Sign-Consistency Based Variable Importance for Machine Learning in Brain Imaging

Gómez-Verdejo, Vanessa; Parrado-Hernández, Emilio; Tohka, Jussi; Initiative, Alzheimer’s Disease Neuroimaging

doi:10.1007/s12021-019-9415-3

Cited by 21 publications

(15 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This mapping allows knowing the contribution of the features to the classification decision. Neu-roMiner has implemented the approach proposed by Gómez-Verdejo et al, 33…”

Section: Machine Learning Classificationmentioning

confidence: 99%

Differentiation of multiple system atrophy subtypes by gray matter atrophy

Campabadal

Abós

Segura

et al. 2021

Journal of Neuroimaging

View full text Add to dashboard Cite

Background and Purpose: Multiple system atrophy(MSA) is a rare adult-onset synucleinopathy that can be divided in two subtypes depending on whether the prevalence of its symptoms is more parkinsonian or cerebellar (MSA-P and MSA-C, respectively). The aim of this work is to investigate the structural MRI changes able to discriminate MSA phenotypes. Methods:The sample includes 31 MSA patients (15 MSA-C and 16 MSA-P) and 39 healthy controls. Participants underwent a comprehensive motor and neuropsychological battery. MRI data were acquired with a 3T scanner (MAGNETOM Trio, Siemens, Germany).FreeSurfer was used to obtain volumetric and cortical thickness measures. A Support Vector Machine (SVM) algorithm was used to assess the classification between patients' group using cortical and subcortical structural data. Results:After correction for multiple comparisons, MSA-C patients had greater atrophy than MSA-P in the left cerebellum, whereas MSA-P showed reduced volume bilaterally in the pallidum and putamen. Using deep gray matter volume ratios and mean cortical thickness as features, the SVM algorithm provided a consistent classification between MSA-C and MSA-P patients (balanced accuracy 74.2%, specificity 75.0%, and sensitivity 73.3%).The cerebellum, putamen, thalamus, ventral diencephalon, pallidum, and caudate were the most contributing features to the classification decision (z > 3.28; p < .05 [false discovery rate]). Conclusions: MSA-C and MSA-P with similar disease severity and duration have a differential distribution of gray matter atrophy. Although cerebellar atrophy is a clear differentiator between groups, thalamic and basal ganglia structures are also relevant contributors to distinguishing MSA subtypes.

show abstract

“…This mapping allows knowing the contribution of the features to the classification decision. Neu-roMiner has implemented the approach proposed by Gómez-Verdejo et al, 33…”

Section: Machine Learning Classificationmentioning

confidence: 99%

Differentiation of multiple system atrophy subtypes by gray matter atrophy

Campabadal

Abós

Segura

et al. 2021

Journal of Neuroimaging

View full text Add to dashboard Cite

show abstract

“…Regularized linear decision functions have been recently applied to neuroimaging for detecting activation patterns, and compared to parametric hypothesis testing, such as univariate t-tests [24,22,23]. In general, they have limited their analyses to provide in-sample estimates based on resampling, failing to demonstrate their out-of-sample performance in terms of confidence intervals.…”

Section: Linear Decision Functions: a Small Upper Boundmentioning

confidence: 99%

Statistical agnostic mapping: a framework in neuroimaging based on concentration inequalities

Górriz

2019

Preprint

View full text Add to dashboard Cite

In the 70s a novel branch of statistics emerged focusing its effort in selecting a function in the pattern recognition problem, which fulfils a definite relationship between the quality of the approximation and its complexity. These data-driven approaches are mainly devoted to problems of estimating dependencies with limited sample sizes and comprise all the empirical out-of sample generalization approaches, e.g. cross validation (CV) approaches. Although the latter are not designed for testing competing hypothesis or comparing different models in neuroimaging, there are a number of theoretical developments within this theory which could be employed to derive a Statistical Agnostic (non-parametric) Mapping (SAM) at voxel or multi-voxel level. Moreover, SAMs could relieve i) the problem of instability in limited sample sizes when estimating the actual risk via the CV approaches, e.g. large error bars, and provide ii) an alternative way of Family-wise-error (FWE) corrected p-value maps in inferential statistics for hypothesis testing. In this sense, we propose a novel framework in neuroimaging based on concentration inequalities, which results in (i) a rigorous development for model validation with a small sample/dimension ratio, and (ii) a less-conservative procedure than FWE p-value correction, to determine the brain significance maps from the inferences made using small upper bounds of the actual risk. effects (large or subtle) in binary group comparisons. The critical p-value (significance vs. not significant) is often complemented by effect-size measures of the magnitude of the phenomenon H 0 [2].

show abstract

“…The variable selection is the most significant variables with their perspective. Variable selections only provide the rank of highest important variables, which means that techniques didn't have no rules in selecting the suitable range of variable important [58]. Hence, we choose the 30 highest variable importance.…”

Section: Datamentioning

confidence: 99%

Accurate and Hybrid Regularization - Robust Regression Model in Handling Multicollinearity and Outlier Using 8SC for Big Data

Mukhtar,

Ali,

Javaid

et al. 2021

MMEP

View full text Add to dashboard Cite

Regressions have been continuously received great attention. However, there are still open issues in regression, and two of the issues is regression with multicollinearity and outlier. Regularization (Ridge, Lasso, and Elastic Net) techniques implement a means to control regression coefficients. The methods can decrease the variance and reduce our sample error for tackle multicollinearity. In robust regression, it is a form of regression method designed to overcome outliers. Robust regression is an important method for analyzing data that are infected with outliers. The data have been interacted on the second order interaction. The data contained 435 different independent interaction variables. The primary focus of this paper is to analyze and compare the impact of three different variable selection techniques regularization regression algorithms for the data seaweed drying. After that, it will be analyzed through robust regression (Tukey Bi-Square, Hampel, and Huber). As the result, the Lasso-Hampel was better than others with the MAE (4.09641), RMSE (5.275992), MAPE (7.9962), SSE (182491.2), R-square (0.6514791), and R-square Adjusted (0.649279). The method of Lasso-Hampel is able to be relied on investigation of the accuracy in big data obtained from regularization and robust regression.

show abstract

Sign-Consistency Based Variable Importance for Machine Learning in Brain Imaging

Cited by 21 publications

References 51 publications

Differentiation of multiple system atrophy subtypes by gray matter atrophy

Differentiation of multiple system atrophy subtypes by gray matter atrophy

Statistical agnostic mapping: a framework in neuroimaging based on concentration inequalities

Accurate and Hybrid Regularization - Robust Regression Model in Handling Multicollinearity and Outlier Using 8SC for Big Data

Contact Info

Product

Resources

About