Metal mixtures are associated with increased anxiety during pregnancy.

BACKGROUND: Exposure to low-dose toxic metals in the environment is ubiquitous. Several murine studies have shown metals induce anxiety-like behaviors, and mechanistic research supports that metals disrupt neurotransmitter signaling systems implicated in the pathophysiology of anxiety. In this study, we extend prior research by examining joint exposure to six metals in relation to maternal anxiety symptoms during pregnancy. METHODS: The sample includes 380 participants enrolled in the PRogramming of Intergenerational Stress Mechanisms (PRISM) pregnancy cohort. Spot urine was collected during pregnancy (mean ± standard deviation: 31.1 ± 6.1 weeks), and concentrations of six metals (barium [Ba], cadmium [Cd], chromium [Cr], cesium [Cs], lead [Pb], antimony [Sb]) were measured by Inductively Coupled Plasma - Mass Spectrometry. Trait anxiety symptoms were measured during pregnancy using a short version of the Spielberger State Trait Anxiety Inventory (STAI-T) and information on covariates was collected by questionnaire. We used weighted quantile sum (WQS) regression as the primary modeling approach to examine metals, treated as a mixture, in relation to higher (≥20) vs. lower anxiety symptoms while adjusting for urinary creatinine and key sociodemographic variables. RESULTS: The sample is socioeconomically and racially/ethnically diverse. Urinary metal concentrations were log-normally distributed and 25% of the sample had an STAI-T score ≥20. Joint exposure to metals was associated with elevated anxiety symptoms (ORWQS = 1.56, 95% CI: 1.24, 1.96); Cd (61.8%), Cr (14.7%), and Cs (12.7%) contributed the greatest weight to the mixture effect. CONCLUSION: Exposure to metals in the environment may be associated with anxiety symptoms during pregnancy. This is a public health concern, as anxiety disorders are highly prevalent and associated with significant co-morbidities, especially during pregnancy when both the mother and developing fetus are susceptible to adverse health outcomes.

Association of Neuroimaging Data with Behavioral Variables: A Class of Multivariate Methods and Their Comparison Using Multi-Task FMRI Data.

It is becoming increasingly common to collect multiple related neuroimaging datasets either from different modalities or from different tasks and conditions. In addition, we have non-imaging data such as cognitive or behavioral variables, and it is through the association of these two sets of data-neuroimaging and non-neuroimaging-that we can understand and explain the evolution of neural and cognitive processes, and predict outcomes for intervention and treatment. Multiple methods for the joint analysis or fusion of multiple neuroimaging datasets or modalities exist; however, methods for the joint analysis of imaging and non-imaging data are still in their infancy. Current approaches for identifying brain networks related to cognitive assessments are still largely based on simple one-to-one correlation analyses and do not use the cross information available across multiple datasets. This work proposes two approaches based on independent vector analysis (IVA) to jointly analyze the imaging datasets and behavioral variables such that multivariate relationships across imaging data and behavioral features can be identified. The simulation results show that our proposed methods provide better accuracy in identifying associations across imaging and behavioral components than current approaches. With functional magnetic resonance imaging (fMRI) task data collected from 138 healthy controls and 109 patients with schizophrenia, results reveal that the central executive network (CEN) estimated in multiple datasets shows a strong correlation with the behavioral variable that measures working memory, a result that is not identified by traditional approaches. Most of the identified fMRI maps also show significant differences in activations across healthy controls and patients potentially providing a useful signature of mental disorders.

Multi-media biomarkers: Integrating information to improve lead exposure assessment.

Exposure assessment traditionally relies on biomarkers that measure chemical concentrations in individual biological media (i.e., blood, urine, etc.). However, chemicals distribute unevenly among different biological media; thus, each medium provides incomplete information about body burden. We propose that machine learning and statistical approaches can create integrated exposure estimates from multiple biomarker matrices that better represent the overall body burden, which we term multi-media biomarkers (MMBs). We measured lead (Pb) in blood, urine, hair and nails from 251 Italian adolescents aged 11-14 years from the Public Health Impact of Metals Exposure (PHIME) cohort. We derived aggregated MMBs from the four biomarkers and then tested their association with Wechsler Intelligence Scale for Children (WISC) IQ scores. We used three approaches to derive the Pb MMB: one supervised learning technique, weighted quantile sum regression (WQS), and two unsupervised learning techniques, independent component analysis (ICA) and non-negative matrix factorization (NMF). Overall, the Pb MMB derived using WQS was most consistently associated with IQ scores and was the only method to be statistically significant for Verbal IQ, Performance IQ and Total IQ. A one standard deviation increase in the WQS MMB was associated with lower Verbal IQ (ß [95% CI] = -2.2 points [-3.7, -0.6]), Performance IQ (-1.9 points [-3.5, -0.4]) and Total IQ (-2.1 points [-3.8, -0.5]). Blood Pb was negatively associated with only Verbal IQ, with a one standard deviation increase in blood Pb being associated with a -1.7 point (95% CI: [-3.3, -0.1]) decrease in Verbal IQ. Increases of one standard deviation in the ICA MMB were associated with lower Verbal IQ (-1.7 points [-3.3, -0.1]) and lower Total IQ (-1.7 points [-3.3, -0.1]). Similarly, an increase of one standard deviation in the NMF MMB was associated with lower Verbal IQ (-1.8 points [-3.4, -0.2]) and lower Total IQ (-1.8 points [-3.4, -0.2]). Weights highlighting the contributions of each medium to the MMB revealed that blood Pb was the largest contributor to most MMBs, although the weights varied from more than 80% for the ICA and NMF MMBs to between 30% and 54% for the WQS-derived MMBs. Our results suggest that MMBs better reflect the total body burden of a chemical that may be acting on target organs than individual biomarkers. Estimating MMBs improved our ability to estimate the full impact of Pb on IQ. Compared with individual Pb biomarkers, including blood, a Pb MMB derived using WQS was more strongly associated with IQ scores. MMBs may increase statistical power when the choice of exposure medium is unclear or when the sample size is small. Future work will need to validate these methods in other cohorts and for other chemicals.

The role of diversity in data-driven analysis of multi-subject fMRI data: Comparison of approaches based on independence and sparsity using global performance metrics.

Data-driven methods have been widely used in functional magnetic resonance imaging (fMRI) data analysis. They extract latent factors, generally, through the use of a simple generative model. Independent component analysis (ICA) and dictionary learning (DL) are two popular data-driven methods that are based on two different forms of diversity-statistical properties of the data-statistical independence for ICA and sparsity for DL. Despite their popularity, the comparative advantage of emphasizing one property over another in the decomposition of fMRI data is not well understood. Such a comparison is made harder due to the differences in the modeling assumptions between ICA and DL, as well as within different ICA algorithms where each algorithm exploits a different form of diversity. In this paper, we propose the use of objective global measures, such as time course frequency power ratio, network connection summary, and graph theoretical metrics, to gain insight into the role that different types of diversity have on the analysis of fMRI data. Four ICA algorithms that account for different types of diversity and one DL algorithm are studied. We apply these algorithms to real fMRI data collected from patients with schizophrenia and healthy controls. Our results suggest that no one particular method has the best performance using all metrics, implying that the optimal method will change depending on the goal of the analysis. However, we note that in none of the scenarios we test the highly popular Infomax provides the best performance, demonstrating the cost of exploiting limited form of diversity.

Time-varying associations between prenatal metal mixtures and rapid visual processing in children.

BACKGROUND: Humans are exposed to mixtures of chemicals across their lifetimes, a concept sometimes called the "exposome." Mixtures likely have temporal "critical windows" of susceptibility like single agents and measuring them repeatedly might help to define such windows. Common approaches to evaluate the effects of chemical mixtures have focused on their effects at a single time point. Our goal is to expand upon these previous techniques and examine the time-varying critical windows for metal mixtures on subsequent neurobehavior in children. METHODS: We propose two methods, joint weighted quantile sum regression (JWQS) and meta-weighted quantile sum regression (MWQS), to estimate the effects of chemical mixtures measured across multiple time points, while providing data on their critical windows of exposure. We compare the performance of both methods using simulations. We also applied both techniques to assess second and third trimester metal mixture effects in predicting performance in the Rapid Visual Processing (RVP) task from the Cambridge Neuropsychological Test Automated Battery (CANTAB) assessed at 6-9 years in children who are part of the PROGRESS (Programming Research in Obesity, GRowth, Environment and Social Stressors) longitudinal cohort study. The metals, arsenic, cadmium (Cd), cesium, chromium, lead (Pb) and antimony (Sb) were selected based on their toxicological profile. RESULTS: In simulations, JWQS and MWQS had over 80% accuracy in classifying exposures as either strongly or weakly contributing to an association. In real data, both JWQS and MWQS consistently found that Pb and Cd exposure jointly predicted longer latency in the RVP and that second trimester exposure better predicted the results than the third trimester. Additionally, both JWQS and MWQS highlighted the strong association Cd and Sb had with lower accuracy in the RVP and that third trimester exposure was a better predictor than second trimester exposure. CONCLUSIONS: Our results indicate that metal mixtures effects vary across time, have distinct critical windows and that both JWQS and MWQS can determine longitudinal mixture effects including the cumulative contribution of each exposure and critical windows of effect.

Sample-poor estimation of order and common signal subspace with application to fusion of medical imaging data.

Due to their data-driven nature, multivariate methods such as canonical correlation analysis (CCA) have proven very useful for fusion of multimodal neurological data. However, being able to determine the degree of similarity between datasets and appropriate order selection are crucial to the success of such techniques. The standard methods for calculating the order of multimodal data focus only on sources with the greatest individual energy and ignore relations across datasets. Additionally, these techniques as well as the most widely-used methods for determining the degree of similarity between datasets assume sufficient sample support and are not effective in the sample-poor regime. In this paper, we propose to jointly estimate the degree of similarity between datasets and their order when few samples are present using principal component analysis and canonical correlation analysis (PCA-CCA). By considering these two problems simultaneously, we are able to minimize the assumptions placed on the data and achieve superior performance in the sample-poor regime compared to traditional techniques. We apply PCA-CCA to the pairwise combinations of functional magnetic resonance imaging (fMRI), structural magnetic resonance imaging (sMRI), and electroencephalogram (EEG) data drawn from patients with schizophrenia and healthy controls while performing an auditory oddball task. The PCA-CCA results indicate that the fMRI and sMRI datasets are the most similar, whereas the sMRI and EEG datasets share the least similarity. We also demonstrate that the degree of similarity obtained by PCA-CCA is highly predictive of the degree of significance found for components generated using CCA.

Multi-modal data fusion using source separation: Two effective models based on ICA and IVA and their properties.

Fusion of information from multiple sets of data in order to extract a set of features that are most useful and relevant for the given task is inherent to many problems we deal with today. Since, usually, very little is known about the actual interaction among the datasets, it is highly desirable to minimize the underlying assumptions. This has been the main reason for the growing importance of data-driven methods, and in particular of independent component analysis (ICA) as it provides useful decompositions with a simple generative model and using only the assumption of statistical independence. A recent extension of ICA, independent vector analysis (IVA) generalizes ICA to multiple datasets by exploiting the statistical dependence across the datasets, and hence, as we discuss in this paper, provides an attractive solution to fusion of data from multiple datasets along with ICA. In this paper, we focus on two multivariate solutions for multi-modal data fusion that let multiple modalities fully interact for the estimation of underlying features that jointly report on all modalities. One solution is the Joint ICA model that has found wide application in medical imaging, and the second one is the the Transposed IVA model introduced here as a generalization of an approach based on multi-set canonical correlation analysis. In the discussion, we emphasize the role of diversity in the decompositions achieved by these two models, present their properties and implementation details to enable the user make informed decisions on the selection of a model along with its associated parameters. Discussions are supported by simulation results to help highlight the main issues in the implementation of these methods.

Integrated measures of lead and manganese exposure improve estimation of their joint effects on cognition in Italian school-age children.

Every day humans are exposed to mixtures of chemicals, such as lead (Pb) and manganese (Mn). An underappreciated aspect of studying the health effects of mixtures is the role that the exposure biomarker media (blood, hair, etc.) may play in estimating the effects of the mixture. Different biomarker media represent different aspects of each chemical's toxicokinetics, thus no single medium can fully capture the toxicokinetic profile for all the chemicals in a mixture. A potential solution to this problem is to combine exposure data across different media to derive integrated estimates of each chemical's internal concentration. This concept, formalized as a multi-media biomarker (MMB) has proven effective for estimating the health impacts of Pb exposure, but may also be useful to estimate mixture effects, such as the joint effects of metals like Pb and Mn, while factoring in how the association changes based upon the biomarker media. Levels of Pb and Mn were quantified in five media: blood, hair, nails, urine, and saliva in the Public Health Impact of Metals Exposure (PHIME) project, a study of Italian adolescents aged 10-14 years. MMBs were derived for both metals using weighted quantile sum (WQS) regression across the five media. Age-adjusted Wechsler Intelligence Scale for Children (WISC) IQ scores, measured at the same time as the exposure measures, were the primary outcome and models were adjusted for sex and socioeconomic status. The levels Pb and Mn were relatively low, with median blood Pb of 1.27 (IQR: 0.84) µg/dL and median blood Mn of 1.09 (IQR: 0.45) µg/dL. Quartile increases in a Pb-Mn combination predicted decreased Full Scale IQ of 1.9 points (95% CI: 0.3, 3.5) when Pb and Mn exposure levels were estimated using MMBs, while individual regressions for each metal were not associated with Full Scale IQ. Additionally, a quartile increase in the WQS index of Pb and Mn, measured using MMBs, were associated with reductions in Verbal IQ by 2.8 points (1.0, 4.5). Weights that determine the contributions of the metals to the joint effect highlighted that the contribution of the Pb-Mn was 72-28% for Full Scale IQ and 42-58% for Verbal IQ. We found that the joint effects of Pb and Mn are strongly affected by the medium used to measure exposure and that the joint effects of the Pb and Mn MMBs on cognition were the stronger than any individual biomarker. Thus, increase power and accuracy for measuring mixture effects compared to individual biomarkers. As the number of chemicals in mixtures increases, appropriate biomarker selection will become increasingly important and MMBs are a natural way to reduce bias in such analyses.

Prenatal metal mixtures and sex-specific infant negative affectivity.

Prenatal exposure to metals has been associated with a range of adverse neurocognitive outcomes; however, associations with early behavioral development are less well understood. We examined joint exposure to multiple co-occurring metals in relation to infant negative affect, a stable temperamental trait linked to psychopathology among children and adults. METHODS: Analyses included 308 mother-infant pairs enrolled in the PRISM pregnancy cohort. We measured As, Ba, Cd, Cs, Cr, Pb, and Sb in urine, collected on average during late pregnancy, by ICP-MS. At age 6 months, we assessed negative affect using the Infant Behavior Questionnaire-Revised. We used Weighted Quantile Sum (WQS) regression with repeated holdout validation to estimate the joint association between the metals and global negative affectivity, as well as four subdomains (Fear, Sadness, Distress to Limitations, and Falling Reactivity). We also tested for a sex interaction with estimated stratified weights. RESULTS: In adjusted models, urinary metals were associated with higher scores on the Fear scale (ßWQS = 0.20, 95% confidence interval [CI]: 0.09, 0.30), which captures behavioral inhibition, characterized by startle or distress to sudden changes in the environment and inhibited approach to novelty. We observed a significant sex interaction (95% CI for the cross-product term: -0.19, -0.01), and stratified weights showed girls (61.6%) contributed substantially more to the mixture effect compared with boys (38.4%). Overall, Ba contributed the greatest mixture weight (22.5%), followed by Cs (14.9%) and As (14.6%). CONCLUSIONS: Prenatal exposure to metals was associated with increased infant scores on the temperamental domain of fear, with girls showing particular sensitivity.Key words: Prenatal; Metals; Mixtures; Temperament; Infancy; Negative affect.

Nephrotoxic Metal Mixtures and Preadolescent Kidney Function.

Exposure to metals including lead (Pb), cadmium (Cd), and arsenic (As), may impair kidney function as individual toxicants or in mixtures. However, no single medium is ideal to study multiple metals simultaneously. We hypothesized that multi-media biomarkers (MMBs), integrated indices combining information across biomarkers, are informative of adverse kidney function. Levels of Pb, Cd, and As were quantified in blood and urine in 4-6-year-old Mexican children (n = 300) in the PROGRESS longitudinal cohort study. We estimated the mixture effects of these metals, using weighted quantile sum regression (WQS) applied to urine biomarkers (Umix), blood biomarkers (Bmix), and MMBs, on the cystatin C-based estimated glomerular filtration rate (eGFR) and serum cystatin C assessed at 8-10 years of age, adjusted for covariates. Quartile increases in Umix and the MMB mixture were associated with 2.5% (95%CI: 0.1, 5.0) and 3.0% (95%CI: 0.2, 5.7) increased eGFR and -2.6% (95% CI: -5.1%, -0.1%) and -3.3% (95% CI: -6.5%, -0.1%) decreased cystatin C, respectively. Weights indicate that the strongest contributors to the associations with eGFR and serum cystatin C were Cd and Pb, respectively. MMBs detected mixture effects distinct from associations with individual metals or media-type, highlighting the benefits of incorporating information from multiple exposure media in mixtures analyses.

Exosomal miRNAs in urine associated with children's cardiorenal parameters: a cross-sectional study.

Aims: The authors sought to examine associations between urinary exosomal miRNAs (exo-miRs), emerging biomarkers of renal health, and cardiorenal outcomes in early childhood. Materials & methods: The authors extracted exo-miRs in urine from 88 healthy Mexican children aged 4-6 years. The authors measured associations between 193 exo-miRs and cardiorenal outcomes: systolic/diastolic blood pressure, estimated glomerular filtration rate and urinary sodium and potassium levels. The authors adjusted for age, sex, BMI, socioeconomic status, indoor tobacco smoke exposure and urine specific gravity. Results: Multiple exo-miRs were identified meeting a false discovery rate threshold of q < 0.1. Specifically, three exo-miRs had increased expression with urinary sodium, 17 with urinary sodium-to-potassium ratio and one with decreased estimated glomerular filtration rate. Conclusions: These results highlight urinary exo-miRs as early-life biomarkers of children's cardiorenal health.

Sex-specific associations between co-exposure to multiple metals and visuospatial learning in early adolescence.

The predisposition, severity, and progression of many diseases differ between males and females. Sex-related differences in susceptibility to neurotoxicant exposures may provide insight into the cause of the observed discrepancy. Early adolescence, a period of substantial structural and functional brain changes, may present a critical window of vulnerability to environmental exposures. This study aimed to examine sex-specific associations between co-exposure to multiple metals and visuospatial memory in early adolescence. Manganese (Mn), lead (Pb), chromium (Cr), and copper (Cu) were measured in blood, urine, hair, nails, and saliva of 188 participants (88 girls; 10-14 years of age). Visuospatial memory skills were assessed using a computerized maze task, the virtual radial arm maze (VRAM). Using generalized weighted quantile sum regression, we investigated sex-specific associations between the combined effect of exposure to the metal mixture and visuospatial working memory and determined the contribution of each component to the outcome. The results suggest that sex moderates the association between the metal mixture and visuospatial learning for all outcomes measured. In girls, exposure was associated with slower visuospatial learning and driven by Mn and Cu. In boys, exposure was associated with faster visuospatial learning, and driven by Cr. These results suggest that (a) the effect of metal co-exposure on learning differs in magnitude, and in the direction between sexes, and (b) early adolescence may be a sensitive developmental period for metal exposure.

A method to compare the discriminatory power of data-driven methods: Application to ICA and IVA.

BACKGROUND: The widespread application of data-driven factorization-based methods, such as independent component analysis (ICA), to functional magnetic resonance imaging data facilitates the study of neural function and how it is disrupted by psychiatric disorders such as schizophrenia. While the increasing number of these methods motivates a comparison of their relative performance, such a comparison is difficult to perform on real fMRI data, since the ground truth is, relatively, unknown and the alignment of factors across different methods is impractical and imprecise. NEW METHOD: We present a novel method, global difference maps (GDMs), to compare the results of different fMRI analysis techniques on real fMRI data, quantify their relative performances, and highlight the differences between the decompositions visually. COMPARISON WITH EXISTING METHODS: We apply this method to compare the performances of two different factorization-based methods, ICA and its multiset extension independent vector analysis (IVA), for the analysis of fMRI data from 109 patients with schizophrenia and 138 healthy controls during the performance of three tasks. RESULTS: Through this application of GDMs, we find that IVA can determine regions that are more discriminatory between patients and controls than ICA, though IVA is less effective at emphasizing regions found in only a subset of the tasks. CONCLUSIONS: These results demonstrate that GDMs are an effective way to compare the performances of different factorization-based methods as well as regression-based analyses.

Unraveling Diagnostic Biomarkers of Schizophrenia Through Structure-Revealing Fusion of Multi-Modal Neuroimaging Data.

Fusing complementary information from different modalities can lead to the discovery of more accurate diagnostic biomarkers for psychiatric disorders. However, biomarker discovery through data fusion is challenging since it requires extracting interpretable and reproducible patterns from data sets, consisting of shared/unshared patterns and of different orders. For example, multi-channel electroencephalography (EEG) signals from multiple subjects can be represented as a third-order tensor with modes: subject, time, and channel, while functional magnetic resonance imaging (fMRI) data may be in the form of subject by voxel matrices. Traditional data fusion methods rearrange higher-order tensors, such as EEG, as matrices to use matrix factorization-based approaches. In contrast, fusion methods based on coupled matrix and tensor factorizations (CMTF) exploit the potential multi-way structure of higher-order tensors. The CMTF approach has been shown to capture underlying patterns more accurately without imposing strong constraints on the latent neural patterns, i.e., biomarkers. In this paper, EEG, fMRI, and structural MRI (sMRI) data collected during an auditory oddball task (AOD) from a group of subjects consisting of patients with schizophrenia and healthy controls, are arranged as matrices and higher-order tensors coupled along the subject mode, and jointly analyzed using structure-revealing CMTF methods [also known as advanced CMTF (ACMTF)] focusing on unique identification of underlying patterns in the presence of shared/unshared patterns. We demonstrate that joint analysis of the EEG tensor and fMRI matrix using ACMTF reveals significant and biologically meaningful components in terms of differentiating between patients with schizophrenia and healthy controls while also providing spatial patterns with high resolution and improving the clustering performance compared to the analysis of only the EEG tensor. We also show that these patterns are reproducible, and study reproducibility for different model parameters. In comparison to the joint independent component analysis (jICA) data fusion approach, ACMTF provides easier interpretation of EEG data by revealing a single summary map of the topography for each component. Furthermore, fusion of sMRI data with EEG and fMRI through an ACMTF model provides structural patterns; however, we also show that when fusing data sets from multiple modalities, hence of very different nature, preprocessing plays a crucial role.

Length of gestation and birth weight are associated with indices of combined kidney biomarkers in early childhood.

Infants born prematurely or with low birth weights are more susceptible to kidney dysfunction throughout their lives. Multiple proteins measured in urine are noninvasive biomarkers of subclinical kidney damage, but few studies have examined the joint effects of multiple biomarkers. We conducted an exploratory study of 103 children in the Programing Research in Obesity, Growth, Environment, and Social Stressors (PROGRESS) longitudinal birth cohort, and measured nine proteins selected a priori in banked spot urine samples collected at ages 4-6. The goal of our study was to explore the combined effects of kidney damage biomarkers previously associated with birth outcomes. To do this, we generated kidney biomarker indices using weighted quantile sum regression and assessed associations with length of gestation or birth weight. A decile increase in each kidney biomarker index was associated with 2-day shorter gestations (ß = -2.0, 95% CI: -3.2, -0.9) and 59-gram lower birth weights (ß = -58.5, 95% CI: -98.3, -18.7), respectively. Weights highlighting the contributions showed neutrophil gelatinase-associated lipocalin (NGAL) (60%) and osteopontin (19%) contributed most to the index derived for gestational age. NGAL (66%) and beta-2-microglobulin (10%) contributed most to the index derived for birth weight. Joint analyses of multiple kidney biomarkers can provide integrated measures of kidney dysfunction and improved statistical assessments compared to biomarkers assessed individually. Additionally, shorter gestations and lower birth weights may contribute to subclinical kidney damage measurable in childhood.

Quantifying the Interaction and Contribution of Multiple Datasets in Fusion: Application to the Detection of Schizophrenia.

The extraction of information from multiple sets of data is a problem inherent to many disciplines. This is possible by either analyzing the data sets jointly as in data fusion or separately and then combining as in data integration. However, selecting the optimal method to combine and analyze multiset data is an ever-present challenge. The primary reason for this is the difficulty in determining the optimal contribution of each data set to an analysis as well as the amount of potentially exploitable complementary information among data sets. In this paper, we propose a novel classification rate-based technique to unambiguously quantify the contribution of each data set to a fusion result as well as facilitate direct comparisons of fusion methods on real data and apply a new method, independent vector analysis (IVA), to multiset fusion. This classification rate-based technique is used on functional magnetic resonance imaging data collected from 121 patients with schizophrenia and 150 healthy controls during the performance of three tasks. Through this application, we find that though optimal performance is achieved by exploiting all tasks, each task does not contribute equally to the result and this framework enables effective quantification of the value added by each task. Our results also demonstrate that data fusion methods are more powerful than data integration methods, with the former achieving a classification rate of 73.5 % and the latter achieving one of 70.9 %, a difference which we show is significant when all three tasks are analyzed together. Finally, we show that IVA, due to its flexibility, has equivalent or superior performance compared with the popular data fusion method, joint independent component analysis.

The role of diversity in complex ICA algorithms for fMRI analysis.

BACKGROUND: The widespread use of data-driven methods, such as independent component analysis (ICA), for the analysis of functional magnetic resonance imaging data (fMRI) has enabled deeper understanding of neural function. However, most popular ICA algorithms for fMRI analysis make several simplifying assumptions, thus ignoring sources of statistical information, types of "diversity," and limiting their performance. NEW METHOD: We propose the use of complex entropy rate bound minimization (CERBM) for the analysis of actual fMRI data in its native, complex, domain. Though CERBM achieves enhanced performance through the exploitation of the three types of diversity inherent to complex fMRI data: noncircularity, non-Gaussianity, and sample-to-sample dependence, CERBM produces results that are more variable than simpler methods. This motivates the development of a minimum spanning tree (MST)-based stability analysis that mitigates the variability of CERBM. COMPARISON WITH EXISTING METHODS: In order to validate our method, we compare the performance of CERBM with the popular CInfomax as well as complex entropy bound minimization (CEBM). RESULTS: We show that by leveraging CERBM and the MST-based stability analysis, we are able to consistently produce components that have a greater number of activated voxels in physically meaningful regions and can more accurately classify patients with schizophrenia than components generated using simpler models. CONCLUSIONS: Our results demonstrate the advantages of using ICA algorithms that can exploit all inherent types of diversity for the analysis of fMRI data when coupled with appropriate stability analyses.