Multivariate BWAS can be replicable with moderate sample sizes

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.

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.

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.

Psychiatric neuroimaging designs for individualised, cohort, and population studies

Psychiatric neuroimaging faces challenges to rigour and reproducibility that prompt reconsideration of the relative strengths and limitations of study designs. Owing to high resource demands and varying inferential goals, current designs differentially emphasise sample size, measurement breadth, and longitudinal assessments. In this overview and perspective, we provide a guide to the current landscape of psychiatric neuroimaging study designs with respect to this balance of scientific goals and resource constraints. Through a heuristic data cube contrasting key design features, we discuss a resulting trade-off among small sample, precision longitudinal studies (e.g., individualised studies and cohorts) and large sample, minimally longitudinal, population studies. Precision studies support tests of within-person mechanisms, via intervention and tracking of longitudinal course. Population studies support tests of generalisation across multifaceted individual differences. A proposed reciprocal validation model (RVM) aims to recursively leverage these complementary designs in sequence to accumulate evidence, optimise relative strengths, and build towards improved long-term clinical utility.

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.

Principles of intensive human neuroimaging

The rise of large, publicly shared functional magnetic resonance imaging (fMRI) data sets in human neuroscience has focused on acquiring either a few hours of data on many individuals ('wide' fMRI) or many hours of data on a few individuals ('deep' fMRI). In this opinion article, we highlight an emerging approach within deep fMRI, which we refer to as 'intensive' fMRI: one that strives for extensive sampling of cognitive phenomena to support computational modeling and detailed investigation of brain function at the single voxel level. We discuss the fundamental principles, trade-offs, and practical considerations of intensive fMRI. We also emphasize that intensive fMRI does not simply mean collecting more data: it requires careful design of experiments to enable a rich hypothesis space, optimizing data quality, and strategically curating public resources to maximize community impact.

Polyconnectomic scoring of functional connectivity patterns across eight neuropsychiatric and three neurodegenerative disorders

BACKGROUND

Neuropsychiatric and neurodegenerative disorders involve diverse changes in brain functional connectivity. As an alternative to approaches searching for specific mosaic patterns of affected connections and networks, we used polyconnectomic scoring to quantify disorder-related whole-brain connectivity signatures into interpretable, personalized scores.

METHODS

The polyconnectomic score (PCS) measures the extent to which an individual's functional connectivity (FC) mirrors the whole-brain circuitry characteristics of a trait. We computed PCS for eight neuropsychiatric conditions (attention-deficit/hyperactivity disorder, anxiety-related disorders, autism spectrum disorder, obsessive-compulsive disorder, bipolar disorder, major depressive disorder, schizoaffective disorder, and schizophrenia) and three neurodegenerative conditions (Alzheimer's disease, frontotemporal dementia, and Parkinson's disease) across 22 datasets with resting-state functional MRI of 10,667 individuals (5,325 patients, 5,342 controls). We further examined PCS in 26,673 individuals from the population-based UK Biobank cohort.

RESULTS

PCS was consistently higher in out-of-sample patients across six of the eight neuropsychiatric and across all three investigated neurodegenerative disorders ([min, max]: AUC = [0.55, 0.73], pFDR = [1.8 x 10-16, 4.5 x 10-2]). Individuals with elevated PCS levels for neuropsychiatric conditions exhibited higher neuroticism (pFDR < 9.7 x 10-5), lower cognitive performance (pFDR < 5.3 x 10-5), and lower general wellbeing (pFDR < 9.7 x 10-4).

CONCLUSIONS

Our findings reveal generalizable whole-brain connectivity alterations in brain disorders. PCS effectively aggregates disorder-related signatures across the entire brain into an interpretable, subject-specific metric. A toolbox is provided for PCS computation.

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.

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.

Neuroimaging Biomarkers for Drug Discovery and Development in Schizophrenia

Schizophrenia is a chronic mental illness that affects up to 1% of the population. While efficacious therapies are available for positive symptoms, effective treatment of cognitive and negative symptoms remains an unmet need after decades of research. New developments in the field of neuroimaging are accelerating our knowledge gain regarding the underlying pathophysiology of symptoms in schizophrenia and psychosis spectrum disorders, inspiring new targets for drug development. However, no validated and qualified biomarkers are currently available to support the development of new therapeutics. This review summarizes the current use of neuroimaging technology in clinical drug development for psychotic disorders. As exemplified by drug development programs that target NMDA receptor hypofunction, neuroimaging results play a critical role in target discovery and establishing target engagement and dose selection. Furthermore, pharmacological neuroimaging may provide response biomarkers that allow for early decision making in proof-of-concept studies that leverage pharmacological challenge models in healthy volunteers. That said, while response and predictive biomarkers are starting to be evaluated in patient populations, they continue to play a limited role. Novel approaches to neuroimaging data acquisition and analysis may aid the establishment of biomarkers that are predictive at the individual level in the future. Nevertheless, various gaps in knowledge need to be addressed and biomarkers need to be validated to establish them as "fit for purpose" in drug development.

Power and reproducibility in the external validation of brain-phenotype predictions

Brain-phenotype predictive models seek to identify reproducible and generalizable brain-phenotype associations. External validation, or the evaluation of a model in external datasets, is the gold standard in evaluating the generalizability of models in neuroimaging. Unlike typical studies, external validation involves two sample sizes: the training and the external sample sizes. Thus, traditional power calculations may not be appropriate. Here we ran over 900 million resampling-based simulations in functional and structural connectivity data to investigate the relationship between training sample size, external sample size, phenotype effect size, theoretical power and simulated power. Our analysis included a wide range of datasets: the Healthy Brain Network, the Adolescent Brain Cognitive Development Study, the Human Connectome Project (Development and Young Adult), the Philadelphia Neurodevelopmental Cohort, the Queensland Twin Adolescent Brain Project, and the Chinese Human Connectome Project; and phenotypes: age, body mass index, matrix reasoning, working memory, attention problems, anxiety/depression symptoms and relational processing. High effect size predictions achieved adequate power with training and external sample sizes of a few hundred individuals, whereas low and medium effect size predictions required hundreds to thousands of training and external samples. In addition, most previous external validation studies used sample sizes prone to low power, and theoretical power curves should be adjusted for the training sample size. Furthermore, model performance in internal validation often informed subsequent external validation performance (Pearson's r difference <0.2), particularly for well-harmonized datasets. These results could help decide how to power future external validation studies.

Dimensional and Categorical Solutions to Parsing Depression Heterogeneity in a Large Single-Site Sample

BACKGROUND

Recent studies have reported significant advances in modeling the biological basis of heterogeneity in major depressive disorder, but investigators have also identified important technical challenges, including scanner-related artifacts, a propensity for multivariate models to overfit, and a need for larger samples with more extensive clinical phenotyping. The goals of the current study were to evaluate dimensional and categorical solutions to parsing heterogeneity in depression that are stable and generalizable in a large, single-site sample.

METHODS

We used regularized canonical correlation analysis to identify data-driven brain-behavior dimensions that explain individual differences in depression symptom domains in a large, single-site dataset comprising clinical assessments and resting-state functional magnetic resonance imaging data for 328 patients with major depressive disorder and 461 healthy control participants. We examined the stability of clinical loadings and model performance in held-out data. Finally, hierarchical clustering on these dimensions was used to identify categorical depression subtypes.

RESULTS

The optimal regularized canonical correlation analysis model yielded 3 robust and generalizable brain-behavior dimensions that explained individual differences in depressed mood and anxiety, anhedonia, and insomnia. Hierarchical clustering identified 4 depression subtypes, each with distinct clinical symptom profiles, abnormal resting-state functional connectivity patterns, and antidepressant responsiveness to repetitive transcranial magnetic stimulation.

CONCLUSIONS

Our results define dimensional and categorical solutions to parsing neurobiological heterogeneity in major depressive disorder that are stable, generalizable, and capable of predicting treatment outcomes, each with distinct advantages in different contexts. They also provide additional evidence that regularized canonical correlation analysis and hierarchical clustering are effective tools for investigating associations between functional connectivity and clinical symptoms.

Neuroticism/Negative Emotionality Is Associated with Increased Reactivity to Uncertain Threat in the Bed Nucleus of the Stria Terminalis, Not the Amygdala

Neuroticism/negative emotionality (N/NE)-the tendency to experience anxiety, fear, and other negative emotions-is a fundamental dimension of temperament with profound consequences for health, wealth, and well-being. Elevated N/NE is associated with a panoply of adverse outcomes, from reduced socioeconomic attainment to psychiatric illness. Animal research suggests that N/NE reflects heightened reactivity to uncertain threat in the bed nucleus of the stria terminalis (BST) and central nucleus of the amygdala (Ce), but the relevance of these discoveries to humans has remained unclear. Here we used a novel combination of psychometric, psychophysiological, and neuroimaging approaches to test this hypothesis in an ethnoracially diverse, sex-balanced sample of 220 emerging adults selectively recruited to encompass a broad spectrum of N/NE. Cross-validated robust-regression analyses demonstrated that N/NE is preferentially associated with heightened BST activation during the uncertain anticipation of a genuinely distressing threat (aversive multimodal stimulation), whereas N/NE was unrelated to BST activation during certain-threat anticipation, Ce activation during either type of threat anticipation, or BST/Ce reactivity to threat-related faces. It is often assumed that different threat paradigms are interchangeable assays of individual differences in brain function, yet this has rarely been tested. Our results revealed negligible associations between BST/Ce reactivity to the anticipation of threat and the presentation of threat-related faces, indicating that the two tasks are nonfungible. These observations provide a framework for conceptualizing emotional traits and disorders; for guiding the design and interpretation of biobank and other neuroimaging studies of psychiatric risk, disease, and treatment; and for refining mechanistic research.

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.

Transdiagnostic Mood, Anxiety, and Trauma Symptom Factors in Alcohol Use Disorder: Neural Correlates Across 3 Brain Networks

BACKGROUND

Alcohol use disorder (AUD) is associated with high rates of trauma, mood, and anxiety disorders. Across these diagnoses, individual symptoms substantially overlap, highlighting the need for a transdiagnostic approach. Furthermore, there is limited research on how transdiagnostic psychopathology impacts the neural correlates of AUD. Thus, we aimed to identify symptom factors spanning diagnoses and examine how they relate to the neurocircuitry of addiction.

METHODS

Eighty-six veterans with AUD completed self-report measures and reward, incentive salience, and cognitive control functional magnetic resonance imaging tasks. Factor analysis was performed on self-reported trauma, depression, anxiety, and stress symptoms to obtain transdiagnostic symptom compositions. Neural correlates of a priori-defined regions of interest in the 3 networks were assessed. Independent sample t tests were used to compare the same nodes by DSM-5 diagnosis.

RESULTS

Four symptom factors were identified: Trauma distress, Negative affect, Hyperarousal, and Somatic anxiety. Trauma distress score was associated with increased cognitive control activity during response inhibition (dorsal anterior cingulate cortex). Negative affect was related to lower activation in reward regions (right caudate) but higher activation in cognitive control regions during response inhibition (left dorsolateral prefrontal cortex). Hyperarousal was related to lower reward activity during monetary reward anticipation (left caudate, right caudate). Somatic anxiety was not significantly associated with brain activation. No difference in neural activity was found by posttraumatic stress disorder, major depressive disorder, or generalized anxiety disorder diagnosis.

CONCLUSIONS

These hypothesis-generating findings offer transdiagnostic symptom factors that are differentially associated with neural function and could guide us toward a brain-based classification of psychiatric dysfunction in AUD. Results warrant further investigation of transdiagnostic approaches in addiction.

Placebo treatment affects brain systems related to affective and cognitive processes, but not nociceptive pain

Drug treatments for pain often do not outperform placebo, and a better understanding of placebo mechanisms is needed to improve treatment development and clinical practice. In a large-scale fMRI study (N = 392) with pre-registered analyses, we tested whether placebo analgesic treatment modulates nociceptive processes, and whether its effects generalize from conditioned to unconditioned pain modalities. Placebo treatment caused robust analgesia in conditioned thermal pain that generalized to unconditioned mechanical pain. However, placebo did not decrease pain-related fMRI activity in brain measures linked to nociceptive pain, including the Neurologic Pain Signature (NPS) and spinothalamic pathway regions, with strong support for null effects in Bayes Factor analyses. In addition, surprisingly, placebo increased activity in some spinothalamic regions for unconditioned mechanical pain. In contrast, placebo reduced activity in a neuromarker associated with higher-level contributions to pain, the Stimulus Intensity Independent Pain Signature (SIIPS), and affected activity in brain regions related to motivation and value, in both pain modalities. Individual differences in behavioral analgesia were correlated with neural changes in both modalities. Our results indicate that cognitive and affective processes primarily drive placebo analgesia, and show the potential of neuromarkers for separating treatment influences on nociception from influences on evaluative processes.

An externally validated resting-state brain connectivity signature of pain-related learning

Pain can be conceptualized as a precision signal for reinforcement learning in the brain and alterations in these processes are a hallmark of chronic pain conditions. Investigating individual differences in pain-related learning therefore holds important clinical and translational relevance. Here, we developed and externally validated a novel resting-state brain connectivity-based predictive model of pain-related learning. The pre-registered external validation indicates that the proposed model explains 8-12% of the inter-individual variance in pain-related learning. Model predictions are driven by connections of the amygdala, posterior insula, sensorimotor, frontoparietal, and cerebellar regions, outlining a network commonly described in aversive learning and pain. We propose the resulting model as a robust and highly accessible biomarker candidate for clinical and translational pain research, with promising implications for personalized treatment approaches and with a high potential to advance our understanding of the neural mechanisms of pain-related learning.

Intergenerational transmission of brain structure and function in humans: a narrative review of designs, methods, and findings

Children often show cognitive and affective traits that are similar to their parents. Although this indicates a transmission of phenotypes from parents to children, little is known about the neural underpinnings of that transmission. Here, we provide a general overview of neuroimaging studies that explore the similarity between parents and children in terms of brain structure and function. We notably discuss the aims, designs, and methods of these so-called intergenerational neuroimaging studies, focusing on two main designs: the parent-child design and the multigenerational design. For each design, we also summarize the major findings, identify the sources of variability between studies, and highlight some limitations and future directions. We argue that the lack of consensus in defining the parent-child transmission of brain structure and function leads to measurement heterogeneity, which is a challenge for future studies. Additionally, multigenerational studies often use measures of family resemblance to estimate the proportion of variance attributed to genetic versus environmental factors, though this estimate is likely inflated given the frequent lack of control for shared environment. Nonetheless, intergenerational neuroimaging studies may still have both clinical and theoretical relevance, not because they currently inform about the etiology of neuromarkers, but rather because they may help identify neuromarkers and test hypotheses about neuromarkers coming from more standard neuroimaging designs.

Insomnia Subtypes Have Differentiating Deviations in Brain Structural Connectivity

BACKGROUND

Insomnia disorder is the most common sleep disorder. A better understanding of insomnia-related deviations in the brain could inspire better treatment. Insufficiently recognized heterogeneity within the insomnia population could obscure detection of involved brain circuits. In the current study, we investigated whether structural brain connectivity deviations differed between recently discovered and validated insomnia subtypes.

METHODS

Structural and diffusion-weighted 3T magnetic resonance imaging data from 4 independent studies were harmonized. The sample consisted of 73 control participants without sleep complaints and 204 participants with insomnia who were grouped into 5 insomnia subtypes based on their fingerprint of mood and personality traits assessed with the Insomnia Type Questionnaire. Linear regression correcting for age and sex was used to evaluate group differences in structural connectivity strength, indicated by fractional anisotropy, streamline volume density, and mean diffusivity and evaluated within 3 different atlases.

RESULTS

Insomnia subtypes showed differentiating profiles of deviating structural connectivity that were concentrated in different functional networks. Permutation testing against randomly drawn heterogeneous subsamples indicated significant specificity of deviation profiles in 4 of the 5 subtypes: highly distressed, moderately distressed reward sensitive, slightly distressed low reactive, and slightly distressed high reactive. Connectivity deviation profile significance ranged from p = .001 to p = .049 for different resolutions of brain parcellation and connectivity weight.

CONCLUSIONS

Our results provide an initial indication that different insomnia subtypes exhibit distinct profiles of deviations in structural brain connectivity. Subtyping insomnia may be essential for a better understanding of brain mechanisms that contribute to insomnia vulnerability.

Study design features increase replicability in cross-sectional and longitudinal brain-wide association studies

Brain-wide association studies (BWAS) are a fundamental tool in discovering brain-behavior associations. Several recent studies showed that thousands of study participants are required for good replicability of BWAS because the standardized effect sizes (ESs) are much smaller than the reported standardized ESs in smaller studies. Here, we perform analyses and meta-analyses of a robust effect size index using 63 longitudinal and cross-sectional magnetic resonance imaging studies from the Lifespan Brain Chart Consortium (77,695 total scans) to demonstrate that optimizing study design is critical for increasing standardized ESs and replicability in BWAS. A meta-analysis of brain volume associations with age indicates that BWAS with larger variability in covariate have larger reported standardized ES. In addition, the longitudinal studies we examined reported systematically larger standardized ES than cross-sectional studies. Analyzing age effects on global and regional brain measures from the United Kingdom Biobank and the Alzheimer's Disease Neuroimaging Initiative, we show that modifying longitudinal study design through sampling schemes improves the standardized ESs and replicability. Sampling schemes that improve standardized ESs and replicability include increasing between-subject age variability in the sample and adding a single additional longitudinal measurement per subject. To ensure that our results are generalizable, we further evaluate these longitudinal sampling schemes on cognitive, psychopathology, and demographic associations with structural and functional brain outcome measures in the Adolescent Brain and Cognitive Development dataset. We demonstrate that commonly used longitudinal models can, counterintuitively, reduce standardized ESs and replicability. The benefit of conducting longitudinal studies depends on the strengths of the between- versus within-subject associations of the brain and non-brain measures. Explicitly modeling between- versus within-subject effects avoids averaging the effects and allows optimizing the standardized ESs for each separately. Together, these results provide guidance for study designs that improve the replicability of BWAS.

Leveraging the adolescent brain cognitive development study to improve behavioral prediction from neuroimaging in smaller replication samples

Neuroimaging is a popular method to map brain structural and functional patterns to complex human traits. Recently published observations cast doubt upon these prospects, particularly for prediction of cognitive traits from structural and resting state functional magnetic resonance imaging (MRI). We leverage baseline data from thousands of children in the Adolescent Brain Cognitive DevelopmentSM Study to inform the replication sample size required with univariate and multivariate methods across different imaging modalities to detect reproducible brain-behavior associations. We demonstrate that by applying multivariate methods to high-dimensional brain imaging data, we can capture lower dimensional patterns of structural and functional brain architecture that correlate robustly with cognitive phenotypes and are reproducible with only 41 individuals in the replication sample for working memory-related functional MRI, and ~ 100 subjects for structural and resting state MRI. Even with 100 random re-samplings of 100 subjects in discovery, prediction can be adequately powered with 66 subjects in replication for multivariate prediction of cognition with working memory task functional MRI. These results point to an important role for neuroimaging in translational neurodevelopmental research and showcase how findings in large samples can inform reproducible brain-behavior associations in small sample sizes that are at the heart of many research programs and grants.

Neuromarkers in addiction: definitions, development strategies, and recent advances

Substance use disorders (SUDs) are the most costly and prevalent psychiatric conditions. Recent calls emphasize a need for biomarkers-measurable, stable indicators of normal and abnormal processes and response to treatment or environmental agents-and, in particular, brain-based neuromarkers that will advance understanding of the neurobiological basis of SUDs and clinical practice. To develop neuromarkers, researchers must be grounded in evidence that a putative marker (i) is sensitive and specific to the psychological phenomenon of interest, (ii) constitutes a predictive model, and (iii) generalizes to novel observations (e.g., through internal cross-validation and external application to novel data). These neuromarkers may be used to index risk of developing SUDs (susceptibility), classify individuals with SUDs (diagnostic), assess risk for progression to more severe pathology (prognostic) or index current severity of pathology (monitoring), detect response to treatment (response), and predict individualized treatment outcomes (predictive). Here, we outline guidelines for developing and assessing neuromarkers, we then review recent advances toward neuromarkers in addiction neuroscience centering our discussion around neuromarkers of craving-a core feature of SUDs. In doing so, we specifically focus on the Neurobiological Craving Signature (NCS), which show great promise for meeting the demand of neuromarkers.

Intrinsic functional connectivity of motor and heteromodal association cortex predicts individual differences in regulatory focus

Regulatory focus theory (RFT) describes two cognitive-motivational systems for goal pursuit-the promotion and prevention systems-important for self-regulation and previously implicated in vulnerability to psychopathology. According to RFT, the promotion system is engaged in attaining ideal goals (e.g. hopes and dreams), whereas the prevention system is associated with accomplishing ought goals (e.g. duties and obligations). Prior task-based functional magnetic resonance imaging (fMRI) studies have mostly explored the mapping of these two systems onto the activity of a priori brain regions supporting motivation and executive control in both healthy and depressed adults. However, complex behavioral processes such as those guided by individual differences in regulatory focus are likely supported by widely distributed patterns of intrinsic functional connectivity. We used data-driven connectome-based predictive modeling to identify patterns of distributed whole-brain intrinsic network connectivity associated with individual differences in promotion and prevention system orientation in 1,307 young university volunteers. Our analyses produced a network model predictive of prevention but not promotion orientation, specifically the subjective experience of successful goal pursuit using prevention strategies. The predictive model of prevention success was highlighted by decreased intrinsic functional connectivity of both heteromodal association cortices in the parietal and limbic networks and the primary motor cortex. We discuss these findings in the context of strategic inaction, which drives individuals with a strong dispositional prevention orientation to inhibit their behavioral tendencies in order to shield the self from potential losses, thus maintaining the safety of the status quo but also leading to trade-offs in goal pursuit success.

Reliability and predictability of phenotype information from functional connectivity in large imaging datasets

One of the central objectives of contemporary neuroimaging research is to create predictive models that can disentangle the connection between patterns of functional connectivity across the entire brain and various behavioral traits. Previous studies have shown that models trained to predict behavioral features from the individual's functional connectivity have modest to poor performance. In this study, we trained models that predict observable individual traits (phenotypes) and their corresponding singular value decomposition (SVD) representations - herein referred to as latent phenotypes from resting state functional connectivity. For this task, we predicted phenotypes in two large neuroimaging datasets: the Human Connectome Project (HCP) and the Philadelphia Neurodevelopmental Cohort (PNC). We illustrate the importance of regressing out confounds, which could significantly influence phenotype prediction. Our findings reveal that both phenotypes and their corresponding latent phenotypes yield similar predictive performance. Interestingly, only the first five latent phenotypes were reliably identified, and using just these reliable phenotypes for predicting phenotypes yielded a similar performance to using all latent phenotypes. This suggests that the predictable information is present in the first latent phenotypes, allowing the remainder to be filtered out without any harm in performance. This study sheds light on the intricate relationship between functional connectivity and the predictability and reliability of phenotypic information, with potential implications for enhancing predictive modeling in the realm of neuroimaging research.

Pre-acquired Functional Connectivity Predicts Choice Inconsistency

Economic choice theories usually assume that humans maximize utility in their choices. However, studies have shown that humans make inconsistent choices, leading to suboptimal behavior, even without context-dependent manipulations. Previous studies showed that activation in value and motor networks are associated with inconsistent choices at the moment of choice. Here, we investigated if the neural predispositions, measured before a choice task, can predict choice inconsistency in a later risky choice task. Using functional connectivity (FC) measures from resting-state functional magnetic resonance imaging (rsfMRI), derived before any choice was made, we aimed to predict subjects' inconsistency levels in a later-performed choice task. We hypothesized that rsfMRI FC measures extracted from value and motor brain areas would predict inconsistency. Forty subjects (21 females) completed a rsfMRI scan before performing a risky choice task. We compared models that were trained on FC that included only hypothesized value and motor regions with models trained on whole-brain FC. We found that both model types significantly predicted inconsistency levels. Moreover, even the whole-brain models relied mostly on FC between value and motor areas. For external validation, we used a neural network pretrained on FC matrices of 37,000 subjects and fine-tuned it on our data and again showed significant predictions. Together, this shows that the tendency for choice inconsistency is predicted by predispositions of the nervous system and that synchrony between the motor and value networks plays a crucial role in this tendency.

Complementary benefits of multivariate and hierarchical models for identifying individual differences in cognitive control

Understanding individual differences in cognitive control is a central goal in psychology and neuroscience. Reliably measuring these differences, however, has proven extremely challenging, at least when using standard measures in cognitive neuroscience such as response times or task-based fMRI activity. While prior work has pinpointed the source of the issue - the vast amount of cross-trial variability within these measures - no study has rigorously evaluated potential solutions. Here, we do so with one potential way forward: an analytic framework that combines hierarchical Bayesian modeling with multivariate decoding of trial-level fMRI data. Using this framework and longitudinal data from the Dual Mechanisms of Cognitive Control project, we estimated individuals' neural responses associated with cognitive control within a color-word Stroop task, then assessed the reliability of these individuals' responses across a time interval of several months. We show that in many prefrontal and parietal brain regions, test-retest reliability was near maximal, and that only hierarchical models were able to reveal this state of affairs. Further, when compared to traditional univariate contrasts, multivariate decoding enabled individual-level correlations to be estimated with significantly greater precision. We specifically link these improvements in precision to the optimized suppression of cross-trial variability in decoding. Together, these findings not only indicate that cognitive control-related neural responses individuate people in a highly stable manner across time, but also suggest that integrating hierarchical and multivariate models provides a powerful approach for investigating individual differences in cognitive control, one that can effectively address the issue of high-variability measures.

Whole-brain functional connectivity predicts groupwise and sex-specific tau PET in preclincal Alzheimer's disease

Preclinical Alzheimer's disease, characterized by the initial accumulation of amyloid and tau pathologies without symptoms, presents a critical opportunity for early intervention. Yet, the interplay between these pathological markers and the functional connectome during this window remains understudied. We therefore set out to elucidate the relationship between the functional connectome and amyloid and tau, as assessed by PET imaging, in individuals with preclinical AD using connectome-based predictive modeling (CPM). We found that functional connectivity predicts tau PET, outperforming amyloid PET models. These models were predominantly governed by linear relationships between functional connectivity and tau. Tau models demonstrated a stronger correlation to global connectivity than underlying tau PET. Furthermore, we identify sex-based differences in the ability to predict regional tau, without any underlying differences in tau PET or global connectivity. Taken together, these results suggest tau is more closely coupled to functional connectivity than amyloid in preclinical disease, and that multimodal predictive modeling approaches stand to identify unique relationships that any one modality may be insufficient to discern.

Intersubject representational similarity analysis uncovers the impact of state anxiety on brain activation patterns in the human extrastriate cortex

The current study used functional magnetic resonance imaging (fMRI) and showed that state anxiety modulated extrastriate cortex activity in response to emotionally-charged visual images. State anxiety and neuroimaging data from 53 individuals were subjected to an intersubject representational similarity analysis (ISRSA), wherein the geometries between neural and behavioral data were compared. This analysis identified the extrastriate cortex (fusiform gyrus and area MT) to be the sole regions whose activity patterns covaried with state anxiety. Importantly, we show that this brain-behavior association is revealed when treating state anxiety data as a multidimensional response pattern, rather than a single composite score. This suggests that ISRSA using multivariate distances may be more sensitive in identifying the shared geometries between self-report questionnaires and brain imaging data. Overall, our findings demonstrate that a transient state of anxiety may influence how visual information - especially those relevant to the valence dimension - is processed in the extrastriate cortex.

Parameter Space and Potential for Biomarker Development in 25 Years of fMRI Drug Cue Reactivity: A Systematic Review

Importance

In the last 25 years, functional magnetic resonance imaging drug cue reactivity (FDCR) studies have characterized some core aspects in the neurobiology of drug addiction. However, no FDCR-derived biomarkers have been approved for treatment development or clinical adoption. Traversing this translational gap requires a systematic assessment of the FDCR literature evidence, its heterogeneity, and an evaluation of possible clinical uses of FDCR-derived biomarkers.

Objective

To summarize the state of the field of FDCR, assess their potential for biomarker development, and outline a clear process for biomarker qualification to guide future research and validation efforts.

Evidence Review

The PubMed and Medline databases were searched for every original FDCR investigation published from database inception until December 2022. Collected data covered study design, participant characteristics, FDCR task design, and whether each study provided evidence that might potentially help develop susceptibility, diagnostic, response, prognostic, predictive, or severity biomarkers for 1 or more addictive disorders.

Findings

There were 415 FDCR studies published between 1998 and 2022. Most focused on nicotine (122 [29.6%]), alcohol (120 [29.2%]), or cocaine (46 [11.1%]), and most used visual cues (354 [85.3%]). Together, these studies recruited 19 311 participants, including 13 812 individuals with past or current substance use disorders. Most studies could potentially support biomarker development, including diagnostic (143 [32.7%]), treatment response (141 [32.3%]), severity (84 [19.2%]), prognostic (30 [6.9%]), predictive (25 [5.7%]), monitoring (12 [2.7%]), and susceptibility (2 [0.5%]) biomarkers. A total of 155 interventional studies used FDCR, mostly to investigate pharmacological (67 [43.2%]) or cognitive/behavioral (51 [32.9%]) interventions; 141 studies used FDCR as a response measure, of which 125 (88.7%) reported significant interventional FDCR alterations; and 25 studies used FDCR as an intervention outcome predictor, with 24 (96%) finding significant associations between FDCR markers and treatment outcomes.

Conclusions and Relevance

Based on this systematic review and the proposed biomarker development framework, there is a pathway for the development and regulatory qualification of FDCR-based biomarkers of addiction and recovery. Further validation could support the use of FDCR-derived measures, potentially accelerating treatment development and improving diagnostic, prognostic, and predictive clinical judgments.

Brain Mechanisms Explaining Postural Imbalance in Traumatic Brain Injury: A Systematic Review

Introduction: Persisting imbalance and falls in community-dwelling traumatic brain injury (TBI) survivors are linked to reduced long-term survival. However, a detailed understanding of the impact of TBI upon the brain mechanisms mediating imbalance is lacking. To understand the state of the art concerning the brain mechanisms mediating imbalance in TBI, we performed a systematic review of the literature. Methods: PubMed, Web of Science, and Scopus were searched and peer-reviewed research articles in humans, with any severity of TBI (mild, moderate, severe, or concussion), which linked a postural balance assessment (objective or subjective) with brain imaging (through computed tomography, T1-weighted imaging, functional magnetic resonance imaging [fMRI], resting-state fMRI, diffusion tensor imaging, magnetic resonance spectroscopy, single-photon emission computed tomography, electroencephalography, magnetoencephalography, near-infrared spectroscopy, and evoked potentials) were included. Out of 1940 articles, 60 were retrieved and screened, and 25 articles fulfilling inclusion criteria were included. Results: The most consistent finding was the link between imbalance and the cerebellum; however, the regions within the cerebellum were inconsistent. Discussion: The lack of consistent findings could reflect that imbalance in TBI is due to a widespread brain network dysfunction, as opposed to focal cortical damage. The inconsistency in the reported findings may also be attributed to heterogeneity of methodology, including data analytical techniques, small sample sizes, and choice of control groups. Future studies should include a detailed clinical phenotyping of vestibular function in TBI patients to account for the confounding effect of peripheral vestibular disorders on imbalance and brain imaging.

The future of neuroscience in developmental psychopathology

Developmental psychopathology started as an intersection of fields and is now a field itself. As we contemplate the future of this field, we consider the ways in which a newer, interdisciplinary field - human developmental neuroscience - can inform, and be informed by, developmental psychopathology. To do so, we outline principles of developmental psychopathology and how they are and/or can be implemented in developmental neuroscience. In turn, we highlight how the collaboration between these fields can lead to richer models and more impactful translation. In doing so, we describe the ways in which models from developmental psychopathology can enrich developmental neuroscience and future directions for developmental psychopathology.

In the face of ambiguity: intrinsic brain organization in development predicts one's bias toward positivity or negativity

Exacerbated negativity bias, including in responses to ambiguity, represents a common phenotype of internalizing disorders. Individuals differ in their propensity toward positive or negative appraisals of ambiguity. This variability constitutes one's valence bias, a stable construct linked to mental health. Evidence suggests an initial negativity in response to ambiguity that updates via regulatory processes to support a more positive bias. Previous work implicates the amygdala and prefrontal cortex, and regions of the cingulo-opercular system, in this regulatory process. Nonetheless, the neurodevelopmental origins of valence bias remain unclear. The current study tests whether intrinsic brain organization predicts valence bias among 119 children and adolescents (6 to 17 years). Using whole-brain resting-state functional connectivity, a machine-learning model predicted valence bias (r = 0.20, P = 0.03), as did a model restricted to amygdala and cingulo-opercular system features (r = 0.19, P = 0.04). Disrupting connectivity revealed additional intra-system (e.g. fronto-parietal) and inter-system (e.g. amygdala to cingulo-opercular) connectivity important for prediction. The results highlight top-down control systems and bottom-up perceptual processes that influence valence bias in development. Thus, intrinsic brain organization informs the neurodevelopmental origins of valence bias, and directs future work aimed at explicating related internalizing symptomology.

Structure-Function Interactions in the Hippocampus and Prefrontal Cortex Are Associated with Episodic Memory in Healthy Aging

Aging comes with declines in episodic memory. Memory decline is accompanied by structural and functional alterations within key brain regions, including the hippocampus and lateral prefrontal cortex, as well as their affiliated default and frontoparietal control networks. Most studies have examined how structural or functional differences relate to memory independently. Here we implemented a multimodal, multivariate approach to investigate how interactions between individual differences in structural integrity and functional connectivity relate to episodic memory performance in healthy aging. In a sample of younger (N = 111; mean age, 22.11 years) and older (N = 78; mean age, 67.29 years) adults, we analyzed structural MRI and multiecho resting-state fMRI data. Participants completed measures of list recall (free recall of words from a list), associative memory (cued recall of paired words), and source memory (cued recall of the trial type, or the sensory modality in which a word was presented). The findings revealed that greater structural integrity of the posterior hippocampus and middle frontal gyrus were linked with a pattern of increased within-network connectivity, which together were related to better associative and source memory in older adulthood. Critically, older adults displayed better memory performance in the context of decreased hippocampal volumes when structural differences were accompanied by functional reorganization. This functional reorganization was characterized by a pruning of connections between the hippocampus and the limbic and frontoparietal control networks. Our work provides insight into the neural mechanisms that underlie age-related compensation, revealing that the functional architecture associated with better memory performance in healthy aging is tied to the structural integrity of the hippocampus and prefrontal cortex.

Data leakage inflates prediction performance in connectome-based machine learning models

Predictive modeling is a central technique in neuroimaging to identify brain-behavior relationships and test their generalizability to unseen data. However, data leakage undermines the validity of predictive models by breaching the separation between training and test data. Leakage is always an incorrect practice but still pervasive in machine learning. Understanding its effects on neuroimaging predictive models can inform how leakage affects existing literature. Here, we investigate the effects of five forms of leakage-involving feature selection, covariate correction, and dependence between subjects-on functional and structural connectome-based machine learning models across four datasets and three phenotypes. Leakage via feature selection and repeated subjects drastically inflates prediction performance, whereas other forms of leakage have minor effects. Furthermore, small datasets exacerbate the effects of leakage. Overall, our results illustrate the variable effects of leakage and underscore the importance of avoiding data leakage to improve the validity and reproducibility of predictive modeling.

Sex differences in brain-behavior relationships in the first two years of life

Background

Evidence for sex differences in cognition in childhood is established, but less is known about the underlying neural mechanisms for these differences. Recent findings suggest the existence of brain-behavior relationship heterogeneities during infancy; however, it remains unclear whether sex underlies these heterogeneities during this critical period when sex-related behavioral differences arise.

Methods

A sample of 316 infants was included with resting-state functional magnetic resonance imaging scans at neonate (3 weeks), 1, and 2 years of age. We used multiple linear regression to test interactions between sex and resting-state functional connectivity on behavioral scores of working memory, inhibitory self-control, intelligence, and anxiety collected at 4 years of age.

Results

We found six age-specific, intra-hemispheric connections showing significant and robust sex differences in functional connectivity-behavior relationships. All connections are either with the prefrontal cortex or the temporal pole, which has direct anatomical pathways to the prefrontal cortex. Sex differences in functional connectivity only emerge when associated with behavior, and not in functional connectivity alone. Furthermore, at neonate and 2 years of age, these age-specific connections displayed greater connectivity in males and lower connectivity in females in association with better behavioral scores.

Conclusions

Taken together, we critically capture robust and conserved brain mechanisms that are distinct to sex and are defined by their relationship to behavioral outcomes. Our results establish brain-behavior mechanisms as an important feature in the search for sex differences during development.

Generalizability and Out-of-Sample Predictive Ability of Associations Between Neuromelanin-Sensitive Magnetic Resonance Imaging and Psychosis in Antipsychotic-Free Individuals

Importance

The link between psychosis and dopaminergic dysfunction is established, but no generalizable biomarkers with clear potential for clinical adoption exist.

Objective

To replicate previous findings relating neuromelanin-sensitive magnetic resonance imaging (NM-MRI), a proxy measure of dopamine function, to psychosis severity in antipsychotic-free individuals in the psychosis spectrum and to evaluate the out-of-sample predictive ability of NM-MRI for psychosis severity.

Design, Setting, and Participants

This cross-sectional study recruited participants from 2019 to 2023 in the New York City area (main samples) and Mexico City area (external validation sample). The main samples consisted of 42 antipsychotic-free patients with schizophrenia, 53 antipsychotic-free individuals at clinical high risk for psychosis (CHR), and 52 matched healthy controls. An external validation sample consisted of 16 antipsychotic-naive patients with schizophrenia.

Main Outcomes and Measures

NM-MRI contrast within a subregion of the substantia nigra previously linked to psychosis severity (a priori psychosis region of interest [ROI]) and psychosis severity measured using the Positive and Negative Syndrome Scale (PANSS) in schizophrenia and the Structured Interview for Psychosis-Risk Syndromes (SIPS) in CHR. The cross-validated performance of linear support vector regression to predict psychosis severity across schizophrenia and CHR was assessed, and a final trained model was tested on the external validation sample.

Results

Of the 163 included participants, 76 (46.6%) were female, and the mean (SD) age was 29.2 (10.4) years. In the schizophrenia sample, higher PANSS positive total scores correlated with higher mean NM-MRI contrast in the psychosis ROI (t37 = 2.24, P = .03; partial r = 0.35; 95% CI, 0.05 to 0.55). In the CHR sample, no significant association was found between higher SIPS positive total score and NM-MRI contrast in the psychosis ROI (t48 = -0.55, P = .68; partial r = -0.08; 95% CI, -0.36 to 0.23). The 10-fold cross-validated prediction accuracy of psychosis severity was above chance in held-out test data (mean r = 0.305, P = .01; mean root-mean-square error [RMSE] = 1.001, P = .005). External validation prediction accuracy was also above chance (r = 0.422, P = .046; RMSE = 0.882, P = .047).

Conclusions and Relevance

This study provided a direct ROI-based replication of the in-sample association between NM-MRI contrast and psychosis severity in antipsychotic-free patients with schizophrenia. In turn, it failed to replicate such association in CHR individuals. Most critically, cross-validated machine-learning analyses provided a proof-of-concept demonstration that NM-MRI patterns can be used to predict psychosis severity in new data, suggesting potential for developing clinically useful tools.

Brain-phenotype predictions can survive across diverse real-world data

Recent work suggests that machine learning models predicting psychiatric treatment outcomes based on clinical data may fail when applied to unharmonized samples. Neuroimaging predictive models offer the opportunity to incorporate neurobiological information, which may be more robust to dataset shifts. Yet, among the minority of neuroimaging studies that undertake any form of external validation, there is a notable lack of attention to generalization across dataset-specific idiosyncrasies. 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 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. We demonstrate that reproducible and generalizable brain-behavior associations can be realized across diverse dataset features with sample sizes in the hundreds. Results indicate the potential of functional connectivity-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 neuroimaging predictive models in real-world scenarios and clinical settings.

Machine learning and artificial intelligence in neuroscience: A primer for researchers

Artificial intelligence (AI) is often used to describe the automation of complex tasks that we would attribute intelligence to. Machine learning (ML) is commonly understood as a set of methods used to develop an AI. Both have seen a recent boom in usage, both in scientific and commercial fields. For the scientific community, ML can solve bottle necks created by complex, multi-dimensional data generated, for example, by functional brain imaging or *omics approaches. ML can here identify patterns that could not have been found using traditional statistic approaches. However, ML comes with serious limitations that need to be kept in mind: their tendency to optimise solutions for the input data means it is of crucial importance to externally validate any findings before considering them more than a hypothesis. Their black-box nature implies that their decisions usually cannot be understood, which renders their use in medical decision making problematic and can lead to ethical issues. Here, we present an introduction for the curious to the field of ML/AI. We explain the principles as commonly used methods as well as recent methodological advancements before we discuss risks and what we see as future directions of the field. Finally, we show practical examples of neuroscience to illustrate the use and limitations of ML.

The effects of data leakage on connectome-based machine learning models

Predictive modeling has now become a central technique in neuroimaging to identify complex brain-behavior relationships and test their generalizability to unseen data. However, data leakage, which unintentionally breaches the separation between data used to train and test the model, undermines the validity of predictive models. Previous literature suggests that leakage is generally pervasive in machine learning, but few studies have empirically evaluated the effects of leakage in neuroimaging data. Although leakage is always an incorrect practice, understanding the effects of leakage on neuroimaging predictive models provides insight into the extent to which leakage may affect the literature. Here, we investigated the effects of leakage on machine learning models in two common neuroimaging modalities, functional and structural connectomes. Using over 400 different pipelines spanning four large datasets and three phenotypes, we evaluated five forms of leakage fitting into three broad categories: feature selection, covariate correction, and lack of independence between subjects. As expected, leakage via feature selection and repeated subjects drastically inflated prediction performance. Notably, other forms of leakage had only minor effects (e.g., leaky site correction) or even decreased prediction performance (e.g., leaky covariate regression). In some cases, leakage affected not only prediction performance, but also model coefficients, and thus neurobiological interpretations. Finally, we found that predictive models using small datasets were more sensitive to leakage. Overall, our results illustrate the variable effects of leakage on prediction pipelines and underscore the importance of avoiding data leakage to improve the validity and reproducibility of predictive modeling.

Corticolimbic structural connectivity encapsulates real-world emotional reactivity and happiness

Emotional reactivity to everyday events predicts happiness, but the neural circuits underlying this relationship remain incompletely understood. Here, we combined experience sampling methods and diffusion magnetic resonance imaging to examine the association among corticolimbic structural connectivity, real-world emotional reactivity and daily experiences of happiness from 79 young adults (35 females). Participants recorded momentary assessments of emotional and happiness experiences five times a day for a week, approximately 2 weeks after brain scanning. Model-based emotional reactivity scores, which index the degree to which moment-to-moment affective state varies with the occurrence of positive or negative events, were computed. Results showed that stronger microstructural integrity of the uncinate fasciculus and the external capsule was associated with both greater positive and negative emotional reactivity scores. The relationship between these fiber tracts and experienced happiness was explained by emotional reactivity. Importantly, this indirect effect was observed for emotional reactivity to positive but not negative real-world events. Our findings suggest that the corticolimbic circuits supporting socioemotional functions are associated with emotional reactivity and happiness in the real world.

Brain morphology predicts individual sensitivity to pain: a multicenter machine learning approach

ABSTRACT

Sensitivity to pain shows a remarkable interindividual variance that has been reported to both forecast and accompany various clinical pain conditions. Although pain thresholds have been reported to be associated to brain morphology, it is still unclear how well these findings replicate in independent data and whether they are powerful enough to provide reliable pain sensitivity predictions on the individual level. In this study, we constructed a predictive model of pain sensitivity (as measured with pain thresholds) using structural magnetic resonance imaging-based cortical thickness data from a multicentre data set (3 centres and 131 healthy participants). Cross-validated estimates revealed a statistically significant and clinically relevant predictive performance (Pearson r = 0.36, P < 0.0002, R2 = 0.13). The predictions were found to be specific to physical pain thresholds and not biased towards potential confounding effects (eg, anxiety, stress, depression, centre effects, and pain self-evaluation). Analysis of model coefficients suggests that the most robust cortical thickness predictors of pain sensitivity are the right rostral anterior cingulate gyrus, left parahippocampal gyrus, and left temporal pole. Cortical thickness in these regions was negatively correlated to pain sensitivity. Our results can be considered as a proof-of-concept for the capacity of brain morphology to predict pain sensitivity, paving the way towards future multimodal brain-based biomarkers of pain.

Power and reproducibility in the external validation of brain-phenotype predictions

Identifying reproducible and generalizable brain-phenotype associations is a central goal of neuroimaging. Consistent with this goal, prediction frameworks evaluate brain-phenotype models in unseen data. Most prediction studies train and evaluate a model in the same dataset. However, external validation, or the evaluation of a model in an external dataset, provides a better assessment of robustness and generalizability. Despite the promise of external validation and calls for its usage, the statistical power of such studies has yet to be investigated. In this work, we ran over 60 million simulations across several datasets, phenotypes, and sample sizes to better understand how the sizes of the training and external datasets affect statistical power. We found that prior external validation studies used sample sizes prone to low power, which may lead to false negatives and effect size inflation. Furthermore, increases in the external sample size led to increased simulated power directly following theoretical power curves, whereas changes in the training dataset size offset the simulated power curves. Finally, we compared the performance of a model within a dataset to the external performance. The within-dataset performance was typically within r=0.2 of the cross-dataset performance, which could help decide how to power future external validation studies. Overall, our results illustrate the importance of considering the sample sizes of both the training and external datasets when performing external validation.

Leveraging the Adolescent Brain Cognitive Development Study to improve behavioral prediction from neuroimaging in smaller replication samples

Magnetic resonance imaging (MRI) is a popular and useful non-invasive method to map patterns of brain structure and function to complex human traits. Recently published observations in multiple large scale studies cast doubt upon these prospects, particularly for prediction of cognitive traits from structural and resting state functional MRI, which seems to account for little behavioral variability. We leverage baseline data from thousands of children in the Adolescent Brain Cognitive DevelopmentSM (ABCD®) Study to inform the replication sample size required with both univariate and multivariate methods across different imaging modalities to detect reproducible brain-behavior associations. We demonstrate that by applying multivariate methods to high-dimensional brain imaging data, we can capture lower dimensional patterns of structural and functional brain architecture that correlate robustly with cognitive phenotypes and are reproducible with only 41 individuals in the replication sample for working memory-related functional MRI, and ~100 subjects for structural MRI. Even with 100 random re-samplings of 50 subjects in the discovery sample, prediction can be adequately powered with 98 subjects in the replication sample for multivariate prediction of cognition with working memory task functional MRI. These results point to an important role for neuroimaging in translational neurodevelopmental research and showcase how findings in large samples can inform reproducible brain-behavior associations in small sample sizes that are at the heart of many investigators' research programs and grants.

Placebo effects in osteoarthritis: implications for treatment and drug development

Osteoarthritis (OA) is the most common form of arthritis worldwide, affecting ~500 million people, yet there are no effective treatments to halt its progression. Without any structure-modifying agents, management of OA focuses on ameliorating pain and improving function. Treatment approaches typically have modest efficacy, and many patients have contraindications to recommended pharmacological treatments. Drug development for OA is hindered by the gradual and progressive nature of the disease and the targeting of established disease in clinical trials. Additionally, new medications for OA cannot receive regulatory approval without demonstrating improvements in both structure (pathological features of OA) and symptoms (reduced pain and/or improved function). In clinical trials, people with OA show high 'placebo responses', which hamper the ability to identify new effective treatments. Placebo responses refer to the individual variability in response to placebos given in the context of clinical trials and other settings. Placebo effects refer specifically to short-lasting improvements in symptoms that occur because of physiological changes. To mitigate the effects of the placebo phenomenon, we must first understand what it is, how it manifests, how to identify placebo responders in OA trials and how these insights can be used to improve clinical trials in OA. Leveraging placebo responses and effects in clinical practice might provide additional avenues to augment symptom management of OA.

Functional connectomics in depression: insights into therapies

Depression is a common mental disorder characterized by heterogeneous cognitive and behavioral symptoms. The emerging research paradigm of functional connectomics has provided a quantitative theoretical framework and analytic tools for parsing variations in the organization and function of brain networks in depression. In this review, we first discuss recent progress in depression-associated functional connectome variations. We then discuss treatment-specific brain network outcomes in depression and propose a hypothetical model highlighting the advantages and uniqueness of each treatment in relation to the modulation of specific brain network connectivity and symptoms of depression. Finally, we look to the future promise of combining multiple treatment types in clinical practice, using multisite datasets and multimodal neuroimaging approaches, and identifying biological depression subtypes.

The nature and neurobiology of fear and anxiety: State of the science and opportunities for accelerating discovery

Fear and anxiety play a central role in mammalian life, and there is considerable interest in clarifying their nature, identifying their biological underpinnings, and determining their consequences for health and disease. Here we provide a roundtable discussion on the nature and biological bases of fear- and anxiety-related states, traits, and disorders. The discussants include scientists familiar with a wide variety of populations and a broad spectrum of techniques. The goal of the roundtable was to take stock of the state of the science and provide a roadmap to the next generation of fear and anxiety research. Much of the discussion centered on the key challenges facing the field, the most fruitful avenues for future research, and emerging opportunities for accelerating discovery, with implications for scientists, funders, and other stakeholders. Understanding fear and anxiety is a matter of practical importance. Anxiety disorders are a leading burden on public health and existing treatments are far from curative, underscoring the urgency of developing a deeper understanding of the factors governing threat-related emotions.