Abstract
Network-based representations have introduced a revolution in neuroscience, expanding the understanding of the brain from the activity of individual regions to the interactions between them. This augmented network view comes at the cost of high dimensionality, which hinders both our capacity of deciphering the main mechanisms behind pathologies, and the significance of any statistical and/or machine learning task used in processing this data. A link selection method, allowing to remove irrelevant connections in a given scenario, is an obvious solution that provides improved utilization of these network representations. In this contribution we review a large set of statistical and machine learning link selection methods and evaluate them on real brain functional networks. Results indicate that most methods perform in a qualitatively similar way, with NBS (Network Based Statistics) winning in terms of quantity of retained information, AnovaNet in terms of stability and ExT (Extra Trees) in terms of lower computational cost. While machine learning methods are conceptually more complex than statistical ones, they do not yield a clear advantage. At the same time, the high heterogeneity in the set of links retained by each method suggests that they are offering complementary views to the data. The implications of these results in neuroscience tasks are finally discussed.
Highlights
IntroductionSince the beginning of modern neuroscience, one of the main focuses has been describing the differences between groups of subjects, with one of them usually comprising people suffering from a given condition, and the other matched healthy control subjects
The resulting classification score is used as a measure of the quantity of information retained by each link selection method
Excluding three outliers (SLDA, False Discovery Rate (FDR) and Bonferroni), the 16 remaining methods are included between Network Based Statistics (NBS) (AUC of 0.869) and Elastic-Net (AUC of 0.822)
Summary
Since the beginning of modern neuroscience, one of the main focuses has been describing the differences between groups of subjects, with one of them usually comprising people suffering from a given condition, and the other matched healthy control subjects. The objective is to describe what is significantly different between controls and patients, what is potentially causing the condition and, ideally, how can its impact be mitigated. This yields another benefit, i.e., validation; if no differences are detected in patients suffering from a condition that is profoundly modifying the cognitive capabilities, as e.g., Alzheimer’s or Parkinson’s diseases, one may infer that the data used in the comparison are not characterising important aspects of brain activity
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
