scholarly journals Sparse Infomax Based on Hoyer Projection and its Application to Simulated Structural MRI and SNP Data

2019 ◽  
Author(s):  
Kuaikuai Duan ◽  
Rogers F. Silva ◽  
Jiayu Chen ◽  
Dongdong Lin ◽  
Vince D. Calhoun ◽  
...  
Keyword(s):  
Structural Mri ◽  
Snp Data

scholarly journals Sparse Infomax Based on Hoyer Projection and its Application to Simulated Structural MRI and SNP Data

2019 ◽  
Author(s):  
Kuaikuai Duan ◽  
Rogers F. Silva ◽  
Jiayu Chen ◽  
Dongdong Lin ◽  
Vince D. Calhoun ◽  
...  
Keyword(s):  
Brain Imaging ◽  
Input Data ◽  
Signal To Noise Ratio ◽  
Genetic Data ◽  
Structural Mri ◽  
Statistical Independence ◽  
Data Types ◽  
Data Analyses ◽  
Snp Data ◽  
Simulation Results

ABSTRACTIndependent component analysis has been widely applied to brain imaging and genetic data analyses for its ability to identify interpretable latent sources. Nevertheless, leveraging source sparsity in a more granular way may further improve its ability to optimize the solution for certain data types. For this purpose, we propose a sparse infomax algorithm based on nonlinear Hoyer projection, leveraging both sparsity and statistical independence of latent sources. The proposed algorithm iteratively updates the unmixing matrix by infomax (for independence) and the sources by Hoyer projection (for sparsity), feeding the sparse sources back as input data for the next iteration. Consequently, sparseness propagates effectively through infomax iterations, producing sources with more desirable properties. Simulation results on both brain imaging and genetic data demonstrate that the proposed algorithm yields improved pattern recovery, particularly under low signal-to-noise ratio conditions, as well as improved sparseness compared to traditional infomax.

scholarly journals Massively expedited genome-wide heritability analysis (MEGHA)

2015 ◽  
Vol 112 (8) ◽  
pp. 2479-2484 ◽  
Author(s):  
Tian Ge ◽  
Thomas E. Nichols ◽  
Phil H. Lee ◽  
Avram J. Holmes ◽  
Joshua L. Roffman ◽  
...  
Keyword(s):  
Large Scale ◽  
Structural Mri ◽  
Population Based ◽  
European Ancestry ◽  
Computational Time ◽  
High Dimensional ◽  
Pedigree Data ◽  
Snp Data ◽  
Genome Wide ◽  
Heritability Analysis

The discovery and prioritization of heritable phenotypes is a computational challenge in a variety of settings, including neuroimaging genetics and analyses of the vast phenotypic repositories in electronic health record systems and population-based biobanks. Classical estimates of heritability require twin or pedigree data, which can be costly and difficult to acquire. Genome-wide complex trait analysis is an alternative tool to compute heritability estimates from unrelated individuals, using genome-wide data that are increasingly ubiquitous, but is computationally demanding and becomes difficult to apply in evaluating very large numbers of phenotypes. Here we present a fast and accurate statistical method for high-dimensional heritability analysis using genome-wide SNP data from unrelated individuals, termed massively expedited genome-wide heritability analysis (MEGHA) and accompanying nonparametric sampling techniques that enable flexible inferences for arbitrary statistics of interest. MEGHA produces estimates and significance measures of heritability with several orders of magnitude less computational time than existing methods, making heritability-based prioritization of millions of phenotypes based on data from unrelated individuals tractable for the first time to our knowledge. As a demonstration of application, we conducted heritability analyses on global and local morphometric measurements derived from brain structural MRI scans, using genome-wide SNP data from 1,320 unrelated young healthy adults of non-Hispanic European ancestry. We also computed surface maps of heritability for cortical thickness measures and empirically localized cortical regions where thickness measures were significantly heritable. Our analyses demonstrate the unique capability of MEGHA for large-scale heritability-based screening and high-dimensional heritability profile construction.

Examining the episodic-semantic interplay during future thinking – A reanalysis of external details

2020 ◽  
Author(s):  
Cherie Strikwerda-Brown ◽  
John Hodges ◽  
Olivier Piguet ◽  
Muireann Irish
Keyword(s):  
Life Story ◽  
Semantic Content ◽  
Structural Mri ◽  
Future Thinking ◽  
Fine Grained ◽  
Differential Vulnerability ◽  
Clinical Disorders ◽  
External Component ◽  
Future Narratives ◽  
General Semantic

Traditional analyses of autobiographical construction have tended to focus on the ‘internal’ or episodic details of the narrative. Contemporary studies employing fine-grained scoring measures, however, reveal the ‘external’ component of autobiographical narratives to contain important information relevant to the individual’s life story. Here, we used the recently developed NExt scoring protocol to explore profiles of external details generated by patients with Alzheimer’s disease (AD) (n = 11) and semantic dementia (SD) (n = 13) on a future thinking task. Voxel-based morphometry analyses of structural MRI were used to determine the neural correlates of external detail profiles in each patient group. Overall, distinct NExt profiles were observed across past and future temporal contexts in AD and SD groups, which involved elevations in external details, in the context of reduced internal details, relative to healthy Controls. Specifically, AD patients provided significantly more General Semantic details compared with Controls during past retrieval, whereas Specific Episode external details were elevated during future simulation. These increased external details within future narratives related to grey matter integrity in medial and lateral frontal regions in AD. By contrast, SD patients displayed an elevation of Specific Episode, Extended Episode, and General Semantic details exclusively during future simulation relative to Controls, which related to integrity of medial and lateral parietal regions. Our findings suggest that the compensatory external details generated during future simulation comprise an array of episodic and semantic details that vary in terms of specificity and self-relevance. Moreover, these profiles appear to be differentially affected depending on the locus of underlying neuropathology in dementia. Adopting a fine-grained approach to external details provides important information regarding the interplay between episodic and semantic content during future stimulation and highlights the differential vulnerability and preservation of distinct components of the constructed narrative in clinical disorders.

Diagnostic test accuracy for use of machine learning in diagnosis of autism spectrum disorder: A Systematic Review and Meta-Analysis (Preprint)

2019 ◽  
Author(s):  
Sun Jae Moon ◽  
Jin Seub Hwang ◽  
Rajesh Kana ◽  
John Torous ◽  
Jung Won Kim
Keyword(s):  
Machine Learning ◽  
Systematic Review ◽  
Autism Spectrum Disorder ◽  
Meta Analysis ◽  
Learning Algorithms ◽  
Structural Mri ◽  
Autism Spectrum ◽  
Machine Learning Algorithms ◽  
Spectrum Disorder ◽  
Test Accuracy

BACKGROUND Over the recent years, machine learning algorithms have been more widely and increasingly applied in biomedical fields. In particular, its application has been drawing more attention in the field of psychiatry, for instance, as diagnostic tests/tools for autism spectrum disorder. However, given its complexity and potential clinical implications, there is ongoing need for further research on its accuracy. OBJECTIVE The current study aims to summarize the evidence for the accuracy of use of machine learning algorithms in diagnosing autism spectrum disorder (ASD) through systematic review and meta-analysis. METHODS MEDLINE, Embase, CINAHL Complete (with OpenDissertations), PsyINFO and IEEE Xplore Digital Library databases were searched on November 28th, 2018. Studies, which used a machine learning algorithm partially or fully in classifying ASD from controls and provided accuracy measures, were included in our analysis. Bivariate random effects model was applied to the pooled data in meta-analysis. Subgroup analysis was used to investigate and resolve the source of heterogeneity between studies. True-positive, false-positive, false negative and true-negative values from individual studies were used to calculate the pooled sensitivity and specificity values, draw SROC curves, and obtain area under the curve (AUC) and partial AUC. RESULTS A total of 43 studies were included for the final analysis, of which meta-analysis was performed on 40 studies (53 samples with 12,128 participants). A structural MRI subgroup meta-analysis (12 samples with 1,776 participants) showed the sensitivity at 0.83 (95% CI-0.76 to 0.89), specificity at 0.84 (95% CI -0.74 to 0.91), and AUC/pAUC at 0.90/0.83. An fMRI/deep neural network (DNN) subgroup meta-analysis (five samples with 1,345 participants) showed the sensitivity at 0.69 (95% CI- 0.62 to 0.75), the specificity at 0.66 (95% CI -0.61 to 0.70), and AUC/pAUC at 0.71/0.67. CONCLUSIONS Machine learning algorithms that used structural MRI features in diagnosis of ASD were shown to have accuracy that is similar to currently used diagnostic tools.

Sign in / Sign up

Export Citation Format

Share Document