals from an independent sample with the propensity to trust or distrust. Our modular and functional decoding analyses showed that the contributing regions were part of three large-scale networks implicated in calculus-based trust strategy, cost-benefit calculation, and trustworthiness inference. These findings do not only deepen our neuropsychological understanding of individual differences in trust propensity, but also provide potential biomarkers in predicting trust impairment in neuropsychiatric disorders.

Psychopathological symptom network structure in transgender and gender queer youth reporting parental psychological abuse: a network analysis.

BACKGROUND: This is the first study to investigate the effect of parental psychological abuse on potential psychopathological symptoms in gender minority youth subgroups, including transgender women, transgender men, and gender queer individuals. METHODS: Data was analysed from the Chinese National Transgender Survey in 2017; the survey was distributed through community-based organizations to transgender adolescents and adults residing in China, with representation from all 32 provinces and autonomous regions. A total of 1293 youth that self-identified as transgender or gender queer completed the study. Measures covered psychopathological symptoms including depression, anxiety, risk of suicideand self-harm. Parental psychological abuse was assessed in terms of neglect and avoidance, force to change, and verbal insults. Both the edges and centralities were computed via network analysis, and the network properties were then compared among the three gender minority subgroups. In addition, linear regression was adopted to test the predictive ability of node centrality for low self-esteem. RESULTS: Descriptive analysis revealed that among the three subgroups, transgender women had more severe psychopathological symptoms and reported the most psychological abuse. Network analysis revealed that the risk of suicide and self-harm was directly connected with one type of parental psychological abuse ("neglect and avoidance"). Node centrality was significantly associated with the predicting value of the nodes on low self-esteem (r2 = 0.25, 0.17, 0.31) among all three gender minority subgroups. CONCLUSIONS: The distinctive core psychopathological symptoms, within the networks of the gender minority subgroups, revealed specific symptoms across each group. The significant association between node centrality and low self-esteem indicated the extent of parental psychological abuse. Parental psychological abuse directed towards gender minority youth should be recognized as a form of family cold violence. It is recommended that schools and local communities should support early intervention to improve psychological well-being.

Characterizing the hyper- and hypometabolism in temporal lobe epilepsy using multivariate machine learning.

Mesial temporal lobe epilepsy (MTLE) is the most common type of focal epilepsy, presenting both structural and metabolic abnormalities in the ipsilateral mesial temporal lobe. While it has been demonstrated that the metabolic abnormalities in MTLE actually extend beyond the epileptogenic zone, how such multidimensional information is associated with the diagnosis of MTLE remains to be tested. Here, we explore the whole-brain metabolic patterns in 23 patients with MTLE and 24 healthy controls using [18 F]fluorodeoxyglucose PET imaging. Based on a multivariate machine learning approach, we demonstrate that the brain metabolic patterns can discriminate patients with MTLE from controls with a superior accuracy (>95%). Importantly, voxels showing the most extreme contributing weights to the classification (i.e., the most important regional predictors) distribute across both hemispheres, involving both ipsilateral negative weights over the anterior part of lateral and medial temporal lobe, posterior insula, and lateral orbital frontal gyrus, and contralateral positive weights over the anterior frontal lobe, temporal lobe, and lingual gyrus. Through region-of-interest analyses, we verify that in patients with MTLE, the negatively weighted regions are hypometabolic, and the positively weighted regions are hypermetabolic, compared to controls. Interestingly, despite that both hypo- and hypermetabolism have mutually contributed to our model, they may reflect different pathological and/or compensative responses. For instance, patients with earlier age at epilepsy onset present greater hypometabolism in the ipsilateral inferior temporal gyrus, while we find no evidence of such association with hypermetabolism. In summary, quantitative models utilizing multidimensional brain metabolic information may provide additional assistance to presurgical workups in TLE.

Amygdala-prefrontal connectivity modulates loss aversion bias in anxious individuals.

Anxious individuals tend to make pessimistic judgments in decision making under uncertainty. While this phenomenon is commonly attributed to risk aversion, loss aversion is a critical but often overlooked factor. In this study, we simultaneously examined risk aversion and loss aversion during decision making in high and low trait anxious individuals in a variable gain/loss gambling task during functional magnetic resonance imaging. Although high relative to low anxious individuals showed significant increased risk aversive behavior reflected by decreased overall gamble decisions, there was no group difference in subjective aversion to risk. Instead, loss aversion rather than risk aversion dominantly contributed to predict behavioral decisions, which was associated with attenuated functional connectivity between the amygdala-based emotional system and the prefrontal control regions. Our findings suggest a dominant role of loss aversion in maladaptive risk assessment of anxious individuals, underpinned by disorganization of emotion-related and cognitive-control-related brain networks.

Multi-scale network regression for brain-phenotype associations.

Brain networks are increasingly characterized at different scales, including summary statistics, community connectivity, and individual edges. While research relating brain networks to behavioral measurements has yielded many insights into brain-phenotype relationships, common analytical approaches only consider network information at a single scale. Here, we designed, implemented, and deployed Multi-Scale Network Regression (MSNR), a penalized multivariate approach for modeling brain networks that explicitly respects both edge- and community-level information by assuming a low rank and sparse structure, both encouraging less complex and more interpretable modeling. Capitalizing on a large neuroimaging cohort (n = 1, 051), we demonstrate that MSNR recapitulates interpretable and statistically significant connectivity patterns associated with brain development, sex differences, and motion-related artifacts. Compared to single-scale methods, MSNR achieves a balance between prediction performance and model complexity, with improved interpretability. Together, by jointly exploiting both edge- and community-level information, MSNR has the potential to yield novel insights into brain-behavior relationships.

Brain hemispheric involvement in visuospatial and verbal divergent thinking.

Hemispheric lateralization for creative thinking remains a controversial topic. Early behavioral and neuroimaging research supported right hemisphere dominance in creative thinking, but more recent evidence suggests the left hemisphere plays an equally important role. In addition, the extent to which hemispheric lateralization in specific brain regions relates to individual creative ability, and whether hemispheric dominance relates to distinct task performance, remain poorly understood. Here, using multivariate predictive modeling of resting-state functional MRI data in a large sample of adults (N = 502), we estimated hemispheric segregation and integration for each brain region and investigated these lateralization indices with respect to individual differences in visuospatial and verbal divergent thinking. Our analyses revealed that individual visuospatial divergent thinking performance could be predicted by right-hemispheric segregation within the visual network, sensorimotor network, and some regions within the default mode network. High visuospatial divergent thinking was related to stronger functional connectivity between the visual network, fronto-parietal network, and default mode network within the right hemisphere. In contrast, high verbal divergent thinking performance could be predicted by inter-hemispheric balance within regions mainly involved in complex semantic processing (e.g., lateral temporal cortex and inferior frontal gyrus) and cognitive control processing (e.g., inferior frontal gyrus, middle frontal cortex, and superior parietal lobule). The current study suggests that two distinct forms of functional lateralization support individual differences in visuospatial and verbal divergent thinking. These findings have important implications for our understanding of hemispheric interaction mechanisms of creative thinking.

Network analysis reveals disrupted functional brain circuitry in drug-naive social anxiety disorder.

Social anxiety disorder (SAD) is a common and disabling condition characterized by excessive fear and avoidance of public scrutiny. Psychoradiology studies have suggested that the emotional and behavior deficits in SAD are associated with abnormalities in regional brain function and functional connectivity. However, little is known about whether intrinsic functional brain networks in patients with SAD are topologically disrupted. Here, we collected resting-state fMRI data from 33 drug-naive patients with SAD and 32 healthy controls (HC), constructed functional networks with 34 predefined regions based on previous meta-analytic research with task-based fMRI in SAD, and performed network-based statistic and graph-theory analyses. The network-based statistic analysis revealed a single connected abnormal circuitry including the frontolimbic circuit (termed the "fear circuit", including the dorsolateral prefrontal cortex, ventral medial prefrontal cortex and insula) and posterior cingulate/occipital areas supporting perceptual processing. In this single altered network, patients with SAD had higher functional connectivity than HC. At the global level, graph-theory analysis revealed that the patients exhibited a lower normalized characteristic path length than HC, which suggests a disorder-related shift of network topology toward randomized configurations. SAD-related deficits in nodal degree, efficiency and participation coefficient were detected in the parahippocampal gyrus, posterior cingulate cortex, dorsolateral prefrontal cortex, insula and the calcarine sulcus. Aspects of abnormal connectivity were associated with anxiety symptoms. These findings highlight the aberrant topological organization of functional brain network organization in SAD, which provides insights into the neural mechanisms underlying excessive fear and avoidance of social interactions in patients with debilitating social anxiety.

Individualized prediction of dispositional worry using white matter connectivity.

BACKGROUND: Excessive worry is a defining feature of generalized anxiety disorder and is present in a wide range of other psychiatric conditions. Therefore, individualized predictions of worry propensity could be highly relevant in clinical practice, with respect to the assessment of worry symptom severity at the individual level. METHODS: We applied a multivariate machine learning approach to predict dispositional worry based on microstructural integrity of white matter (WM) tracts. RESULTS: We demonstrated that the machine learning model was able to decode individual dispositional worry scores from microstructural properties in widely distributed WM tracts (mean absolute error = 10.46, p < 0.001; root mean squared error = 12.82, p < 0.001; prediction R2 = 0.17, p < 0.001). WM tracts that contributed to worry prediction included the posterior limb of internal capsule, anterior corona radiate, and cerebral peduncle, as well as the corticolimbic pathways (e.g. uncinate fasciculus, cingulum, and fornix) already known to be critical for emotion processing and regulation. CONCLUSIONS: The current work thus elucidates potential neuromarkers for clinical assessment of worry symptoms across a wide range of psychiatric disorders. In addition, the identification of widely distributed pathways underlying worry propensity serves to better improve the understanding of the neurobiological mechanisms associated with worry.

Individualized Prediction of Reading Comprehension Ability Using Gray Matter Volume.

Reading comprehension is a crucial reading skill for learning and putatively contains 2 key components: reading decoding and linguistic comprehension. Current understanding of the neural mechanism underlying these reading comprehension components is lacking, and whether and how neuroanatomical features can be used to predict these 2 skills remain largely unexplored. In the present study, we analyzed a large sample from the Human Connectome Project (HCP) dataset and successfully built multivariate predictive models for these 2 skills using whole-brain gray matter volume features. The results showed that these models effectively captured individual differences in these 2 skills and were able to significantly predict these components of reading comprehension for unseen individuals. The strict cross-validation using the HCP cohort and another independent cohort of children demonstrated the model generalizability. The identified gray matter regions contributing to the skill prediction consisted of a wide range of regions covering the putative reading, cerebellum, and subcortical systems. Interestingly, there were gender differences in the predictive models, with the female-specific model overestimating the males' abilities. Moreover, the identified contributing gray matter regions for the female-specific and male-specific models exhibited considerable differences, supporting a gender-dependent neuroanatomical substrate for reading comprehension.

Support vector machine-based multivariate pattern classification of methamphetamine dependence using arterial spin labeling.

Arterial spin labeling (ASL) magnetic resonance imaging has been widely applied to identify cerebral blood flow (CBF) abnormalities in a number of brain disorders. To evaluate its significance in detecting methamphetamine (MA) dependence, this study used a multivariate pattern classification algorithm, ie, a support vector machine (SVM), to construct classifiers for discriminating MA-dependent subjects from normal controls. Forty-five MA-dependent subjects, 45 normal controls, and 36 heroin-dependent subjects were enrolled. Classifiers trained with ASL-CBF data from the left or right cerebrum showed significant hemispheric asymmetry in their cross-validated prediction performance (P < 0.001 for accuracy, sensitivity, specificity, kappa, and area under the curve [AUC] of the receiver operating characteristics [ROC] curve). A classifier trained with ASL-CBF data from all cerebral regions (bilateral hemispheres and corpus callosum) was able to differentiate MA-dependent subjects from normal controls with a cross-validated prediction accuracy, sensitivity, specificity, kappa, and AUC of 89%, 94%, 84%, 0.78, and 0.95, respectively. The discrimination map extracted from this classifier covered multiple brain circuits that either constitute a network related to drug abuse and addiction or could be impaired in MA-dependence. The cerebral regions contribute most to classification include occipital lobe, insular cortex, postcentral gyrus, corpus callosum, and inferior frontal cortex. This classifier was also specific to MA-dependence rather than substance use disorders in general (ie, 55.56% accuracy for heroin dependence). These results support the future utilization of ASL with an SVM-based classifier for the diagnosis of MA-dependence and could help improve the understanding of MA-related neuropathology.

The effect of machine learning regression algorithms and sample size on individualized behavioral prediction with functional connectivity features.

Individualized behavioral/cognitive prediction using machine learning (ML) regression approaches is becoming increasingly applied. The specific ML regression algorithm and sample size are two key factors that non-trivially influence prediction accuracies. However, the effects of the ML regression algorithm and sample size on individualized behavioral/cognitive prediction performance have not been comprehensively assessed. To address this issue, the present study included six commonly used ML regression algorithms: ordinary least squares (OLS) regression, least absolute shrinkage and selection operator (LASSO) regression, ridge regression, elastic-net regression, linear support vector regression (LSVR), and relevance vector regression (RVR), to perform specific behavioral/cognitive predictions based on different sample sizes. Specifically, the publicly available resting-state functional MRI (rs-fMRI) dataset from the Human Connectome Project (HCP) was used, and whole-brain resting-state functional connectivity (rsFC) or rsFC strength (rsFCS) were extracted as prediction features. Twenty-five sample sizes (ranged from 20 to 700) were studied by sub-sampling from the entire HCP cohort. The analyses showed that rsFC-based LASSO regression performed remarkably worse than the other algorithms, and rsFCS-based OLS regression performed markedly worse than the other algorithms. Regardless of the algorithm and feature type, both the prediction accuracy and its stability exponentially increased with increasing sample size. The specific patterns of the observed algorithm and sample size effects were well replicated in the prediction using re-testing fMRI data, data processed by different imaging preprocessing schemes, and different behavioral/cognitive scores, thus indicating excellent robustness/generalization of the effects. The current findings provide critical insight into how the selected ML regression algorithm and sample size influence individualized predictions of behavior/cognition and offer important guidance for choosing the ML regression algorithm or sample size in relevant investigations.