Task-induced brain state manipulation improves prediction of individual traits

Beyond Increasing Sample Sizes: Optimizing Effect Sizes in Neuroimaging Research on Individual Differences

Linking neurobiology to relatively stable individual differences in cognition, emotion, motivation, and behavior can require large sample sizes to yield replicable results. Given the nature of between-person research, sample sizes at least in the hundreds are likely to be necessary in most neuroimaging studies of individual differences, regardless of whether they are investigating the whole brain or more focal hypotheses. However, the appropriate sample size depends on the expected effect size. Therefore, we propose four strategies to increase effect sizes in neuroimaging research, which may help to enable the detection of replicable between-person effects in samples in the hundreds rather than the thousands: (1) theoretical matching between neuroimaging tasks and behavioral constructs of interest; (2) increasing the reliability of both neural and psychological measurement; (3) individualization of measures for each participant; and (4) using multivariate approaches with cross-validation instead of univariate approaches. We discuss challenges associated with these methods and highlight strategies for improvements that will help the field to move toward a more robust and accessible neuroscience of individual differences.

Clinical response to neurofeedback in major depression relates to subtypes of whole-brain activation patterns during training

Major Depressive Disorder (MDD) poses a significant public health challenge due to its high prevalence and the substantial burden it places on individuals and healthcare systems. Real-time functional magnetic resonance imaging neurofeedback (rtfMRI-NF) shows promise as a treatment for this disorder, although its mechanisms of action remain unclear. This study investigated whole-brain response patterns during rtfMRI-NF training to explain interindividual variability in clinical efficacy in MDD. We analyzed data from 95 participants (67 active, 28 control) with MDD from previous rtfMRI-NF studies designed to increase left amygdala activation through positive autobiographical memory recall. Significant symptom reduction was observed in the active group (t = -4.404, d = -0.704, p < 0.001) but not in the control group (t = -1.609, d = -0.430, p = 0.111). However, left amygdala activation did not account for the variability in clinical efficacy. To elucidate the brain training process underlying the clinical effect, we examined whole-brain activation patterns during two critical phases of the neurofeedback procedure: activation during the self-regulation period, and transient responses to feedback signal presentations. Using a systematic process involving feature selection, manifold extraction, and clustering with cross-validation, we identified two subtypes of regulation activation and three subtypes of brain responses to feedback signals. These subtypes were significantly associated with the clinical effect (regulation subtype: F = 8.735, p = 0.005; feedback response subtype: F = 5.326, p = 0.008; subtypes' interaction: F = 3.471, p = 0.039). Subtypes associated with significant symptom reduction were characterized by selective increases in control regions, including lateral prefrontal areas, and decreases in regions associated with self-referential thinking, such as default mode areas. These findings suggest that large-scale brain activity during training is more critical for clinical efficacy than the level of activation in the neurofeedback target region itself. Tailoring neurofeedback training to incorporate these patterns could significantly enhance its therapeutic efficacy.

Event cache: An independent component in working memory

Working memory (WM) has been a major focus of cognitive science and neuroscience for the past 50 years. While most WM research has centered on the mechanisms of objects, there has been a lack of investigation into the cognitive and neural mechanisms of events, which are the building blocks of our experience. Using confirmatory factor analysis, psychophysical experiments, and resting-state and task functional magnetic resonance imaging methods, our study demonstrated that events have an independent storage space within WM, named as event cache, with distinct neural correlates compared to object storage in WM. We found the cerebellar network to be the most essential network for event cache, with the left cerebellum Crus I being particularly involved in encoding and maintaining events. Our findings shed critical light on the neuropsychological mechanism of WM by revealing event cache as an independent component of WM and encourage the reconsideration of theoretical models for WM.

Direct Comparison of EEG Resting State and Task Functional Connectivity Patterns for Predicting Working Memory Performance Using Connectome-Based Predictive Modeling

Background: The integration of machine learning with advanced neuroimaging has emerged as a powerful approach for uncovering the relationship between neuronal activity patterns and behavioral traits. While resting-state neuroimaging has significantly contributed to understanding the neural basis of cognition, recent fMRI studies suggest that task-based paradigms may offer superior predictive power for cognitive outcomes. However, this hypothesis has never been tested using electroencephalography (EEG) data. Methods: We conducted the first experimental comparison of predictive models built on high-density EEG data recorded during both resting-state and an auditory working memory task. Multiple data processing pipelines were employed to ensure robustness and reliability. Model performance was evaluated by computing the Pearson correlation coefficient between predicted and observed behavioral scores, supplemented by mean absolute error and root mean square error metrics for each model configuration. Results: Consistent with prior fMRI findings, task-based EEG data yielded slightly better modeling performance than resting-state data. Both conditions demonstrated high predictive accuracy, with peak correlations between observed and predicted values reaching r = 0.5. Alpha and beta band functional connectivity were the strongest predictors of working memory performance, followed by theta and gamma bands. Additionally, the choice of parcellation atlas and connectivity method significantly influenced results, highlighting the importance of methodological considerations. Conclusion: Our findings support the advantage of task-based EEG over resting-state data in predicting cognitive performance, aligning with. The study underscores the critical role of frequency-specific functional connectivity and methodological choices in model performance. These insights should guide future experimental designs in cognitive neuroscience. Impact Statement This study provides the first direct comparison of EEG-based functional connectivity during rest and task conditions for predicting working memory performance using connectome-based predictive modeling (CPM). It demonstrates that task-based EEG data slightly outperforms resting-state data, with alpha and beta bands being the most predictive. The findings highlight the critical influence of methodological choices, such as parcellation atlases and connectivity metrics, on model outcomes. By bridging gaps in EEG research and validating CPM's applicability, this work advances the optimization of neuroimaging protocols for cognitive assessment, offering insights for future studies in cognitive neuroscience.

Social Cognition and Functional Connectivity in Early and Chronic Schizophrenia

BACKGROUND

Individuals with schizophrenia (SZ) experience impairments in social cognition that contribute to poor functional outcomes. However, mechanisms of social cognitive dysfunction in SZ remain poorly understood, which impedes the design of novel interventions to improve outcomes. In this preregistered project, we examined the representation of social cognition in the brain's functional architecture in early and chronic SZ.

METHODS

The study contains 2 parts: a confirmatory and an exploratory portion. In the confirmatory portion, we identified resting-state connectivity disruptions evident in early and chronic SZ. We performed a connectivity analysis using regions associated with social cognitive dysfunction in early and chronic SZ to test whether aberrant connectivity observed in chronic SZ (n = 47 chronic SZ and n = 52 healthy control participants) was also present in early SZ (n = 71 early SZ and n = 47 healthy control participants). In the exploratory portion, we assessed the out-of-sample generalizability and precision of predictive models of social cognition. We used machine learning to predict social cognition and established generalizability with out-of-sample testing and confound control.

RESULTS

Results revealed decreases between the left inferior frontal gyrus and the intraparietal sulcus in early and chronic SZ, which were significantly associated with social and general cognition and global functioning in chronic SZ and with general cognition and global functioning in early SZ. Predictive modeling revealed the importance of out-of-sample evaluation and confound control.

CONCLUSIONS

This work provides insights into the functional architecture in early and chronic SZ and suggests that inferior frontal gyrus-intraparietal sulcus connectivity could be a prognostic biomarker of social impairments and a target for future interventions (e.g., neuromodulation) focused on improved social functioning.

Spinal Cord Lower Urinary Tract Control in Humans

BACKGROUND AND OBJECTIVE

Although there have been significant advancements in functional magnetic resonance imaging (fMRI) studies that have enhanced our understanding of brain control over bladder function in humans, a notable gap still exists in exploring spinal cord involvement in real-time. The objective of this study was to develop and validate an fMRI protocol to assess innate spinal cord activity in humans within regions associated with bladder function.

METHODS

Twenty healthy adult participants 9 men, 11 women underwent functional magnetic resonance imaging (fMRI) of the spinal cord during implementation of a natural bladder filling protocol and simulated bulbocavernosus reflex (sBCR). Anatomical images were obtained, followed by resting-state and task-based fMRI assessments during both full and empty bladder states. Functional spinal neuroimaging data were analyzed using a custom pipeline comprised of Spinal Cord Toolbox, FSL, and MATLAB scripts for preprocessing and analysis.

KEY FINDINGS AND LIMITATIONS

Our preliminary findings revealed activation in 15 participants (7 men, 8 women), exhibiting diverse patterns of activity across the T10-S5 neuronal segments during task-fMRI sessions conducted with both empty and full bladder conditions during sBCR. The identified activated regions included sympathetic (T10-L2), parasympathetic (S2-S4), and somatic nuclei (S2-S4), previously implicated in facilitating lower urinary tract (LUT) control. Notably, our preliminary findings suggest that sex differences may influence these activation patterns, though further investigation and second-level analysis are warranted to confirm this observation.

CONCLUSIONS

Although preliminary, our findings demonstrate, for the first time, the efficacy of our fMRI protocol in detecting task-induced activity in the lumbosacral spinal cord, underscoring our capability to precisely target specific regions responsible for regulating LUT function.

Network segregation during episodic memory shows age-invariant relations with memory performance from 7 to 82 years

Lower episodic memory capability, as seen in development and aging compared with younger adulthood, may partly depend on lower brain network segregation. Here, our objective was twofold: (1) test this hypothesis using within- and between-network functional connectivity (FC) during episodic memory encoding and retrieval, in two independent samples (n = 734, age 7-82 years). (2) Assess associations with age and the ability to predict memory comparing task-general FC and memory-modulated FC. In a multiverse-inspired approach, we performed tests across multiple analytic choices. Results showed that relationships differed based on these analytic choices and were mainly present in the largest dataset,. Significant relationships indicated that (i) memory-modulated FC predicted memory performance and associated with memory in an age-invariant manner. (ii) In line with the so-called neural dedifferentiation view, task-general FC showed lower segregation with higher age in adults which was associated with worse memory performance. In development, although there were only weak signs of a neural differentiation, that is, gradually higher segregation with higher age, we observed similar lower segregation-worse memory relationships. This age-invariant relationships between FC and episodic memory suggest that network segregation is pivotal for memory across the healthy lifespan.

Prediction of Verbal Abilities From Brain Connectivity Data Across the Lifespan Using a Machine Learning Approach

Compared to nonverbal cognition such as executive or memory functions, language-related cognition generally appears to remain more stable until later in life. Nevertheless, different language-related processes, for example, verbal fluency versus vocabulary knowledge, appear to show different trajectories across the life span. One potential explanation for differences in verbal functions may be alterations in the functional and structural network architecture of different large-scale brain networks. For example, differences in verbal abilities have been linked to the communication within and between the frontoparietal (FPN) and default mode network (DMN). It, however, remains open whether brain connectivity within these networks may be informative for language performance at the individual level across the life span. Further information in this regard may be highly desirable as verbal abilities allow us to participate in daily activities, are associated with quality of life, and may be considered in preventive and interventional setups to foster cognitive health across the life span. So far, mixed prediction results based on resting-state functional connectivity (FC) and structural connectivity (SC) data have been reported for language abilities across different samples, age groups, and machine-learning (ML) approaches. Therefore, the current study set out to investigate the predictability of verbal fluency and vocabulary knowledge based on brain connectivity data in the DMN, FPN, and the whole brain using an ML approach in a lifespan sample (N = 717; age range: 18-85) from the 1000BRAINS study. Prediction performance was, thereby, systematically compared across (i) verbal [verbal fluency and vocabulary knowledge] and nonverbal abilities [processing speed and visual working memory], (ii) modalities [FC and SC data], (iii) feature sets [DMN, FPN, DMN-FPN, and whole brain], and (iv) samples [total, younger, and older aged group]. Results from the current study showed that verbal abilities could not be reliably predicted from FC and SC data across feature sets and samples. Thereby, no predictability differences emerged between verbal fluency and vocabulary knowledge across input modalities, feature sets, and samples. In contrast to verbal functions, nonverbal abilities could be moderately predicted from connectivity data, particularly SC, in the total and younger age group. Satisfactory prediction performance for nonverbal cognitive functions based on currently chosen connectivity data was, however, not encountered in the older age group. Current results, hence, emphasized that verbal functions may be more difficult to predict from brain connectivity data in domain-general cognitive networks and the whole brain compared to nonverbal abilities, particularly executive functions, across the life span. Thus, it appears warranted to more closely investigate differences in predictability between different cognitive functions and age groups.

Multivariate Neural Markers of Individual Differences in Thought Control Difficulties

Difficulties in controlling thought, including pathological rumination, worry, and intrusive thoughts, occur in a range of mental health disorders. Here we identify specific patterns of brain activity distributed within and across canonical brain networks that are associated with self-reported difficulties in controlling one's thoughts. These activity patterns were derived using multivariate pattern analysis on fMRI data recorded while participants engaged in one of four operations on an item in working memory: maintaining it, replacing it with another, specifically suppressing it, or clearing the mind of all thought. Individuals who reported greater difficulties exhibited brain activation patterns that were more variable and less differentiated across the four operations in frontoparietal and default mode networks, and showed less distinct patterns of connectivity within the default mode network. These activity profiles were absent during rest but serve as promising task-based neural markers, explaining over 30% of the variance in thought control difficulties.

Whole-brain functional connectivity predicts regional tau PET in preclinical Alzheimer's disease

Preclinical Alzheimer's disease (AD), characterized by the abnormal accumulation of amyloid prior to cognitive symptoms, presents a critical opportunity for early intervention. Past work has described functional connectivity changes in preclinical disease, yet the interplay between AD pathology and the functional connectome during this window remains unexplored. We applied connectome-based predictive modeling to investigate the ability of resting-state whole-brain functional connectivity to predict tau (18F-flortaucipir) and amyloid (18F-florbetapir) PET binding in a preclinical AD cohort (A4, n =342, age 65-85). Separate predictive models were developed for each of 14 regions, and model performance was assessed using a Spearman's correlation between predicted and observed PET binding standard uptake value ratios. We assessed the validity of significant models by applying them to an external dataset, and visualized the underlying connectivity that was positively and negatively correlated to posterior cingulate tau binding, the most successful model. We found that whole brain functional connectivity predicts regional tau PET, outperforming amyloid PET models. The best performing tau models were for regions affected in Braak stage IV-V regions (posterior cingulate, precuneus, lateral occipital cortex, middle temporal, inferior temporal, and Bank STS), while models for regions of earlier tau pathology (entorhinal, parahippocampal, fusiform, and amygdala) performed poorly. Importantly, tau models generalized to a symptomatic AD cohort (ADNI; amyloid positive, n = 211, age 55-90), in tau-elevated but not tau-negative individuals. For the posterior cingulate A4 tau model, the most successful model, the predictive edges positively correlated with posterior cingulate tau predominantly came from nodes within temporal, limbic, and cerebellar regions. The most predictive edges negatively associated to tau were from nodes of heteromodal association areas, particularly within the prefrontal and parietal cortices. These findings reveal that whole-brain functional connectivity predicts tau PET in preclinical AD and generalizes to a clinical dataset specifically in individuals with abnormal tau PET, highlighting the relevance of the functional connectome for the early detection and monitoring of AD pathology.

Brain functional connectivity and anatomical features as predictors of cognitive behavioral therapy outcome for anxiety in youths

BACKGROUND

Because pediatric anxiety disorders precede the onset of many other problems, successful prediction of response to the first-line treatment, cognitive-behavioral therapy (CBT), could have a major impact. This study evaluates whether structural and resting-state functional magnetic resonance imaging can predict post-CBT anxiety symptoms.

METHODS

Two datasets were studied: (A) one consisted of n = 54 subjects with an anxiety diagnosis, who received 12 weeks of CBT, and (B) one consisted of n = 15 subjects treated for 8 weeks. Connectome predictive modeling (CPM) was used to predict treatment response, as assessed with the PARS. The main analysis included network edges positively correlated with treatment outcome and age, sex, and baseline anxiety severity as predictors. Results from alternative models and analyses are also presented. Model assessments utilized 1000 bootstraps, resulting in a 95% CI for R2, r, and mean absolute error (MAE).

RESULTS

The main model showed a MAE of approximately 3.5 (95% CI: [3.1-3.8]) points, an R2 of 0.08 [-0.14-0.26], and an r of 0.38 [0.24-0.511]. When testing this model in the left-out sample (B), the results were similar, with an MAE of 3.4 [2.8-4.7], R2-0.65 [-2.29-0.16], and r of 0.4 [0.24-0.54]. The anatomical metrics showed a similar pattern, where models rendered overall low R2.

CONCLUSIONS

The analysis showed that models based on earlier promising results failed to predict clinical outcomes. Despite the small sample size, this study does not support the extensive use of CPM to predict outcomes in pediatric anxiety.

Time-frequency and functional connectivity analysis in drug-naive adolescents with depression based on electroencephalography using a visual cognitive task: A comparative study

BACKGROUND

Previous research studies have demonstrated cognitive deficits in adolescents with depression; however, the neuroelectrophysiological mechanisms underlying these deficits remain poorly understood. Utilizing electroencephalography (EEG) data collected during cognitive tasks, this study applies time-frequency analysis and functional connectivity (FC) techniques to explore the neuroelectrophysiological alterations associated with cognitive deficits in adolescents with depression.

METHODS

A total of 173 adolescents with depression and 126 healthy controls (HC) participated in the study, undergoing EEG while performing a visual oddball task. Delta, theta, and alpha power spectra, along with FC, were calculated and analyzed.

RESULTS

Adolescents with depression exhibited significantly reduced delta, theta, and alpha power at the Fz, Cz, C5, C6, Pz, P5, and P6 electrodes compared to the HC group. Notably, theta power at the F5 electrode and alpha power at the F5 and F6 electrodes were significantly lower in the depression group than in the HC group. Additionally, cortical FC in the frontal and central regions was markedly decreased in adolescents with depression compared to HC.

CONCLUSIONS

During cognitive tasks, adolescents with depression display distinct abnormalities in both high- and low-frequency brain oscillations, as well as reduced functional connectivity in the frontal, central, and parietal regions compared to HC. These findings offer valuable neuroelectrophysiological insights into the cognitive deficits associated with adolescent depression.

Connectome-wide brain signature during fast-food advertisement exposure predicts BMI at 2 years

Food advertisements target adolescents, contributing to weight gain and obesity. However, whether brain connectivity during those food advertisements can predict weight gain is unknown. Here, 121 adolescents [14.1 ± 1.0 years; 50.4% female; body mass index (BMI): 23.4 ± 4.8; 71.9% White] completed both a baseline fMRI paradigm viewing advertisements (unhealthy fast food, healthier fast food, and nonfood) and an anthropometric assessment 2 years later. We used connectome-based predictive modeling to derive brain networks that were associated with BMI both at baseline and the 2-year follow-up. During exposure to unhealthy fast-food commercials, we identified a brain network comprising high-degree nodes in the hippocampus, parahippocampal gyrus, and fusiform gyrus rich with connections to prefrontal and occipital nodes that predicted lower BMI at the 2-year follow-up (r = 0.17; P = .031). A similar network was derived from baseline BMI (n = 168; r = 0.34; P < .001). Functional connectivity networks during exposure to the healthier fast food (P = .152) and nonfood commercials (P = .117) were not significant predictors of 2-year BMI. Key brain regions in our derived networks have been previously shown to encode aspects of memory formation, visual processing, and self-control. As such, the integration of these regions may reflect a mechanism of adolescents' ability to exert self-control toward obesogenic food stimuli.

Tangent space functional reconfigurations in individuals at risk for alcohol use disorder

Human brain function dynamically adjusts to ever-changing stimuli from the external environment. Studies characterizing brain functional reconfiguration are, nevertheless, scarce. Here, we present a principled mathematical framework to quantify brain functional reconfiguration when engaging and disengaging from a stop signal task (SST). We apply tangent space projection (a Riemannian geometry mapping technique) to transform the functional connectomes (FCs) of 54 participants and quantify functional reconfiguration using the correlation distance of the resulting tangent-FCs. Our goal was to compare functional reconfigurations in individuals at risk for alcohol use disorder (AUD). We hypothesized that functional reconfigurations when transitioning to/from a task would be influenced by family history of AUD (FHA) and other AUD risk factors. Multilinear regression models showed that engaging and disengaging functional reconfiguration were associated with FHA and recent drinking. When engaging in the SST after a rest condition, functional reconfiguration was negatively associated with recent drinking, while functional reconfiguration when disengaging from the SST was negatively associated with FHA. In both models, several other factors contributed to the functional reconfiguration. This study demonstrates that tangent-FCs can characterize task-induced functional reconfiguration and that it is related to AUD risk.

Connectome-Based Predictive Modeling of PTSD Development Among Recent Trauma Survivors

Importance

The weak link between subjective symptom-based diagnostics for posttraumatic psychopathology and objective neurobiological indices hinders the development of effective personalized treatments.

Objective

To identify early neural networks associated with posttraumatic stress disorder (PTSD) development among recent trauma survivors.

Design, Setting, and Participants

This prognostic study used data from the Neurobehavioral Moderators of Posttraumatic Disease Trajectories (NMPTDT) large-scale longitudinal neuroimaging dataset of recent trauma survivors. The NMPTDT study was conducted from January 20, 2015, to March 11, 2020, and included adult civilians who were admitted to a general hospital emergency department in Israel and screened for early PTSD symptoms indicative of chronic PTSD risk. Enrolled participants completed comprehensive clinical assessments and functional magnetic resonance imaging (fMRI) scans at 1, 6, and 14 months post trauma. Data were analyzed from September 2023 to March 2024.

Exposure

Traumatic events included motor vehicle incidents, physical assaults, robberies, hostilities, electric shocks, fires, drownings, work accidents, terror attacks, or large-scale disasters.

Main Outcomes and Measures

Connectome-based predictive modeling (CPM), a whole-brain machine learning approach, was applied to resting-state and task-based fMRI data collected at 1 month post trauma. The primary outcome measure was PTSD symptom severity across the 3 time points, assessed with the Clinician-Administered PTSD Scale for DSM-5 (CAPS-5). Secondary outcomes included Diagnostic and Statistical Manual of Mental Disorders (Fifth Edition) (DSM-5) PTSD symptom clusters (intrusion, avoidance, negative alterations in mood and cognition, hyperarousal).

Results

A total of 162 recent trauma survivors (mean [SD] age, 33.9 [11.5] years; 80 women [49.4%] and 82 men [50.6%]) were included at 1 month post trauma. Follow-up assessments were completed by 136 survivors (84.0%) at 6 months and by 133 survivors (82.1%) at 14 months post trauma. Among the 162 recent trauma survivors, CPM significantly predicted PTSD severity at 1 month (ρ = 0.18, P < .001) and 14 months (ρ = 0.24, P < .001) post trauma, but not at 6 months post trauma (ρ = 0.03, P = .39). The most predictive edges at 1 month included connections within and between the anterior default mode, motor sensory, and salience networks. These networks, with the additional contribution of the central executive and visual networks, were predictive of symptoms at 14 months. CPM predicted avoidance and negative alterations in mood and cognition at 1 month, but it predicted intrusion and hyperarousal symptoms at 14 months.

Conclusions and Relevance

In this prognostic study of recent trauma survivors, individual differences in large-scale neural networks shortly after trauma were associated with variability in PTSD symptom trajectories over the first year following trauma exposure. These findings suggest that CPM may identify potential targets for interventions.

Towards a neurodevelopmental model of bipolar disorder: a critical review of trait- and state-related functional neuroimaging in adolescents and young adults

Neurodevelopmental mechanisms are increasingly implicated in bipolar disorder (BD), highlighting the importance of their study in young persons. Neuroimaging studies have demonstrated a central role for frontotemporal corticolimbic brain systems that subserve processing and regulation of emotions, and processing of reward in adults with BD. As adolescence and young adulthood (AYA) is a time when fully syndromal BD often emerges, and when these brain systems undergo dynamic maturational changes, the AYA epoch is implicated as a critical period in the neurodevelopment of BD. Functional magnetic resonance imaging (fMRI) studies can be especially informative in identifying the functional neuroanatomy in adolescents and young adults with BD (BDAYA) and at high risk for BD (HR-BDAYA) that is related to acute mood states and trait vulnerability to the disorder. The identification of early emerging brain differences, trait- and state-based, can contribute to the elucidation of the developmental neuropathophysiology of BD, and to the generation of treatment and prevention targets. In this critical review, fMRI studies of BDAYA and HR-BDAYA are discussed, and a preliminary neurodevelopmental model is presented based on a convergence of literature that suggests early emerging dysfunction in subcortical (e.g., amygdalar, striatal, thalamic) and caudal and ventral cortical regions, especially ventral prefrontal cortex (vPFC) and insula, and connections among them, persisting as trait-related features. More rostral and dorsal cortical alterations, and bilaterality progress later, with lateralization, and direction of functional imaging findings differing by mood state. Altered functioning of these brain regions, and regions they are strongly connected to, are implicated in the range of symptoms seen in BD, such as the insula in interoception, precentral gyrus in motor changes, and prefrontal cortex in cognition. Current limitations, and outlook on the future use of neuroimaging evidence to inform interventions and prevent the onset of mood episodes in BDAYA, are outlined.

Exploring Graph Theory Mechanisms of Fluid Intelligence in the DLPFC: Insights From Resting-State fNIRS Across Various Time Windows

BACKGROUND

Brain imaging technologies can measure fluid intelligence (gF) levels more directly, objectively, and dynamically, compared to traditional questionnaire scales. To clarify the temporal mechanisms of graph theory in measuring gF, this study investigated the relationship between graph theoretical indicators in the dorsolateral prefrontal cortex (DLPFC) and gF levels under various time windows.

METHODS

Using 30-min resting-state fNIRS (rs-fNIRS) data and Raven's Advanced Progressive Matrices from 116 healthy participants, the relationship between individual gF levels and DLPFC brain signals was analyzed using average degree (AD) and global efficiency (Eglob).

RESULTS

AD and Eglob in the resting-state DLPFC were significantly negatively correlated with the RAPM score. Considering the effectiveness and efficiency of gF measurement, a 2-min data collection might suffice, while for Eglob, more than 15-min collection was more effective.

CONCLUSION

These findings help clarify brain indicators and demonstrate the effectiveness of rs-fNIRS in intelligence measurement, providing a theoretical and practical basis for portable and objective gF assessment .

Neurobiological fingerprints of negative symptoms in schizophrenia identified by connectome-based modeling

AIM

As a central component of schizophrenia psychopathology, negative symptoms result in detrimental effects on long-term functional prognosis. However, the neurobiological mechanism underlying negative symptoms remains poorly understood, which limits the development of novel treatment interventions. This study aimed to identify the specific neural fingerprints of negative symptoms in schizophrenia.

METHODS

Based on resting-state functional connectivity data obtained in a large sample (n = 132) of first-episode drug-naïve schizophrenia patients (DN-FES), connectome-based predictive modeling (CPM) with cross-validation was applied to identify functional networks that predict the severity of negative symptoms. The generalizability of identified networks was then validated in an independent sample of n = 40 DN-FES.

RESULTS

A connectivity pattern significantly driving the prediction of negative symptoms (ρ = 0.28, MSE = 81.04, P = 0.012) was identified within and between networks implicated in motivation (medial frontal, subcortical, sensorimotor), cognition (default mode, frontoparietal, medial frontal) and error processing (medial frontal and cerebellum). The identified networks also predicted negative symptoms in the independent validation sample (ρ = 0.37, P = 0.018). Importantly, the predictive model was symptom-specific and robust considering the potential effects of demographic characteristics and validation strategies.

CONCLUSIONS

Our study discovers and validates a comprehensive network model as the unique neural substrates of negative symptoms in schizophrenia, which provides a novel and comprehensive perspective to the development of target treatment strategies for negative symptoms.

Stimulus Selection Influences Prediction of Individual Phenotypes in Naturalistic Conditions

While the use of naturalistic stimuli such as movie clips for understanding individual differences and brain-behaviour relationships attracts increasing interest, the influence of stimulus selection remains largely unclear. By using machine learning to predict individual traits (phenotypes) from brain activity evoked during various movie clips, we show that different movie stimuli can result in distinct prediction performances. In brain regions related to lower-level processing of the stimulus, prediction to a certain degree benefits from stronger synchronisation of brain activity across subjects. By contrast, better predictions in frontoparietal brain regions are mainly associated with larger inter-subject variability. Furthermore, we demonstrate that while movie clips with rich social content in general achieve better predictions, the importance of specific movie features for prediction highly depends on the phenotype under investigation. Overall, our findings underscore the importance of careful stimulus selection and provide novel insights into stimulus selection for phenotype prediction in naturalistic conditions, opening new avenues for future research.

Role of Sex in Shaping Brain Network Organization During Reading in Developmental Dyslexia

Background/Methods: The influence of sex on brain organization was investigated in functional reading networks in 8-year-old children, in those typically developing and those with developmental dyslexia (DD), utilizing the minimum spanning tree model. Results: The word reading task revealed subtle sex differences in brain connectivity and highlighted even small individual variations in functional connectivity characteristics, particularly among boys with DD. In girls, significantly stronger connections and core hubs were identified within and between motor, parietal, and visual networks in posterior brain regions in both hemispheres, particularly in the θ (dyslexics) and δ (normolexics) frequency bands. In contrast, boys showed a more diffuse connectivity pattern, predominantly in the left hemisphere, encompassing anterior heteromodal and sensorimotor networks. Girls exhibited greater network complexity (bigger leaf fraction, kappa, and tree hierarchy), particularly in the θ and δ frequency bands, while boys with DD showed increased network efficiency, except for in the γ2 band (smaller diameter and bigger leaf fraction). Therefore, gender-specific differences in brain network organization may affect reading development and dyslexia. While sex may influence brain network development, its impact on the sensorimotor and frontoparietal networks of 8-year-old children is relatively limited. Significant sex differences were observed in only a small subset of children, primarily in higher (β2-γ2) frequency bands. Conclusions: Interindividual variations were evident only in boys with DD, impacting both sensorimotor and association networks. Different rates of cortical network maturation between sexes with DD during childhood may contribute to variations associated with disruptions in brain network development, even within fundamental networks like the sensorimotor network.

Connectome-based Predictive Models of General and Specific Executive Functions

Executive functions, the set of cognitive control processes that facilitate adaptive thoughts and actions, are composed primarily of three distinct yet interrelated cognitive components: Inhibition, Shifting, and Updating. While prior research has examined the nature of different components as well as their inter-relationships, fewer studies examined whole-brain connectivity to predict individual differences for the three cognitive components and associated tasks. Here, using the Connectome-based Predictive Modelling (CPM) approach and open-access data from the Human Connectome Project, we built brain network models to successfully predict individual performance differences on the Flanker task, the Dimensional Change Card Sort task, and the 2-back task, each putatively corresponding to Inhibition, Shifting, and Updating. We focused on grayordinate fMRI data collected during the 2-back tasks after confirming superior predictive performance over resting-state and volumetric data. High cross-task prediction accuracy as well as joint recruitment of canonical networks, such as the frontoparietal and default-mode networks, suggest the existence of a common executive function factor. To investigate the relationships among the three executive function components, we developed new measures to disentangle their shared and unique aspects. Our analysis confirmed that a shared executive function component can be predicted from functional connectivity patterns densely located around the frontoparietal, default-mode and dorsal attention networks. The Updating-specific component showed significant cross-prediction with the general executive function factor, suggesting a relatively stronger role than the other components. In contrast, the Shifting-specific and Inhibition-specific components exhibited lower cross-prediction performance, indicating more distinct and specialized roles. Given the limitation that individual behavioral measures do not purely reflect the intended cognitive constructs, our study demonstrates a novel approach to infer common and specific components of executive function.

Multivariate Neural Markers of Individual Differences in Thought Control Difficulties

Difficulties in controlling thought, including pathological rumination, worry, and intrusive thoughts, occur in a range of mental health disorders. Here we identify specific patterns of brain activity distributed within and across canonical brain networks that are associated with self-reported difficulties in controlling one's thoughts. These activity patterns were derived using multivariate pattern analysis on fMRI data recorded while participants engaged in one of four operations on an item in working memory: maintaining it, replacing it with another, specifically suppressing it, or clearing the mind of all thought. Individuals who reported greater difficulties exhibited brain activation patterns that were more variable and less differentiated across the four operations in frontoparietal and default mode networks, and showed less distinct patterns of connectivity within the default mode network. These activity profiles were absent during rest but serve as promising task-based neural markers, explaining over 30% of the variance in thought control difficulties.

Identification and External Validation of a Problem Cannabis Risk Network

BACKGROUND

Cannabis use is common, particularly during emerging adulthood when brain development is ongoing, and its use is associated with harmful outcomes for a subset of people. An improved understanding of the neural mechanisms underlying risk for problem-level use is critical to facilitate the development of more effective prevention and treatment approaches.

METHODS

In the current study, we applied a whole-brain, data-driven, machine learning approach to identify neural features predictive of problem-level cannabis use in a nonclinical sample of college students (n = 191, 58% female) based on reward task functional connectivity data. We further examined whether the identified network would generalize to predict cannabis use in an independent sample of European adolescents/emerging adults (n = 1320, 53% female), whether it would predict clinical characteristics among adults seeking treatment for cannabis use disorder (n = 33, 9% female), and whether it was specific for predicting cannabis versus alcohol use outcomes across datasets.

RESULTS

Results demonstrated identification of a problem cannabis risk network, which generalized to predict cannabis use in an independent sample of adolescents and was linked to increased addiction severity and poorer treatment outcome in a third sample of treatment-seeking adults. Furthermore, the identified network was specific for predicting cannabis versus alcohol use outcomes across all 3 datasets.

CONCLUSIONS

Findings provide insight into neural mechanisms of risk for problem-level cannabis use among adolescents/emerging adults. Future work is needed to assess whether targeting this network can improve prevention and treatment outcomes.

Using precision approaches to improve brain-behavior prediction

Predicting individual behavioral traits from brain idiosyncrasies has broad practical implications, yet predictions vary widely. This constraint may be driven by a combination of signal and noise in both brain and behavioral variables. Here, we expand on this idea, highlighting the potential of extended sampling 'precision' studies. First, we discuss their relevance to improving the reliability of individualized estimates by minimizing measurement noise. Second, we review how targeted within-subject experiments, when combined with individualized analysis or modeling frameworks, can maximize signal. These improvements in signal-to-noise facilitated by precision designs can help boost prediction studies. We close by discussing the integration of precision approaches with large-sample consortia studies to leverage the advantages of both.

Patterns of Change in Functional Connectivity and Motor Performance Are Different in Youth Recently Recovered from Concussion

Adolescents who have sustained a concussion or mild traumatic brain injury (mTBI) are prone to repeat injuries which may be related to subtle motor deficits persisting after clinical recovery. Cross-sectional research has found that these deficits are associated with altered functional connectivity among somatomotor, dorsal attention, and default mode networks. However, our understanding of how these brain-behavior relationships change over time after clinical recovery is limited. In this study, we examined categorical and dimensional trajectories of functional connectivity and subtle motor performance in youth clinically recovered from mTBI and never-injured controls (10-17 years). All participants completed task-based and resting-state functional magnetic resonance imaging scans and the Physical and Neurological Examination of Subtle Signs (PANESS) at initial and 3-month follow-up visits. We examined somatomotor-dorsal attention and somatomotor-default mode network connectivity and their association with PANESS performance. Compared with controls, a larger proportion of youth recovered from mTBI showed increases in somatomotor-dorsal attention functional connectivity over time; in contrast, there were no differences in somatomotor-default mode connectivity trajectories between youth recovered from mTBI and controls. Relative to controls, youth recovered from mTBI who showed greater increases in somatomotor-dorsal attention connectivity over time also completed motor tasks more slowly at the 3-month compared with the initial visit. Collectively, these findings suggest that longitudinal changes in somatomotor-dorsal attention functional connectivity may be associated with lingering motor learning deficits after clinical recovery from pediatric mTBI. Further research is necessary to understand how trajectories of functional connectivity and motor performance can inform individual-level outcomes, for instance, susceptibility to future injuries in both youth who are never injured and those clinically recovered from mTBI.

What is the best brain state to predict autistic traits?

Autism is a heterogeneous condition, and functional magnetic resonance imaging-based studies have advanced understanding of neurobiological correlates of autistic features. Nevertheless, little work has focused on the optimal brain states to reveal brain-phenotype relationships. In addition, there is a need to better understand the relevance of attentional abilities in mediating autistic features. Using connectome-based predictive modelling, we interrogate three datasets to determine scanning conditions that can boost prediction of clinically relevant phenotypes and assess generalizability. In dataset one, a sample of youth with autism and neurotypical participants, we find that a sustained attention task (the gradual onset continuous performance task) results in high prediction performance of autistic traits compared to a free-viewing social attention task and a resting-state condition. In dataset two, we observe the predictive network model of autistic traits generated from the sustained attention task generalizes to predict measures of attention in neurotypical adults. In dataset three, we show the same predictive network model of autistic traits from dataset one further generalizes to predict measures of social responsiveness in data from the Autism Brain Imaging Data Exchange. In sum, our data suggest that an in-scanner sustained attention challenge can help delineate robust markers of autistic traits and support the continued investigation of the optimal brain states under which to predict phenotypes in psychiatric conditions.

Toward a functional future for the cognitive neuroscience of human aging

The cognitive neuroscience of human aging seeks to identify neural mechanisms behind the commonalities and individual differences in age-related behavioral changes. This goal has been pursued predominantly through structural or "task-free" resting-state functional neuroimaging. The former has elucidated the material foundations of behavioral decline, and the latter has provided key insight into how functional brain networks change with age. Crucially, however, neither is able to capture brain activity representing specific cognitive processes as they occur. In contrast, task-based functional imaging allows a direct probe into how aging affects real-time brain-behavior associations in any cognitive domain, from perception to higher-order cognition. Here, we outline why task-based functional neuroimaging must move center stage to better understand the neural bases of cognitive aging. In turn, we sketch a multi-modal, behavior-first research framework that is built upon cognitive experimentation and emphasizes the importance of theory and longitudinal design.

An electroencephalography connectome predictive model of craving for methamphetamine

Background

Methamphetamine use disorder (MUD) is characterized by prominent psychological craving and its relapsing nature. Previous studies have linked trait impulsivity and abstinence duration to drug use, but the neural substrates of drug cue-induced craving and its relationship with these traits remain unclear in MUD.

Methods

We acquired high-density resting-state electroencephalography (EEG) after participants watched a five-minute video demonstrating methamphetamine use. Combining precise source imaging to reconstruct brain activities with connectome predictive modeling (CPM), we built a craving-specific network within beta band activity from two independent MUD cohorts (N=144 for model development and N=47 for validation).

Results

This network reveals a unified neural signature for craving in MUD, spanning multiple brain networks including the medial prefrontal, frontal parietal, and subcortical networks. Our findings underscored the mediating role of this craving connectome profile in modulating the relationship between abstinence duration and craving intensity. Moreover, trait impulsivity mediated the relationship between the EEG-derived craving connectome and cue-induced craving.

Conclusion

This study presents a novel predictive model that utilizes sourced connectivity from high-density EEG of resting-state recording to successfully predict methamphetamine craving in abstinent individuals with MUD. These results shed light on the cognitive organization involved in craving, involving cognitive control, attention, and reward reactivity. A comprehensive analysis reveals EEG data's capacity to decipher craving's complex dynamics, facilitating improved understanding and targeted treatments for substance use disorders.

Predicting upper limb motor recovery in subacute stroke patients via fNIRS-measured cerebral functional responses induced by robotic training

BACKGROUND

Neural activation induced by upper extremity robot-assisted training (UE-RAT) helps characterize adaptive changes in the brains of poststroke patients, revealing differences in recovery potential among patients. However, it remains unclear whether these task-related neural activities can effectively predict rehabilitation outcomes. In this study, we utilized functional near-infrared spectroscopy (fNIRS) to measure participants' neural activity profiles during resting and UE-RAT tasks and developed models via machine learning to verify whether task-related functional brain responses can predict the recovery of upper limb motor function.

METHODS

Cortical activation and brain network functional connectivity (FC) in brain regions such as the superior frontal cortex, premotor cortex, and primary motor cortex were measured using fNIRS in 82 subacute stroke patients in the resting state and during UE-RAT. The Fugl-Meyer Upper Extremity Assessment Scale (FMA-UE) was chosen as the index for assessing upper extremity motor function, and clinical information such as demographic and neurophysiological data was also collected. Robust features were screened in 100 randomly divided training sets using the least absolute shrinkage and selection operator (LASSO) method. Based on the selected robust features, machine learning algorithms were used to develop clinical models, fNIRS models, and combined models that integrated both clinical and fNIRS features. Finally, Shapley Additive Explanations (SHAP) was applied to interpret the prediction process and analyze key predictive factors.

RESULTS

Compared to the resting state, task-related FC is a more robust feature for modeling, with screening frequencies above 90%. The combined models built using artificial neural networks (ANNs) and support vector machines (SVMs) significantly outperformed the other algorithms, with an average AUC of 0.861 (± 0.087) for the ANN and an average correlation coefficient (r) of 0.860 (± 0.069) for the SVM. Furthermore, predictive factor analysis of the models revealed that FC measured during tasks is the most important factor for predicting upper limb motor function.

CONCLUSION

This study confirmed that UE-RAT-induced FC can serve as an important predictor of rehabilitation, especially when combined with clinical information, further enhancing the accuracy of model predictions. These findings provide new insights for the early prediction of patients' recovery potential, which may contribute to personalized rehabilitation decisions.

Choosing explanation over performance: Insights from machine learning-based prediction of human intelligence from brain connectivity

A growing body of research predicts individual cognitive ability levels from brain characteristics including functional brain connectivity. The majority of this research achieves statistically significant prediction performance but provides limited insight into neurobiological processes underlying the predicted concepts. The insufficient identification of predictive brain characteristics may present an important factor critically contributing to this constraint. Here, we encourage to design predictive modeling studies with an emphasis on interpretability to enhance our conceptual understanding of human cognition. As an example, we investigated in a preregistered study which functional brain connections successfully predict general, crystallized, and fluid intelligence in a sample of 806 healthy adults (replication: N = 322). The choice of the predicted intelligence component as well as the task during which connectivity was measured proved crucial for better understanding intelligence at the neural level. Further, intelligence could be predicted not solely from one specific set of brain connections, but from various combinations of connections with system-wide locations. Such partially redundant, brain-wide functional connectivity characteristics complement intelligence-relevant connectivity of brain regions proposed by established intelligence theories. In sum, our study showcases how future prediction studies on human cognition can enhance explanatory value by prioritizing a systematic evaluation of predictive brain characteristics over maximizing prediction performance.

Medial Amygdalar Tau Is Associated With Mood Symptoms in Preclinical Alzheimer's Disease

BACKGROUND

While the amygdala receives early tau deposition in Alzheimer's disease (AD) and is involved in social and emotional processing, the relationship between amygdalar tau and early neuropsychiatric symptoms in AD is unknown. We sought to determine whether focal tau binding in the amygdala and abnormal amygdalar connectivity were detectable in a preclinical AD cohort and identify relationships between these and self-reported mood symptoms.

METHODS

We examined 598 individuals (347 amyloid positive [58% female], 251 amyloid negative [62% female] subset in tau positron emission tomography and functional magnetic resonance imaging cohorts) from the A4 (Anti-Amyloid Treatment in Asymptomatic AD) Study. In the tau positron emission tomography cohort, we used amygdalar segmentations to examine representative nuclei from 3 functional divisions of the amygdala. We analyzed between-group differences in division-specific tau binding in the amygdala in preclinical AD. We conducted seed-based functional connectivity analyses from each division in the functional magnetic resonance imaging cohort. Finally, we conducted exploratory post hoc correlation analyses between neuroimaging biomarkers of interest and anxiety and depression scores.

RESULTS

Amyloid-positive individuals demonstrated increased tau binding in the medial and lateral amygdala, and tau binding in these regions was associated with mood symptoms. Across amygdalar divisions, amyloid-positive individuals had relatively higher regional connectivity from the amygdala to other temporal regions, the insula, and the orbitofrontal cortex, but medial amygdala to retrosplenial cortex connectivity was lower. Medial amygdala to retrosplenial connectivity was negatively associated with anxiety symptoms, as was retrosplenial tau.

CONCLUSIONS

Our findings suggest that preclinical tau deposition in the amygdala and associated changes in functional connectivity may be related to early mood symptoms in AD.

Elevated Activity in Left Homologous Music Circuits Is Inhibitory for Music Perception but Mediated by Structure-Function Coupling

AIMS

Previous studies suggested that structural and functional connectivity of right frontotemporal circuits associate with music perception. Emerging evidences demonstrated that structure-function coupling is important for cognition and may allow for a more sensitive investigation of brain-behavior association, while we know little about the relationship between structure-function coupling and music perception.

METHODS

We collected multimodal neuroimaging data from 106 participants and measured their music perception by Montreal Battery of Evaluation of Amusia (MBEA). Then we computed structure-function coupling, amplitude of low-frequency fluctuation (ALFF), gray matter volume (GMV), and structural/functional degree centrality (DC) and utilized support vector regression algorithm to build their relationship with MBEA score.

RESULTS

We found structure-function coupling, rather than GMV, ALFF, or DC, contributed to predict MBEA score. Left middle frontal gyrus (L.MFG), bilateral inferior temporal gyrus, and right insula were the most predictive ROIs for MBEA score. Mediation analysis revealed structure-function coupling of L.MFG, a region that is homologous to typical music circuits, fully mediated the negative link between ALFF of L.MFG and MBEA score.

CONCLUSION

Structure-function coupling is more effective when explaining variation in music perception. Our findings provide further understanding for the neural basis of music and have implications for cognitive causes of amusia.

Brain-phenotype predictions of language and executive function can survive across diverse real-world data: Dataset shifts in developmental populations

Predictive modeling potentially increases the reproducibility and generalizability of neuroimaging brain-phenotype associations. Yet, the evaluation of a model in another dataset is underutilized. Among studies that undertake external validation, there is a notable lack of attention to generalization across dataset-specific idiosyncrasies (i.e., dataset shifts). Research settings, by design, remove the between-site variations that real-world and, eventually, clinical applications demand. Here, we rigorously test the ability of a range of predictive models to generalize across three diverse, unharmonized developmental samples: the Philadelphia Neurodevelopmental Cohort (n=1291), the Healthy Brain Network (n=1110), and the Human Connectome Project in Development (n=428). These datasets have high inter-dataset heterogeneity, encompassing substantial variations in age distribution, sex, racial and ethnic minority representation, recruitment geography, clinical symptom burdens, fMRI tasks, sequences, and behavioral measures. Through advanced methodological approaches, we demonstrate that reproducible and generalizable brain-behavior associations can be realized across diverse dataset features. Results indicate the potential of functional connectome-based predictive models to be robust despite substantial inter-dataset variability. Notably, for the HCPD and HBN datasets, the best predictions were not from training and testing in the same dataset (i.e., cross-validation) but across datasets. This result suggests that training on diverse data may improve prediction in specific cases. Overall, this work provides a critical foundation for future work evaluating the generalizability of brain-phenotype associations in real-world scenarios and clinical settings.

Identification of a cognitive network with effective connectivity to post-stroke cognitive impairment

Altered connectivity within complex functional networks has been observed in individuals with post-stroke cognitive impairment (PSCI) and during cognitive tasks. This study aimed to identify a cognitive function network that is responsive to cognitive changes during cognitive tasks and also sensitive to PSCI. To explore the network, we analyzed resting-state fMRI data from 20 PSCI patients and task-state fMRI data from 100 unrelated healthy young adults using functional connectivity analysis. We further employed spectral dynamic causal modeling to examine the effective connectivity among the pivotal regions within the network. Our findings revealed a common cognitive network that encompassed the hub regions 231 in the Subcortical network (SC), 70, 199, 242 in the Frontoparietal network (FP), 214 in the Visual II network, and 253 in the Cerebellum network (CBL). These hubs' effective connectivity, which showed reliable but slight changes during different cognitive tasks, exhibited notable alterations when comparing post-stroke cognitive impairment and improvement statuses. Decreased coupling strengths were observed in effective connections to CBL253 and from SC231 and FP70 in the improvement status. Increased connections to SC231 and FP70, from CBL253 and FP242, as well as from FP199 and FP242 to FP242 were observed in this status. These alterations exhibited a high sensitivity to signs of recovery, ranging from 80 to 100%. The effective connectivity pattern in both post-stroke cognitive statuses also reflected the influence of the MoCA score. This research succeeded in identifying a cognitive network with sensitive effective connectivity to cognitive changes after stroke, presenting a potential neuroimaging biomarker for forthcoming interventional studies.

Supplementary Information

The online version contains supplementary material available at 10.1007/s11571-024-10139-4.

Inferring neurocognition using artificial intelligence on brain MRIs

Brain magnetic resonance imaging (MRI) offers a unique lens to study neuroanatomic support of human neurocognition. A core mystery is the MRI explanation of individual differences in neurocognition and its manifestation in intelligence. The past four decades have seen great advancement in studying this century-long mystery, but the sample size and population-level studies limit the explanation at the individual level. The recent rise of big data and artificial intelligence offers novel opportunities. Yet, data sources, harmonization, study design, and interpretation must be carefully considered. This review aims to summarize past work, discuss rising opportunities and challenges, and facilitate further investigations on artificial intelligence inferring human neurocognition.

Deep learning of structural MRI predicts fluid, crystallized, and general intelligence

Can brain structure predict human intelligence? T1-weighted structural brain magnetic resonance images (sMRI) have been correlated with intelligence. However, the population-level association does not fully account for individual variability in intelligence. To address this, studies have emerged recently to predict individual subject's intelligence or neurocognitive scores. However, they are mostly on predicting fluid intelligence (the ability to solve new problems). Studies are lacking to predict crystallized intelligence (the ability to accumulate knowledge) or general intelligence (fluid and crystallized intelligence combined). This study tests whether deep learning of sMRI can predict an individual subject's verbal, comprehensive, and full-scale intelligence quotients (VIQ, PIQ, and FSIQ), which reflect fluid and crystallized intelligence. We performed a comprehensive set of 432 experiments, using different input image channels, six deep learning models, and two outcome settings, in 850 healthy and autistic subjects 6-64 years of age. Our findings indicate a statistically significant potential of T1-weighted sMRI in predicting intelligence, with a Pearson correlation exceeding 0.21 (p < 0.001). Interestingly, we observed that an increase in the complexity of deep learning models does not necessarily translate to higher accuracy in intelligence prediction. The interpretations of our 2D and 3D CNNs, based on GradCAM, align well with the Parieto-Frontal Integration Theory (P-FIT), reinforcing the theory's suggestion that human intelligence is a result of interactions among various brain regions, including the occipital, temporal, parietal, and frontal lobes. These promising results invite further studies and open new questions in the field.

Personality traits vary in their association with brain activity across situations

Human cognition supports complex behaviour across a range of situations, and traits (e.g. personality) influence how we react in these different contexts. Although viewing traits as situationally grounded is common in social sciences, often studies attempting to link brain activity to human traits examine brain-trait associations in a single task, or, under passive conditions like wakeful rest. These studies, often referred to as brain wide association studies (BWAS) have recently become the subject of controversy because results are often unreliable even with large sample sizes. Although there are important statistical reasons why BWAS yield inconsistent results, we hypothesised that the situation in which brain activity is measured will impact the power in detecting a reliable link to specific traits. We performed a state-space analysis where tasks from the Human Connectome Project (HCP) were organized into a low-dimensional space based on how they activated different large-scale neural systems. We examined how individuals' observed brain activity across these different contexts related to their personality. We found that for multiple personality traits, stronger associations with brain activity emerge in some tasks than others. These data highlight the importance of context-bound views for understanding how brain activity links to trait variation in human behaviour.

Replicability and generalizability in population psychiatric neuroimaging

Studies linking mental health with brain function in cross-sectional population-based association studies have historically relied on small, underpowered samples. Given the small effect sizes typical of such brain-wide associations, studies require samples into the thousands to achieve the statistical power necessary for replicability. Here, we detail how small sample sizes have hampered replicability and provide sample size targets given established association strength benchmarks. Critically, while replicability will improve with larger samples, it is not guaranteed that observed effects will meaningfully apply to target populations of interest (i.e., be generalizable). We discuss important considerations related to generalizability in psychiatric neuroimaging and provide an example of generalizability failure due to "shortcut learning" in brain-based predictions of mental health phenotypes. Shortcut learning is a phenomenon whereby machine learning models learn an association between the brain and an unmeasured construct (the shortcut), rather than the intended target of mental health. Given the complex nature of brain-behavior interactions, the future of epidemiological approaches to brain-based studies of mental health will require large, diverse samples with comprehensive assessment.

Quality over quantity: powering neuroimaging samples in psychiatry

Neuroimaging has been widely adopted in psychiatric research, with hopes that these non-invasive methods will provide important clues to the underpinnings and prediction of various mental health symptoms and outcomes. However, the translational impact of neuroimaging has not yet reached its promise, despite the plethora of computational methods, tools, and datasets at our disposal. Some have lamented that too many psychiatric neuroimaging studies have been underpowered with respect to sample size. In this review, we encourage this discourse to shift from a focus on sheer increases in sample size to more thoughtful choices surrounding experimental study designs. We propose considerations at multiple decision points throughout the study design, data modeling and analysis process that may help researchers working in psychiatric neuroimaging boost power for their research questions of interest without necessarily increasing sample size. We also provide suggestions for leveraging multiple datasets to inform each other and strengthen our confidence in the generalization of findings to both population-level and clinical samples. Through a greater emphasis on improving the quality of brain-based and clinical measures rather than merely quantity, meaningful and potentially translational clinical associations with neuroimaging measures can be achieved with more modest sample sizes in psychiatry.

Breakthroughs and challenges for generating brain network-based biomarkers of treatment response in depression

Treatment outcomes widely vary for individuals diagnosed with major depressive disorder, implicating a need for deeper understanding of the biological mechanisms conferring a greater likelihood of response to a particular treatment. Our improved understanding of intrinsic brain networks underlying depression psychopathology via magnetic resonance imaging and other neuroimaging modalities has helped reveal novel and potentially clinically meaningful biological markers of response. And while we have made considerable progress in identifying such biomarkers over the last decade, particularly with larger, multisite trials, there are significant methodological and practical obstacles that need to be overcome to translate these markers into the clinic. The aim of this review is to review current literature on brain network structural and functional biomarkers of treatment response or selection in depression, with a specific focus on recent large, multisite trials reporting predictive accuracy of candidate biomarkers. Regarding pharmaco- and psychotherapy, we discuss candidate biomarkers, reporting that while we have identified candidate biomarkers of response to a single intervention, we need more trials that distinguish biomarkers between first-line treatments. Further, we discuss the ways prognostic neuroimaging may help to improve treatment outcomes to neuromodulation-based therapies, such as transcranial magnetic stimulation and deep brain stimulation. Lastly, we highlight obstacles and technical developments that may help to address the knowledge gaps in this area of research. Ultimately, integrating neuroimaging-derived biomarkers into clinical practice holds promise for enhancing treatment outcomes and advancing precision psychiatry strategies for depression management. By elucidating the neural predictors of treatment response and selection, we can move towards more individualized and effective depression interventions, ultimately improving patient outcomes and quality of life.

Connectome-based fingerprinting: reproducibility, precision, and behavioral prediction

Functional magnetic resonance imaging-based functional connectivity enables the non-invasive mapping of individual differences in brain functional organization to individual differences in a vast array of behavioral phenotypes. This flexibility has renewed the search for neuroimaging-based biomarkers that exhibit reproducibility, prediction, and precision. Functional connectivity-based measures that share these three characteristics are key to achieving this goal. Here, we review the functional connectome fingerprinting approach and discuss its value, not only as a simple and intuitive conceptualization of the "functional connectome" that provides new insights into how the connectome is altered in association with psychiatric symptoms, but also as a straightforward and interpretable method for indexing the reproducibility of functional connectivity-based measures. We discuss how these advantages provide new avenues for strengthening reproducibility, precision, and behavioral prediction for functional connectomics and we consider new directions toward discovering better biomarkers for neuropsychiatric conditions.

Advances and challenges in neuroimaging-based pain biomarkers

Identifying neural biomarkers of pain has long been a central theme in pain neuroscience. Here, we review the state-of-the-art candidates for neural biomarkers of acute and chronic pain. We classify these potential neural biomarkers into five categories based on the nature of their target variables, including neural biomarkers of (1) within-individual perception, (2) between-individual sensitivity, and (3) discriminability for acute pain, as well as (4) assessment and (5) prospective neural biomarkers for chronic pain. For each category, we provide a synthesized review of candidate biomarkers developed using neuroimaging techniques including functional magnetic resonance imaging (fMRI), structural magnetic resonance imaging (sMRI), and electroencephalography (EEG). We also discuss the conceptual and practical challenges in developing neural biomarkers of pain. Addressing these challenges, optimal biomarkers of pain can be developed to deepen our understanding of how the brain represents pain and ultimately help alleviate patients' suffering and improve their well-being.

Individual cognitive traits can be predicted from task-based dynamic functional connectivity with a deep convolutional-recurrent model

There has been increased interest in understanding the neural substrates of intelligence and several human traits from neuroimaging data. Deep learning can be used to predict different cognitive measures, such as general and fluid intelligence, from different functional magnetic resonance imaging experiments providing information about the main brain areas involved in these predictions. Using neuroimaging and behavioral data from 874 subjects provided by the Human Connectome Project, we predicted various cognitive scores using dynamic functional connectivity derived from language and working memory functional magnetic resonance imaging task states, using a 360-region multimodal atlas. The deep model joins multiscale convolutional and long short-term memory layers and was trained under a 10-fold stratified cross-validation. We removed the confounding effects of gender, age, total brain volume, motion and the multiband reconstruction algorithm using multiple linear regression. We can explain 17.1% and 16% of general intelligence variance for working memory and language tasks, respectively. We showed that task-based dynamic functional connectivity has more predictive power than resting-state dynamic functional connectivity when compared to the literature and that removing confounders significantly reduces the prediction performance. No specific cortical network showed significant relevance in the prediction of general and fluid intelligence, suggesting a spatial homogeneous distribution of the intelligence construct in the brain.

Linking the neural signature of response time variability to Alzheimer's disease pathology and cognitive functioning

Promising evidence has suggested potential links between mind-wandering and Alzheimer's disease (AD). Yet, older adults with diagnosable neurocognitive disorders show reduced meta-awareness, thus questioning the validity of probe-assessed mind-wandering in older adults. In prior work, we employed response time variability as an objective, albeit indirect, marker of mind-wandering to identify patterns of functional connectivity that predicted mind-wandering. In the current study, we evaluated the association of this connectome-based, mind-wandering model with cerebral spinal fluid (CSF) p-tau/Aβ 42 ratio in 289 older adults from the Alzheimer's Disease NeuroImaging Initiative (ADNI). Moreover, we examined if this model was similarly associated with individual differences in composite measures of global cognition, episodic memory, and executive functioning. Edges from the high response time variability model were significantly associated with CSF p-tau/Aβ ratio. Furthermore, connectivity strength within edges associated with high response time variability was negatively associated with global cognition and episodic memory functioning. This study provides the first empirical support for a link between an objective neuromarker of mind-wandering and AD pathophysiology. Given the observed association between mind-wandering and cognitive functioning in older adults, interventions targeted at reducing mind-wandering, particularly before the onset of AD pathogenesis, may make a significant contribution to the prevention of AD-related cognitive decline.

Network-level enrichment provides a framework for biological interpretation of machine learning results

Machine learning algorithms are increasingly being utilized to identify brain connectivity biomarkers linked to behavioral and clinical outcomes. However, research often prioritizes prediction accuracy at the expense of biological interpretability, and inconsistent implementation of ML methods may hinder model accuracy. To address this, our paper introduces a network-level enrichment approach, which integrates brain system organization in the context of connectome-wide statistical analysis to reveal network-level links between brain connectivity and behavior. To demonstrate the efficacy of this approach, we used linear support vector regression (LSVR) models to examine the relationship between resting-state functional connectivity networks and chronological age. We compared network-level associations based on raw LSVR weights to those produced from the forward and inverse models. Results indicated that not accounting for shared family variance inflated prediction performance, the k-best feature selection via Pearson correlation reduced accuracy and reliability, and raw LSVR model weights produced network-level associations that deviated from the significant brain systems identified by forward and inverse models. Our findings offer crucial insights for applying machine learning to neuroimaging data, emphasizing the value of network enrichment for biological interpretation.

Variation in moment-to-moment brain state engagement changes across development and contributes to individual differences in executive function

Neural variability, or variation in brain signals, facilitates dynamic brain responses to ongoing demands. This flexibility is important during development from childhood to young adulthood, a period characterized by rapid changes in experience. However, little is known about how variability in the engagement of recurring brain states changes during development. Such investigations would require the continuous assessment of multiple brain states concurrently. Here, we leverage a new computational framework to study state engagement variability (SEV) during development. A consistent pattern of SEV changing with age was identified across cross-sectional and longitudinal datasets (N>3000). SEV developmental trajectories stabilize around mid-adolescence, with timing varying by sex and brain state. SEV successfully predicts executive function (EF) in youths from an independent dataset. Worse EF is further linked to alterations in SEV development. These converging findings suggest SEV changes over development, allowing individuals to flexibly recruit various brain states to meet evolving needs.

A robust brain network for sustained attention from adolescence to adulthood that predicts later substance use

Substance use, including cigarettes and cannabis, is associated with poorer sustained attention in late adolescence and early adulthood. Previous studies were predominantly cross-sectional or under-powered and could not indicate if impairment in sustained attention was a predictor of substance use or a marker of the inclination to engage in such behavior. This study explored the relationship between sustained attention and substance use across a longitudinal span from ages 14 to 23 in over 1000 participants. Behaviors and brain connectivity associated with diminished sustained attention at age 14 predicted subsequent increases in cannabis and cigarette smoking, establishing sustained attention as a robust biomarker for vulnerability to substance use. Individual differences in network strength relevant to sustained attention were preserved across developmental stages and sustained attention networks generalized to participants in an external dataset. In summary, brain networks of sustained attention are robust, consistent, and able to predict aspects of later substance use.

Unveiling the core functional networks of cognition: An ontology-guided machine learning approach

Deciphering the functional architecture that underpins diverse cognitive functions is fundamental quest in neuroscience. In this study, we employed an innovative machine learning framework that integrated cognitive ontology with functional connectivity analysis to identify brain networks essential for cognition. We identified a core assembly of functional connectomes, primarily located within the association cortex, which showed superior predictive performance compared to two conventional methods widely employed in previous research across various cognitive domains. Our approach achieved a mean prediction accuracy of 0.13 across 16 cognitive tasks, including working memory, reading comprehension, and sustained attention, outperforming the traditional methods' accuracy of 0.08. In contrast, our method showed limited predictive power for sensory, motor, and emotional functions, with a mean prediction accuracy of 0.03 across 9 relevant tasks, slightly lower than the traditional methods' accuracy of 0.04. These cognitive connectomes were further characterized by distinctive patterns of resting-state functional connectivity, structural connectivity via white matter tracts, and gene expression, highlighting their neurogenetic underpinnings. Our findings reveal a domain-general functional network fingerprint that pivotal to cognition, offering a novel computational approach to explore the neural foundations of cognitive abilities.

Anhedonia severity mediates the relationship between attentional networks recruitment and emotional blunting during music listening

Emotion studies have commonly reported impaired emotional processing in individuals with heightened anhedonic depressive symptoms, as typically measured by collecting single subjective ratings for a given emotional cue. However, the interindividual variation in moment-to-moment emotional reactivity, and associated time-varying brain networks recruitment as emotions are unfolding, remains unclear. In this study, we filled this gap by using the unique temporal characteristics of music to investigate behavioural and brain network dynamics as a function of anhedonic depressive symptoms severity. Thirty-one neurotypical participants aged 18-30 years completed anhedonic depression questionnaires and then continuously rated happy, neutral and sad pieces of music whilst undergoing MRI scanning. Using a unique combination of dynamic approaches to behavioural (i.e., emotion dynamics) and fMRI (i.e., leading eigenvector dynamics analysis; LEiDA) data analysis, we found that participants higher in anhedonic depressive symptoms exhibited increased recruitment of attentional networks and blunted emotional response to both happy and sad musical excerpts. Anhedonic depression mediated the relationship between attentional networks recruitment and emotional blunting, and the elevated recruitment of attentional networks during emotional pieces of music carried over into subsequent neutral music. Future studies are needed to investigate whether these findings could be generalised to a clinical population (i.e., major depressive disorder).