Connectome-based models predict attentional control in aging adults

Brain activity during Stroop task performance at age 74 after exposure to the Dutch famine during early gestation

OBJECTIVE

Poorer performance on the Stroop task has been reported after prenatal famine exposure at age 58, potentially indicating cognitive decline. We investigated whether brain activation during Stroop task performance at age 74 differed between individuals exposed to famine prenatally, individuals born before and individuals conceived after the famine.

METHOD

In the Dutch famine birth cohort, we performed a Stroop task fMRI study of individuals exposed (n = 22) or unexposed (born before (n = 18) or conceived after (n = 25)) to famine in early gestation. We studied group differences in task-related mean activation of the dorsolateral prefrontal cortex (DLPFC), anterior cingulate cortex (ACC) and posterior parietal cortex (PPC). Additionally, we explored potential disconnectivity of the DLPFC using psychophysiological interaction analysis.

RESULTS

We observed similar activation patterns in the DLPFC, ACC and PPC in individuals born before and individuals exposed to famine, while individuals conceived after famine had generally higher activation patterns. However, activation patterns were not significantly different between groups. Task-related decreases in connectivity were observed between left DLPFC-left PPC and right DLPFC-right PPC, but were not significantly different between groups.

CONCLUSIONS

Although not statistically significant, the observed patterns of activation may reflect a combined effect of general brain aging and prenatal famine exposure.

Individualized prediction of cognitive test scores from functional brain connectome in patients with first-episode late-life depression

BACKGROUND

In the realm of cognitive screening, the Mini-Mental State Examination (MMSE) and the Montreal Cognitive Assessment (MoCA) are widely utilized for detecting cognitive deficits in patients with late-life depression (LLD), However, the interindividual variability in neuroimaging biomarkers contributing to individual-specific symptom severity remains poorly understood. In this study, we used a connectome-based predictive model (CPM) approach on resting-state functional magnetic resonance imaging data from patients with LLD to establish individualized prediction models for the MoCA and the MMSE scores.

METHODS

We recruited 135 individuals diagnosed with first-episode LLD for this research. Participants underwent the MMSE and MoCA tests, along with resting-state functional magnetic resonance imaging scans. Functional connectivity matrices derived from these scans were utilized in CPM models to predict MMSE or MoCA scores. Predictive precision was assessed by correlating predicted and observed scores, with the significance of prediction performance evaluated through a permutation test.

RESULTS

The negative model of the CPM procedure demonstrated a significant capacity to predict MoCA scores (r = -0.309, p = 0.002). Similarly, the CPM procedure could predict MMSE scores (r = -0.236, p = 0.016). The predictive models for cognitive test scores in LLD primarily involved the visual network, somatomotor network, dorsal attention network, and ventral attention network.

CONCLUSIONS

Brain functional connectivity emerges as a promising predictor of personalized cognitive test scores in LLD, suggesting that functional connectomes are potential neurobiological markers for cognitive performance in patients with LLD.

Behaviorally meaningful functional networks mediate the effect of Alzheimer's pathology on cognition

Tau pathology is associated with cognitive impairment in both aging and Alzheimer's disease, but the functional and structural bases of this relationship remain unclear. We hypothesized that the integrity of behaviorally meaningful functional networks would help explain the relationship between tau and cognitive performance. Using resting state fMRI, we identified unique networks related to episodic memory and executive function cognitive domains. The episodic memory network was particularly related to tau pathology measured with positron emission tomography in the entorhinal and temporal cortices. Further, episodic memory network strength mediated the relationship between tau pathology and cognitive performance above and beyond neurodegeneration. We replicated the association between these networks and tau pathology in a separate cohort of older adults, including both cognitively unimpaired and mildly impaired individuals. Together, these results suggest that behaviorally meaningful functional brain networks represent a functional mechanism linking tau pathology and cognition.

ConnSearch: A framework for functional connectivity analysis designed for interpretability and effectiveness at limited sample sizes

Functional connectivity studies increasingly turn to machine learning methods, which typically involve fitting a connectome-wide classifier, then conducting post hoc interpretation analyses to identify the neural correlates that best predict a dependent variable. However, this traditional analytic paradigm suffers from two main limitations. First, even if classifiers are perfectly accurate, interpretation analyses may not identify all the patterns expressed by a dependent variable. Second, even if classifiers are generalizable, the patterns implicated via interpretation analyses may not replicate. In other words, this traditional approach can yield effective classifiers while falling short of most neuroscientists' goals: pinpointing the neural correlates of dependent variables. We propose a new framework for multivariate analysis, ConnSearch, which involves dividing the connectome into components (e.g., groups of highly connected regions) and fitting an independent model for each component (e.g., a support vector machine or a correlation-based model). Conclusions about the link between a dependent variable and the brain are based on which components yield predictive models rather than on interpretation analysis. We used working memory data from the Human Connectome Project (N = 50-250) to compare ConnSearch with four existing connectome-wide classification/interpretation methods. For each approach, the models attempted to classify examples as being from the high-load or low-load conditions (binary labels). Relative to traditional methods, ConnSearch identified neural correlates that were more comprehensive, had greater consistency with the WM literature, and better replicated across datasets. Hence, ConnSearch is well-positioned to be an effective tool for functional connectivity research.

Using connectome-based models of working memory to predict emotion regulation in older adults

Older adulthood is characterized by enhanced emotional well-being potentially resulting from greater reliance on adaptive emotion regulation strategies. However, not all older adults demonstrate an increase in emotional well-being and instead rely on maladaptive emotion regulation strategies. An important moderator of age-related shifts in strategy preferences is working memory (WM) and its underlying neural circuitry. As such, individual differences in the neural integrity underlying WM may predict older adults' emotion regulation strategy preferences. Our study used whole-brain WM networks-derived from young adults using connectome-based predictive modeling-to predict WM performance and acceptance strategy use in healthy older adults. Older adults (N = 110) completed baseline assessments as part of a randomized controlled trial examining the impact of mind-body interventions on healthy aging. Our results revealed that the WM networks predicted WM accuracy but not acceptance use or difficulties in emotion regulation in older adults. Individual differences in WM performance, but not WM networks, moderated relationships between image intensity and acceptance use. These findings highlight that robust neural markers of WM generalize to an independent sample of healthy older adults but may not generalize beyond cognitive domains to predict emotion-based behaviors.

Connectome-based predictive modeling for functional recovery of acute ischemic stroke

Patients of acute ischemic stroke possess considerable chance of recovery of various levels in the first several weeks after stroke onset. Prognosis of functional recovery is important for decision-making in poststroke patient care and placement. Poststroke functional recovery has conventionally been based on demographic and clinical variables such as age, gender, and severity of stroke impairment. On the other hand, the concept of connectome has become a basis of interpreting the functional impairment and recovery of stroke patients. In this research, the connectome-based predictive modeling was used to provide predictive models for prognosing poststroke functional recovery. Predictive models were developed to use the brain connectivity at stroke onset to predict functional assessment scores at one or three months later, or to use the brain connectivity one-month poststroke to predict functional assessment scores at three months after stroke onset. The brain connectivity was computed from the resting-state fMRI signals. The functional assessment scores used in this research included modified Rankin Scale (mRS) and Barthel Index (BI). This research found significant models that used the brain connectivity at onset to predict the mRS one-month poststroke and to predict the BI three-month poststroke for patients with supratentorial infarction, as well as predictive models that used the brain connectivity one-month poststroke to predict the mRS three-month poststroke for patients with supratentorial infarction in the right hemisphere. The connectome-based predictive modeling could provide clinical value in prognosis of acute ischemic stroke.

Connectome-based predictive modelling of cognitive reserve using task-based functional connectivity

Cognitive reserve supports cognitive function in the presence of pathology or atrophy. Functional neuroimaging may enable direct and accurate measurement of cognitive reserve which could have considerable clinical potential. The present study aimed to develop and validate a measure of cognitive reserve using task-based fMRI data that could then be applied to independent resting-state data. Connectome-based predictive modelling with leave-one-out cross-validation was applied to predict a residual measure of cognitive reserve using task-based functional connectivity from the Cognitive Reserve/Reference Ability Neural Network studies (n = 220, mean age = 51.91 years, SD = 17.04 years). This model generated summary measures of connectivity strength that accurately predicted a residual measure of cognitive reserve in unseen participants. The theoretical validity of these measures was established via a positive correlation with a socio-behavioural proxy of cognitive reserve (verbal intelligence) and a positive correlation with global cognition, independent of brain structure. This fitted model was then applied to external test data: resting-state functional connectivity data from The Irish Longitudinal Study on Ageing (TILDA, n = 294, mean age = 68.3 years, SD = 7.18 years). The network-strength predicted measures were not positively associated with a residual measure of cognitive reserve nor with measures of verbal intelligence and global cognition. The present study demonstrated that task-based functional connectivity data can be used to generate theoretically valid measures of cognitive reserve. Further work is needed to establish if, and how, measures of cognitive reserve derived from task-based functional connectivity can be applied to independent resting-state data.

Classification and prediction of cognitive performance differences in older age based on brain network patterns using a machine learning approach

Age-related cognitive decline varies greatly in healthy older adults, which may partly be explained by differences in the functional architecture of brain networks. Resting-state functional connectivity (RSFC) derived network parameters as widely used markers describing this architecture have even been successfully used to support diagnosis of neurodegenerative diseases. The current study aimed at examining whether these parameters may also be useful in classifying and predicting cognitive performance differences in the normally aging brain by using machine learning (ML). Classifiability and predictability of global and domain-specific cognitive performance differences from nodal and network-level RSFC strength measures were examined in healthy older adults from the 1000BRAINS study (age range: 55-85 years). ML performance was systematically evaluated across different analytic choices in a robust cross-validation scheme. Across these analyses, classification performance did not exceed 60% accuracy for global and domain-specific cognition. Prediction performance was equally low with high mean absolute errors (MAEs ≥ 0.75) and low to none explained variance (R2 ≤ 0.07) for different cognitive targets, feature sets, and pipeline configurations. Current results highlight limited potential of functional network parameters to serve as sole biomarker for cognitive aging and emphasize that predicting cognition from functional network patterns may be challenging.

Differences in the functional brain architecture of sustained attention and working memory in youth and adults

Sustained attention (SA) and working memory (WM) are critical processes, but the brain networks supporting these abilities in development are unknown. We characterized the functional brain architecture of SA and WM in 9- to 11-year-old children and adults. First, we found that adult network predictors of SA generalized to predict individual differences and fluctuations in SA in youth. A WM model predicted WM performance both across and within children-and captured individual differences in later recognition memory-but underperformed in youth relative to adults. We next characterized functional connections differentially related to SA and WM in youth compared to adults. Results revealed 2 network configurations: a dominant architecture predicting performance in both age groups and a secondary architecture, more prominent for WM than SA, predicting performance in each age group differently. Thus, functional connectivity (FC) predicts SA and WM in youth, with networks predicting WM performance differing more between youths and adults than those predicting SA.

Preoperative brain connectome predicts postoperative changes in processing speed in moyamoya disease

Moyamoya disease is a rare cerebrovascular disorder associated with cognitive dysfunction. It is usually treated by surgical revascularization, but research on the neurocognitive outcomes of revascularization surgery is controversial. Given that neurocognitive impairment could affect the daily activities of patients with moyamoya disease, early detection of postoperative neurocognitive outcomes has the potential to improve patient management. In this study, we applied a well-established connectome-based predictive modelling approach to develop machine learning models that used preoperative resting-state functional connectivity to predict postoperative changes in processing speed in patients with moyamoya disease. Twelve adult patients with moyamoya disease (age range: 23–49 years; female/male: 9/3) were recruited prior to surgery and underwent follow-up at 1 and 6 months after surgery. Twenty healthy controls (age range: 24–54 years; female/male: 14/6) were recruited and completed the behavioural test at baseline, 1-month follow-up and 6-month follow-up. Behavioural results indicated that the behavioural changes in processing speed at 1 and 6 months after surgery compared with baseline were not significant. Importantly, we showed that preoperative resting-state functional connectivity significantly predicted postoperative changes in processing speed at 1 month after surgery (negative network: ρ = 0.63, P_corr = 0.017) and 6 months after surgery (positive network: ρ = 0.62, P_corr = 0.010; negative network: ρ = 0.55, P_corr = 0.010). We also identified cerebro-cerebellar and cortico-subcortical connectivities that were consistently associated with processing speed. The brain regions identified from our predictive models are not only consistent with previous studies but also extend previous findings by revealing their potential roles in postoperative neurocognitive functions in patients with moyamoya disease. Taken together, our findings provide preliminary evidence that preoperative resting-state functional connectivity might predict the post-surgical longitudinal neurocognitive changes in patients with moyamoya disease. Given that processing speed is a crucial cognitive ability supporting higher neurocognitive functions, this study’s findings offer important insight into the clinical management of patients with moyamoya disease.

Protocol for a randomized controlled trial of mindfulness-based stress reduction to improve attentional control in older adults (HealthyAgers trial)

BACKGROUND

Mindfulness meditation is a form of mind-body intervention that has increasing scientific support for its ability to reduce age-related declines in cognitive functioning, improve affective health, and strengthen the neural circuitry supporting improved cognitive and affective health. However, the majority of existent studies have been pilot investigations with small sample sizes, limited follow-up data, and a lack of attention to expectancy effects. Here, we present the study design of a Phase I/II, efficacy trial-HealthyAgers trial-that examines the benefits of a manualized mindfulness-based stress reduction program in improving attentional control and reducing mind-wandering in older adults.

METHODS

One hundred fifty older adults (ages 65-85 years) will be randomized into one of two groups: an eight-week mindfulness program or an eight-week, placebo-controlled, lifestyle education program. Behavioral and neuroimaging assessments are conducted before and after the training. Participants are then invited to booster sessions once every three months for a period of 12 months with post-intervention follow-up assessments conducted at 6-months and 12-months. The primary outcomes for the study are behavioral measures of attentional control and mind-wandering. Additional, secondary outcomes include network strength in an a priori defined neuromarker of attentional control, fluid and everyday cognition, emotion regulation strategy use, and markers of inflammation.

DISCUSSION

This study will establish the efficacy of a group-based, low-cost mind-body intervention for the inter-related facets of attentional control and mind-wandering in older adults. Strengths of this study include a well-designed, placebo-controlled comparison group, use of web/mobile application to track study adherence, and longitudinal follow-up.

TRIAL REGISTRATION

Clinicaltrials.gov (# NCT03626532 ). Registered August 4, 2018.

Connectome-based predictive models using resting-state fMRI for studying brain aging

Changes in the brain with age can provide useful information regarding an individual's chronological age. studies have suggested that functional connectomes identified via resting-state functional magnetic resonance imaging (fMRI) could be a powerful feature for predicting an individual's age. We applied connectome-based predictive modeling (CPM) to investigate individual chronological age predictions via resting-state fMRI using open-source datasets. The significant feature for age prediction was confirmed in 168 subjects from the Southwest University Adult Lifespan Dataset. The higher contributing nodes for age production included a positive connection from the left inferior parietal sulcus and a negative connection from the right middle temporal sulcus. On the network scale, the subcortical-cerebellum network was the dominant network for age prediction. The generalizability of CPM, which was constructed using the identified features, was verified by applying this model to independent datasets that were randomly selected from the Autism Brain Imaging Data Exchange I and the Open Access Series of Imaging Studies 3. CPM via resting-state fMRI is a potential robust predictor for determining an individual's chronological age from changes in the brain.

Employing Connectome-Based Models to Predict Working Memory in Multiple Sclerosis

Introduction: Individuals with multiple sclerosis (MS) are vulnerable to deficits in working memory (WM), but the search for neural correlates of WM within circumscribed areas has been inconclusive. Given the widespread neural alterations observed in MS, predictive modeling approaches that capitalize on whole-brain connectivity may better capture individual differences in WM. Materials and Methods: We applied connectome-based predictive modeling to functional magnetic resonance imaging data from WM tasks in two independent samples with relapsing-remitting MS. In the internal sample (n_internal = 36), cross-validation was used to train a model to predict accuracy on the Paced Visual Serial Addition Test from functional connectivity. We hypothesized that this MS-specific model would successfully predict performance on the N-back task in the validation cohort (n_validation = 36). In addition, we assessed the generalizability of existing WM networks derived in healthy young adults to these samples, and we explored anatomical differences between the healthy and MS networks. Results: We successfully derived an MS-specific predictive model of WM in the internal sample (full: r_s = 0.47, permuted p = 0.011), but the predictions were not significant in the validation cohort (r_s = -0.047; p = 0.78, mean squared error [MSE] = 0.006, R² = -2.21%). In contrast, the healthy networks successfully predicted WM in both MS samples (internal: r_s = 0.33 p = 0.049, MSE = 0.009, R² = 13.4%; validation cohort: r_s = 0.46, p = 0.005, MSE = 0.005, R² = 16.9%), demonstrating their translational potential. Discussion: Functional networks identified in a large sample of healthy individuals predicted significant variance in WM in MS. Networks derived in small samples of people with MS may have limited generalizability, potentially due to disease-related heterogeneity. The robustness of models derived in large clinical samples warrants further investigation. ClinicalTrials.gov ID: NCT03244696.

A brain-based general measure of attention

Attention is central to many aspects of cognition, but there is no singular neural measure of a person's overall attentional functioning across tasks. Here, using original data from 92 participants performing three different attention-demanding tasks during functional magnetic resonance imaging, we constructed a suite of whole-brain models that can predict a profile of multiple attentional components (sustained attention, divided attention and tracking, and working memory capacity) for novel individuals. Multiple brain regions across the salience, subcortical and frontoparietal networks drove accurate predictions, supporting a common (general) attention factor across tasks, distinguished from task-specific ones. Furthermore, connectome-to-connectome transformation modelling generated an individual's task-related connectomes from rest functional magnetic resonance imaging, substantially improving predictive power. Finally, combining the connectome transformation and general attention factor, we built a standardized measure that shows superior generalization across four independent datasets (total N = 495) of various attentional measures, suggesting broad utility for research and clinical applications.

Methodological evaluation of individual cognitive prediction based on the brain white matter structural connectome

An emerging trend is to use regression‐based machine learning approaches to predict cognitive functions at the individual level from neuroimaging data. However, individual prediction models are inherently influenced by the vast options for network construction and model selection in machine learning pipelines. In particular, the brain white matter (WM) structural connectome lacks a systematic evaluation of the effects of different options in the pipeline on predictive performance. Here, we focused on the methodological evaluation of brain structural connectome‐based predictions. For network construction, we considered two parcellation schemes for defining nodes and seven strategies for defining edges. For the regression algorithms, we used eight regression models. Four cognitive domains and brain age were targeted as predictive tasks based on two independent datasets (Beijing Aging Brain Rejuvenation Initiative [BABRI]: 633 healthy older adults; Human Connectome Projects in Aging [HCP‐A]: 560 healthy older adults). Based on the results, the WM structural connectome provided a satisfying predictive ability for individual age and cognitive functions, especially for executive function and attention. Second, different parcellation schemes induce a significant difference in predictive performance. Third, prediction results from different data sets showed that dMRI with distinct acquisition parameters may plausibly result in a preference for proper fiber reconstruction algorithms and different weighting options. Finally, deep learning and Elastic‐Net models are more accurate and robust in connectome‐based predictions. Together, significant effects of different options in WM network construction and regression algorithms on the predictive performances are identified in this study, which may provide important references and guidelines to select suitable options for future studies in this field.

Age-specificity and generalization of behavior-associated structural and functional networks and their relevance to behavioral domains

Behavior-associated structural connectivity (SC) and resting-state functional connectivity (rsFC) networks undergo various changes in aging. To study these changes, we proposed a continuous dimension where at one end networks generalize well across age groups in terms of behavioral predictions (age-general) and at the other end, they predict behaviors well in a specific age group but fare poorly in another age group (age-specific). We examined how age generalizability/specificity of multimodal behavioral associated brain networks varies across behavioral domains and imaging modalities. Prediction models consisting of SC and/or rsFC networks were trained to predict a diverse range of 75 behavioral outcomes in a young adult sample (N = 92). These models were then used to predict behavioral outcomes in unseen young (N = 60) and old (N = 60) subjects. As expected, behavioral prediction models derived from the young age group, produced more accurate predictions in the unseen young than old subjects. These behavioral predictions also differed significantly across behavioral domains, but not imaging modalities. Networks associated with cognitive functions, except for a few mostly relating to semantic knowledge, fell toward the age-specific end of the spectrum (i.e., poor young-to-old generalizability). These findings suggest behavior-associated brain networks are malleable to different degrees in aging; such malleability is partly determined by the nature of the behavior.

Intrinsic functional connectivity in the default mode network predicts mnemonic discrimination: A connectome-based modeling approach

The ability to distinguish existing memories from similar perceptual experiences is a core feature of episodic memory. This ability is often examined using the mnemonic similarity task in which people discriminate memories of studied objects from perceptually similar lures. Studies of the neural basis of such mnemonic discrimination have mostly focused on hippocampal function and connectivity. However, default mode network (DMN) connectivity may also support such discrimination, given that the DMN includes the hippocampus, and its connectivity supports many aspects of episodic memory. Here, we used connectome-based predictive modeling to identify associations between intrinsic DMN connectivity and mnemonic discrimination. We leveraged a wide range of abilities across healthy younger and older adults to facilitate this predictive approach. Resting-state functional connectivity in the DMN predicted mnemonic discrimination outside the MRI scanner, especially among prefrontal and temporal regions and including several hippocampal regions. This predictive relationship was stronger for younger than older adults, primarily for temporal-prefrontal connectivity. The novel associations established here are consistent with mounting evidence that broader cortical networks including the hippocampus support mnemonic discrimination. They also suggest that age-related network disruptions undermine the extent that the DMN supports this ability. This study provides the first indication of how intrinsic functional properties of the DMN support mnemonic discrimination.

Predicting the retinotopic organization of human visual cortex from anatomy using geometric deep learning

Whether it be in a single neuron or a more complex biological system like the human brain, form and function are often directly related. The functional organization of human visual cortex, for instance, is tightly coupled with the underlying anatomy with cortical shape having been shown to be a useful predictor of the retinotopic organization in early visual cortex. Although the current state-of-the-art in predicting retinotopic maps is able to account for gross individual differences, such models are unable to account for any idiosyncratic differences in the structure-function relationship from anatomical information alone due to their initial assumption of a template. Here we developed a geometric deep learning model capable of exploiting the actual structure of the cortex to learn the complex relationship between brain function and anatomy in human visual cortex such that more realistic and idiosyncratic maps could be predicted. We show that our neural network was not only able to predict the functional organization throughout the visual cortical hierarchy, but that it was also able to predict nuanced variations across individuals. Although we demonstrate its utility for modeling the relationship between structure and function in human visual cortex, our approach is flexible and well-suited for a range of other applications involving data structured in non-Euclidean spaces.

Social Robots for Evaluating Attention State in Older Adults

Sustained attention is essential for older adults to maintain an active lifestyle, and the deficiency of this function is often associated with health-related risks such as falling and frailty. The present study examined whether the well-established age-effect on reducing mind-wandering, the drift to internal thoughts that are seen to be detrimental to attentional control, could be replicated by using a robotic experimenter for older adults who are not as familiar with online technologies. A total of 28 younger and 22 older adults performed a Sustained Attention to Response Task (SART) by answering thought probes regarding their attention states and providing confidence ratings for their own task performances. The indices from the modified SART suggested a well-documented conservative response strategy endorsed by older adults, which were represented by slower responses and increased omission errors. Moreover, the slower responses and increased omissions were found to be associated with less self-reported mind-wandering, thus showing consistency with their higher subjective ratings of attentional control. Overall, this study demonstrates the potential of constructing age-related cognitive profiles with attention evaluation instruction based on a social companion robot for older adults at home.

Mindfulness Meditation: Impact on Attentional Control and Emotion Dysregulation

OBJECTIVE

Theoretical models of mindfulness meditation conceptualize the cultivation of focused attention and regulation of emotional states, with the attitudinal foundations that promote nonjudgment and acceptance, to facilitate cognitive and affective processing resulting in improved brain health. Within the scientific study of mindfulness meditation, outcomes assessing behavioral and neural correlates of attentional control and emotion regulation have been examined for their malleability as a function of engagement in mindfulness practices. This review synthesizes the results of our pilot trials examining the preliminary effects of mindfulness meditation on metrics of cognitive, affective, and brain health in older adults and in individuals with multiple sclerosis.

CONCLUSIONS

There is promising support for mindfulness meditation to enhance attentional control, reduce mind-wandering, and reduce emotion dysregulation. However, well-powered efficacy trials, with an objective assessment of mindfulness practice data are needed to further provide causal and comprehensive evidence supporting the efficacy of mindfulness meditation for brain health. Inclusion of independently derived and validated brain-based signatures of cognitive and affective functioning can additionally enable a parsimonious understanding of how mindfulness meditation can causally impact metrics of functional and structural integrity of the human brain.

Distributed functional connectivity predicts neuropsychological test performance among older adults

Neuropsychological test is an essential tool in assessing cognitive and functional changes associated with late-life neurocognitive disorders. Despite the utility of the neuropsychological test, the brain-wide neural basis of the test performance remains unclear. Using the predictive modeling approach, we aimed to identify the optimal combination of functional connectivities that predicts neuropsychological test scores of novel individuals. Resting-state functional connectivity and neuropsychological tests included in the OASIS-3 dataset (n = 428) were used to train the predictive models, and the identified models were iteratively applied to the holdout internal test set (n = 216) and external test set (KSHAP, n = 151). We found that the connectivity-based predicted score tracked the actual behavioral test scores (r = 0.08-0.44). The predictive models utilizing most of the connectivity features showed better accuracy than those composed of focal connectivity features, suggesting that its neural basis is largely distributed across multiple brain systems. The discriminant and clinical validity of the predictive models were further assessed. Our results suggest that late-life neuropsychological test performance can be formally characterized with distributed connectome-based predictive models, and further translational evidence is needed when developing theoretically valid and clinically incremental predictive models.

Memory Suppression Ability can be Robustly Predicted by the Internetwork Communication of Frontoparietal Control Network

Memory suppression (MS) is essential for mental well-being. However, no studies have explored how intrinsic resting-state functional connectivity (rs-FC) predicts this ability. Here, we adopted the connectome-based predictive modeling (CPM) based on the resting-state fMRI data to investigate whether and how rs-FC profiles in predefined brain networks (the frontoparietal control networks or FPCN) can predict MS in healthy individuals with 497 participants. The MS ability was assessed by MS-induced forgetting during the think/no-think paradigm. The results showed that FPCN network was especially informative for generating the prediction model for MS. Some regions of FPCN, such as middle frontal gyrus, superior frontal gyrus and inferior parietal lobe were critical in predicting MS. Moreover, functional interplay between FPCN and multiple networks, such as dorsal attention network (DAN), ventral attention network (VAN), default mode network (DMN), the limbic system and subcortical regions, enabled prediction of MS. Crucially, the predictive FPCN networks were stable and specific to MS. These results indicated that FPCN flexibility interacts with other networks to underpin the ability of MS. These would also be beneficial for understanding how compromises in these functional networks may have led to the intrusive thoughts and memories characterized in some mental disorders.

Connectome-based model predicts episodic memory performance in individuals with subjective cognitive decline and amnestic mild cognitive impairment

OBJECTIVE

To explore whether the whole brain resting-state functional connectivity (rs-FC) could predict episodic memory performance in individuals with subjective cognitive decline and amnestic mild cognitive impairment.

METHOD

This study included 33 cognitive normal (CN), 26 subjective cognitive decline (SCD) and 27 amnestic mild cognitive impairment (aMCI) patients, and all the participants completed resting-state fMRI (rs-fMRI) scan and neuropsychological scale test data. Connectome-based predictive modeling (CPM) based on the rs-FC data was used to predict the auditory verbal learning test-delayed recall (AVLT-DR) scores, which measured episodic memory in individuals. Pearson correlation between each brain connection in the connectivity matrices and AVLT-DR scores was computed across the patients in predementia stages of Alzheimer's disease (AD). The Pearson correlation coefficient values separated into a positive network and a negative network. Predictive networks were then defined and employed by calculating positive and negative network strengths. CPM with leave-one-out cross-validation (LOOCV) was conducted to train linear models to respectively relate positive and negative network strengths to AVLT-DR scores in the training set. During the testing procedure, each left-out testing subject's strengths of positive and negative network was normalized using the parameters acquired during training procedure, and then the trained models were used to predict the testing participant's AVLT-DR score.

RESULTS

The negative network predictive model tested LOOCV significantly predicted individual differences in episodic memory from rs-FC. Key nodes that brain regions contributed to the prediction model were mainly located in the prefrontal cortex, frontal cortex, parietal cortex and temporal lobe.

CONCLUSION

Our findings demonstrated that rs-FC among multiple neural systems could predict episodic memory at the individual level.

Connectome-based prediction of global cognitive performance in people with HIV

•

Networks strengths predicted global cognitive performance in PWH.

•

Model generalized to data from an independent PWH sample.

•

Network strengths in PWH with HAND were different from either controls or PWH without HAND.

•

Network strengths may serve as a potential biomarker to assist HAND diagnosis.

Global cognitive performance plays an important role in the diagnosis of HIV-associated neurocognitive disorders (HAND), yet to date, there is no simple way to measure global cognitive performance in people with HIV (PWH). Here, we performed connectome-based predictive modeling (CPM) to pursue a neural biomarker of global cognitive performance in PWH based on whole-brain resting-state functional connectivity. We built a CPM model that successfully predicted individual differences in global cognitive performance in the training set of 67 PWH by using leave-one-out cross-validation. This model generalized to both 33 novel PWH in the testing set and a subset of 39 PWH who completed a follow-up visit two years later. Furthermore, network strengths identified by the CPM model were significantly different between PWH with HAND and without HAND. Together, these results demonstrate that whole-brain functional network strengths could serve as a potential neural biomarker of global cognitive performance in PWH.

The functional connectome predicts feeling of stress on regular days and during the COVID-19 pandemic

Although many studies have explored the neural mechanism of the feeling of stress, to date, no effort has been made to establish a model capable of predicting the feeling of stress at the individual level using the resting-state functional connectome. Although individuals may be confronted with multidimensional stressors during the coronavirus disease 2019 (COVID-19) pandemic, their appraisal of the impact and severity of these events might vary. In this study, connectome-based predictive modeling (CPM) with leave-one-out cross-validation was conducted to predict individual perceived stress (PS) from whole-brain functional connectivity data from 817 participants. The results showed that the feeling of stress could be predicted by the interaction between the default model network and salience network, which are involved in emotion regulation and salience attribution, respectively. Key nodes that contributed to the prediction model comprised regions mainly located in the limbic systems and temporal lobe. Critically, the CPM model of PS based on regular days can be generalized to predict individual PS levels during the COVID-19 pandemic, which is a multidimensional, uncontrollable stressful situation. The stability of the results was demonstrated by two independent datasets. The present work not only expands existing knowledge regarding the neural mechanism of PS but also may help identify high-risk individuals in healthy populations.

•

Perceived stress (PS) can be predicated by resting-state functional connectome.

•

PS can be predicated by interaction between default model and salience network.

•

Key nodes of the prediction model located in limbic systems and temporal lobe.

•

psCPM of regular days generalized to predict PS level in the COVID-19 pandemic.

Connectome-based models can predict processing speed in older adults

Decrement in processing speed (PS) is a primary cognitive morbidity in clinical populations and could significantly influence other cognitive functions, such as attention and memory. Verifying the usefulness of connectome-based models for predicting neurocognitive abilities has significant translational implications on clinical and aging research. In this study, we verified that resting-state functional connectivity could be used to predict PS in 99 older adults by using connectome-based predictive modeling (CPM). We identified two distinct connectome patterns across the whole brain: the fast-PS and slow-PS networks. Relative to the slow-PS network, the fast-PS network showed more within-network connectivity in the motor and visual networks and less between-network connectivity in the motor-visual, motor-subcortical/cerebellum and motor-frontoparietal networks. We further verified that the connectivity patterns for prediction of PS were also useful for predicting attention and memory in the same sample. To test the generalizability and specificity of the connectome-based predictive models, we applied these two connectome models to an independent sample of three age groups (101 younger adults, 103 middle-aged adults and 91 older adults) and confirmed these models could specifically be generalized to predict PS of the older adults, but not the younger and middle-aged adults. Taking all the findings together, the identified connectome-based predictive models are strong for predicting PS in older adults. The application of CPM to predict neurocognitive abilities can complement conventional neurocognitive assessments, bring significant clinical benefits to patient management and aid the clinical diagnoses, prognoses and management of people undergoing the aging process.

Neuroimaging-based Individualized Prediction of Cognition and Behavior for Mental Disorders and Health: Methods and Promises

The neuroimaging community has witnessed a paradigm shift in biomarker discovery from using traditional univariate brain mapping approaches to multivariate predictive models, allowing the field to move toward a translational neuroscience era. Regression-based multivariate models (hereafter "predictive modeling") provide a powerful and widely used approach to predict human behavior with neuroimaging features. These studies maintain a focus on decoding individual differences in a continuously behavioral phenotype from neuroimaging data, opening up an exciting opportunity to describe the human brain at the single-subject level. In this survey, we provide an overview of recent studies that utilize machine learning approaches to identify neuroimaging predictors over the past decade. We first review regression-based approaches and highlight connectome-based predictive modeling, which has grown in popularity in recent years. Next, we systematically describe recent representative studies using these tools in the context of cognitive function, symptom severity, personality traits, and emotion processing. Finally, we highlight a few challenges related to combining multimodal data, longitudinal prediction, external validations, and the employment of deep learning methods that have emerged from our review of the existing literature, as well as present some promising and challenging future directions.

Predicting dysfunctional age-related task activations from resting-state network alterations

Alzheimer's disease (AD) is linked to changes in fMRI task activations and fMRI resting-state functional connectivity (restFC), which can emerge early in the illness timecourse. These fMRI correlates of unhealthy aging have been studied in largely separate subfields. Taking inspiration from neural network simulations, we propose a unifying mechanism wherein restFC alterations associated with AD disrupt the flow of activations between brain regions, leading to aberrant task activations. We apply this activity flow model in a large sample of clinically normal older adults, which was segregated into healthy (low-risk) and at-risk subgroups based on established imaging (positron emission tomography amyloid) and genetic (apolipoprotein) AD risk factors. Modeling the flow of healthy activations over at-risk AD connectivity effectively transformed the healthy aged activations into unhealthy (at-risk) aged activations. This enabled reliable prediction of at-risk AD task activations, and these predicted activations were related to individual differences in task behavior. These results support activity flow over altered intrinsic functional connections as a mechanism underlying Alzheimer's-related dysfunction, even in very early stages of the illness. Beyond these mechanistic insights, this approach raises clinical potential by enabling prediction of task activations and associated cognitive dysfunction in individuals without requiring them to perform in-scanner cognitive tasks.

Network connectivity predicts language processing in healthy adults

Brain imaging has been used to predict language skills during development and neuropathology but its accuracy in predicting language performance in healthy adults has been poorly investigated. To address this shortcoming, we studied the ability to predict reading accuracy and single‐word comprehension scores from rest‐ and task‐based functional magnetic resonance imaging (fMRI) datasets of 424 healthy adults. Using connectome‐based predictive modeling, we identified functional brain networks with >400 edges that predicted language scores and were reproducible in independent data sets. To simplify these complex models we identified the overlapping edges derived from the three task‐fMRI sessions (language, working memory, and motor tasks), and found 12 edges for reading recognition and 11 edges for vocabulary comprehension that accounted for 20% of the variance of these scores, both in the training sample and in the independent sample. The overlapping edges predominantly emanated from language areas within the frontoparietal and default‐mode networks, with a strong precuneus prominence. These findings identify a small subset of edges that accounted for a significant fraction of the variance in language performance that might serve as neuromarkers for neuromodulation interventions to improve language performance or for presurgical planning to minimize language impairments.

Functional connectivity predicts changes in attention observed across minutes, days, and months

The ability to sustain attention differs across people and changes within a single person over time. Although recent work has demonstrated that patterns of functional brain connectivity predict individual differences in sustained attention, whether these same patterns capture fluctuations in attention within individuals remains unclear. Here, across five independent studies, we demonstrate that the sustained attention connectome-based predictive model (CPM), a validated model of sustained attention function, generalizes to predict attentional state from data collected across minutes, days, weeks, and months. Furthermore, the sustained attention CPM is sensitive to within-subject state changes induced by propofol as well as sevoflurane, such that individuals show functional connectivity signatures of stronger attentional states when awake than when under deep sedation and light anesthesia. Together, these results demonstrate that fluctuations in attentional state reflect variability in the same functional connectivity patterns that predict individual differences in sustained attention.

Distributed Patterns of Functional Connectivity Predict Working Memory Performance in Novel Healthy and Memory-impaired Individuals

Individual differences in working memory relate to performance differences in general cognitive ability. The neural bases of such individual differences, however, remain poorly understood. Here, using a data-driven technique known as connectome-based predictive modeling, we built models to predict individual working memory performance from whole-brain functional connectivity patterns. Using n-back or rest data from the Human Connectome Project, connectome-based predictive models significantly predicted novel individuals' 2-back accuracy. Model predictions also correlated with measures of fluid intelligence and, with less strength, sustained attention. Separate fluid intelligence models predicted working memory score, as did sustained attention models, again with less strength. Anatomical feature analysis revealed significant overlap between working memory and fluid intelligence models, particularly in utilization of prefrontal and parietal regions, and less overlap in predictive features between working memory and sustained attention models. Furthermore, showing the generality of these models, the working memory model developed from Human Connectome Project data generalized to predict memory in an independent data set of 157 older adults (mean age = 69 years; 48 healthy, 54 amnestic mild cognitive impairment, 55 Alzheimer disease). The present results demonstrate that distributed functional connectivity patterns predict individual variation in working memory capability across the adult life span, correlating with constructs including fluid intelligence and sustained attention.

Cerebrospinal Fluid Markers of Synaptic Injury and Functional Connectivity in Alzheimer Disease: Protocol for a Cross-Sectional Study

Background

Synaptic loss is the best surrogate for cognitive decline in Alzheimer disease (AD) and is more closely associated with cognitive function than amyloid or tau pathologies. Neurogranin (Ng) and synaptosome–associated protein-25 (SNAP-25) have demonstrated utility as cerebrospinal fluid (CSF) markers of synaptic injury in presymptomatic and symptomatic AD. While these synaptic markers have been shown to correlate with cognitive impairment and whole brain or regional atrophy in previous studies of AD, to our knowledge, the relationship between fluid markers of synaptic injury and functional brain imaging has not been previously investigated.

Objective

The main objective of this study is to examine the relationship between CSF markers of synaptic injury (Ng and SNAP-25) and functional connectivity (FC) in the default mode and semantic memory networks in individuals with mild cognitive impairment (MCI) and mild dementia due to AD (Clinical Dementia Rating [CDR] 0.5-1) and cognitively normal controls (CDR 0), adjusting for age, gender, and the apolipoprotein E4 (APOE4) genotype. Secondary objectives include investigating the associations between CSF markers of amyloid and tau pathology (CSF tau, p-tau181, and Aβ42) and FC in the default mode and semantic memory networks in AD (CDR 0.5-1) and controls (CDR 0), adjusting for age, gender, and the APOE4 genotype.

Methods

This is a cross-sectional study of individuals with MCI or mild dementia due to AD (CDR 0.5-1; n=20), and cognitively normal controls (CDR 0; n=20). Participants will undergo detailed clinical and neuropsychological assessments, CSF biomarker assessments (CSF Ng, SNAP-25, tau, p-tau181, and Aβ42 levels) and functional magnetic resonance imaging assessments, using a Siemens 3.0 Tesla Prisma scanner, during resting state and during the performance of a semantic memory task. All study procedures will be completed within 4 months of enrollment. Partial correlation analyses will examine associations of CSF biomarker measures with FC in the default mode and semantic memory networks in AD and controls.

Results

This study was funded by the Chronic Brain Injury Discovery Themes of the Ohio State University College of Medicine. Study enrollment began in April 2018. Study procedures and data analysis are currently underway. Results are expected by December 2019.

Conclusions

Findings from this study will further support the utility of CSF Ng and SNAP-25 as markers of synaptic injury by examining their associations with functional alterations in cortical networks affected by early AD pathology.

International Registered Report Identifier (IRRID)

DERR1-10.2196/14302