Optimizing differential identifiability improves connectome predictive modeling of cognitive deficits from functional connectivity in Alzheimer's disease.
Ontology highlight
ABSTRACT:
SUBMITTER: Svaldi DO
PROVIDER: S-EPMC8249900 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:It is a longstanding goal of neuroimaging to produce reliable, generalizable models of brain behavior relationships. More recently, data driven predictive models have become popular. However, overfitting is a common problem with statistical models, which impedes model generalization. Cross validation (CV) is often used to estimate expected model performance within sample. Yet, the best way to generate brain behavior models, and apply them out-of-sample, on an unseen dataset, is unclear. As a solution, this study proposes an ensemble learning method, in this case resample aggregating, encompassing both model parameter estimation and feature selection. Here we investigate the use of resampled aggregated models when used to estimate fluid intelligence (fIQ) from fMRI based functional connectivity (FC) data. We take advantage of two large openly available datasets, the Human Connectome Project (HCP), and the Philadelphia Neurodevelopmental Cohort (PNC). We generate aggregated and non-aggregated models of fIQ in the HCP, using the Connectome Prediction Modelling (CPM) framework. Over various test-train splits, these models are evaluated in sample, on left-out HCP data, and out-of-sample, on PNC data. We find that a resample aggregated model performs best both within- and out-of-sample. We also find that feature selection can vary substantially within-sample. More robust feature selection methods, as detailed here, are needed to improve cross sample performance of CPM based brain behavior models.
| S-EPMC8282199 | biostudies-literature
Project description:Neuroimaging is a fast-developing research area in which anatomical and functional images of human brains are collected using techniques such as functional magnetic resonance imaging (fMRI), diffusion tensor imaging (DTI), and electroencephalography (EEG). Technical advances and large-scale data sets have allowed for the development of models capable of predicting individual differences in traits and behavior using brain connectivity measures derived from neuroimaging data. Here, we present connectome-based predictive modeling (CPM), a data-driven protocol for developing predictive models of brain-behavior relationships from connectivity data using cross-validation. This protocol includes the following steps: (i) feature selection, (ii) feature summarization, (iii) model building, and (iv) assessment of prediction significance. We also include suggestions for visualizing the most predictive features (i.e., brain connections). The final result should be a generalizable model that takes brain connectivity data as input and generates predictions of behavioral measures in novel subjects, accounting for a considerable amount of the variance in these measures. It has been demonstrated that the CPM protocol performs as well as or better than many of the existing approaches in brain-behavior prediction. As CPM focuses on linear modeling and a purely data-driven approach, neuroscientists with limited or no experience in machine learning or optimization will find it easy to implement these protocols. Depending on the volume of data to be processed, the protocol can take 10-100 min for model building, 1-48 h for permutation testing, and 10-20 min for visualization of results.
| S-EPMC5526681 | biostudies-literature
Project description:IntroductionTrait mindfulness refers to one's disposition or tendency to pay attention to their experiences in the present moment, in a non-judgmental and accepting way. Trait mindfulness has been robustly associated with positive mental health outcomes, but its neural underpinnings are poorly understood. Prior resting-state fMRI studies have associated trait mindfulness with within- and between-network connectivity of the default-mode (DMN), fronto-parietal (FPN), and salience networks. However, it is unclear how generalizable the findings are, how they relate to different components of trait mindfulness, and how other networks and brain areas may be involved.MethodsTo address these gaps, we conducted the largest resting-state fMRI study of trait mindfulness to-date, consisting of a pre-registered connectome predictive modeling analysis in 367 adults across three samples collected at different sites.ResultsIn the model-training dataset, we did not find connections that predicted overall trait mindfulness, but we identified neural models of two mindfulness subscales, Acting with Awareness and Non-judging. Models included both positive networks (sets of pairwise connections that positively predicted mindfulness with increasing connectivity) and negative networks, which showed the inverse relationship. The Acting with Awareness and Non-judging positive network models showed distinct network representations involving FPN and DMN, respectively. The negative network models, which overlapped significantly across subscales, involved connections across the whole brain with prominent involvement of somatomotor, visual and DMN networks. Only the negative networks generalized to predict subscale scores out-of-sample, and not across both test datasets. Predictions from both models were also negatively correlated with predictions from a well-established mind-wandering connectome model.ConclusionsWe present preliminary neural evidence for a generalizable connectivity models of trait mindfulness based on specific affective and cognitive facets. However, the incomplete generalization of the models across all sites and scanners, limited stability of the models, as well as the substantial overlap between the models, underscores the difficulty of finding robust brain markers of mindfulness facets.
| S-EPMC11257611 | biostudies-literature
Project description:Connectome-based predictive modeling (CPM; Finn et al., 2015; Shen et al., 2017) was recently developed to predict individual differences in traits and behaviors, including fluid intelligence (Finn et al., 2015) and sustained attention (Rosenberg et al., 2016a), from functional brain connectivity (FC) measured with fMRI. Here, using the CPM framework, we compared the predictive power of three different measures of FC (Pearson's correlation, accordance, and discordance) and two different prediction algorithms (linear and partial least square [PLS] regression) for attention function. Accordance and discordance are recently proposed FC measures that respectively track in-phase synchronization and out-of-phase anti-correlation (Meskaldji et al., 2015). We defined connectome-based models using task-based or resting-state FC data, and tested the effects of (1) functional connectivity measure and (2) feature-selection/prediction algorithm on individualized attention predictions. Models were internally validated in a training dataset using leave-one-subject-out cross-validation, and externally validated with three independent datasets. The training dataset included fMRI data collected while participants performed a sustained attention task and rested (N = 25; Rosenberg et al., 2016a). The validation datasets included: 1) data collected during performance of a stop-signal task and at rest (N = 83, including 19 participants who were administered methylphenidate prior to scanning; Farr et al., 2014a; Rosenberg et al., 2016b), 2) data collected during Attention Network Task performance and rest (N = 41, Rosenberg et al., in press), and 3) resting-state data and ADHD symptom severity from the ADHD-200 Consortium (N = 113; Rosenberg et al., 2016a). Models defined using all combinations of functional connectivity measure (Pearson's correlation, accordance, and discordance) and prediction algorithm (linear and PLS regression) predicted attentional abilities, with correlations between predicted and observed measures of attention as high as 0.9 for internal validation, and 0.6 for external validation (all p's < 0.05). Models trained on task data outperformed models trained on rest data. Pearson's correlation and accordance features generally showed a small numerical advantage over discordance features, while PLS regression models were usually better than linear regression models. Overall, in addition to correlation features combined with linear models (Rosenberg et al., 2016a), it is useful to consider accordance features and PLS regression for CPM.
| S-EPMC5845789 | biostudies-literature
Project description:Autism is a heterogeneous neurodevelopmental condition, and functional magnetic resonance imaging-based studies have helped advance our understanding of its effects on brain network activity. We review how predictive modeling, using measures of functional connectivity and symptoms, has helped reveal key insights into this condition. We discuss how different prediction frameworks can further our understanding of the brain-based features that underlie complex autism symptomatology and consider how predictive models may be used in clinical settings. Throughout, we highlight aspects of study interpretation, such as data decay and sampling biases, that require consideration within the context of this condition. We close by suggesting exciting future directions for predictive modeling in autism.
| S-EPMC10948028 | biostudies-literature
Project description:A multivariate analytical strategy may pinpoint the structural connectivity patterns associated with Alzheimer's disease (AD) pathology in connectome-wide association studies. Diffusion magnetic resonance imaging data from 161 participants including subjects with healthy controls, AD, stable and converting mild cognitive impairment, were selected for group-wise comparisons. A multivariate distance matrix regression (MDMR) analysis was performed to detect abnormality in brain structural network along with disease progression. Based on the seed regions returned by the MDMR analysis, supervised learning was applied to evaluate the disease predictive performance. Nine brain regions, including the left orbital part of superior and middle frontal gyrus, the bilateral supplementary motor area, the bilateral insula, the left hippocampus, the left putamen, and the left thalamus demonstrated extremely significant structural pattern changes along with the progression of AD. The disease classification was more efficient when based on the key connectivity related to these seed regions than when based on whole-brain structural connectivity. MDMR analysis reveals brain network reorganization caused by AD pathology. The key structural connectivity detected in this study exhibits promising distinguishing capability to predict prodromal AD patients.
| S-EPMC6396432 | biostudies-literature
Project description: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.
| S-EPMC10107737 | biostudies-literature
Project description:BackgroundReinforcement learning models provide excellent descriptions of learning in multiple species across a variety of tasks. Many researchers are interested in relating parameters of reinforcement learning models to neural measures, psychological variables or experimental manipulations. We demonstrate that parameter identification is difficult because a range of parameter values provide approximately equal quality fits to data. This identification problem has a large impact on power: we show that a researcher who wants to detect a medium sized correlation (r = .3) with 80% power between a variable and learning rate must collect 60% more subjects than specified by a typical power analysis in order to account for the noise introduced by model fitting.New methodWe derive a Bayesian optimal model fitting technique that takes advantage of information contained in choices and reaction times to constrain parameter estimates.ResultsWe show using simulation and empirical data that this method substantially improves the ability to recover learning rates.Comparison with existing methodsWe compare this method against the use of Bayesian priors. We show in simulations that the combined use of Bayesian priors and reaction times confers the highest parameter identifiability. However, in real data where the priors may have been misspecified, the use of Bayesian priors interferes with the ability of reaction time data to improve parameter identifiability.ConclusionsWe present a simple technique that takes advantage of readily available data to substantially improve the quality of inferences that can be drawn from parameters of reinforcement learning models.
| S-EPMC8930195 | biostudies-literature
Project description:The recent outbreaks of Ebola virus (EBOV) infections have underlined the impact of the virus as a major threat for human health. Due to the high biosafety classification of EBOV (level 4), basic research is very limited. Therefore, the development of new avenues of thinking to advance quantitative comprehension of the virus and its interaction with the host cells is urgently needed to tackle this lethal disease. Mathematical modeling of the EBOV dynamics can be instrumental to interpret Ebola infection kinetics on quantitative grounds. To the best of our knowledge, a mathematical modeling approach to unravel the interaction between EBOV and the host cells is still missing. In this paper, a mathematical model based on differential equations is used to represent the basic interactions between EBOV and wild-type Vero cells in vitro. Parameter sets that represent infectivity of pathogens are estimated for EBOV infection and compared with influenza virus infection kinetics. The average infecting time of wild-type Vero cells by EBOV is slower than in influenza infection. Simulation results suggest that the slow infecting time of EBOV could be compensated by its efficient replication. This study reveals several identifiability problems and what kind of experiments are necessary to advance the quantification of EBOV infection. A first mathematical approach of EBOV dynamics and the estimation of standard parameters in viral infections kinetics is the key contribution of this work, paving the way for future modeling works on EBOV infection.
| S-EPMC4391033 | biostudies-literature
Project description:Resting-state and task-based functional connectivity matrices, or connectomes, are powerful predictors of individual differences in phenotypic measures. However, most of the current state-of-the-art algorithms only build predictive models based on a single connectome for each individual. This approach neglects the complementary information contained in connectomes from different sources and reduces prediction performance. In order to combine different task connectomes into a single predictive model in a principled way, we propose a novel prediction framework, termed multidimensional connectome-based predictive modeling. Two specific algorithms are developed and implemented under this framework. Using two large open-source datasets with multiple tasks-the Human Connectome Project and the Philadelphia Neurodevelopmental Cohort, we validate and compare our framework against performing connectome-based predictive modeling (CPM) on each task connectome independently, CPM on a general functional connectivity matrix created by averaging together all task connectomes for an individual, and CPM with a naïve extension to multiple connectomes where each edge for each task is selected independently. Our framework exhibits superior performance in prediction compared with the other competing methods. We found that different tasks contribute differentially to the final predictive model, suggesting that the battery of tasks used in prediction is an important consideration. This work makes two major contributions: First, two methods for combining multiple connectomes from different task conditions in one predictive model are demonstrated; Second, we show that these models outperform a previously validated single connectome-based predictive model approach.
| S-EPMC6765422 | biostudies-literature