» Articles » PMID: 31781290

Resting-State Functional Network Scale Effects and Statistical Significance-Based Feature Selection in Machine Learning Classification

Overview
Publisher Hindawi
Date 2019 Nov 30
PMID 31781290
Citations 5
Authors
Affiliations
Soon will be listed here.
Abstract

In recent years, functional brain network topological features have been widely used as classification features. Previous studies have found that network node scale differences caused by different network parcellation definitions significantly affect the structure of the constructed network and its topological properties. However, we still do not know how network scale differences affect the classification accuracy, performance of classification features, and effectiveness of the feature selection strategy using values in terms of the machine learning method. This study used five scale parcellations, involving 90, 256, 497, 1003, and 1501 nodes. Three local properties of resting-state functional brain networks were selected (degree, betweenness centrality, and nodal efficiency), and the support vector machine method was used to construct classifiers to identify patients with major depressive disorder. We analyzed the impact of the five scales on classification accuracy. In addition, the effectiveness and redundancy of features obtained by the different scale parcellations were compared. Finally, traditional statistical significance ( value) was verified as a feature selection criterion. The results showed that the feature effectiveness of different scales was similar; in other words, parcellation with more regions did not provide more effective discriminative features. Nevertheless, parcellation with more regions did provide a greater quantity of discriminative features, which led to an improvement in the accuracy of the classification. However, due to the close distance between brain regions, the redundancy of parcellation with more regions was also greater. The traditional value feature selection strategy is feasible with different scales, but our analysis showed that the traditional < 0.05 threshold was too strict for feature selection. This study provides an important reference for the selection of network scales when applying topological properties of brain networks to machine learning methods.

Citing Articles

Prediction models for lymph node metastasis in cervical cancer based on preoperative heart rate variability.

Guan W, Wang Y, Zhao H, Lu H, Zhang S, Liu J Front Neurosci. 2024; 18:1275487.

PMID: 38410157 PMC: 10894972. DOI: 10.3389/fnins.2024.1275487.


The diagnostic performance of machine learning based on resting-state functional magnetic resonance imaging data for major depressive disorders: a systematic review and meta-analysis.

Chen Y, Zhao W, Yi S, Liu J Front Neurosci. 2023; 17:1174080.

PMID: 37811326 PMC: 10559726. DOI: 10.3389/fnins.2023.1174080.


Sampling inequalities affect generalization of neuroimaging-based diagnostic classifiers in psychiatry.

Chen Z, Hu B, Liu X, Becker B, Eickhoff S, Miao K BMC Med. 2023; 21(1):241.

PMID: 37400814 PMC: 10318841. DOI: 10.1186/s12916-023-02941-4.


Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis: A Systematic Review.

Chen Z, Liu X, Yang Q, Wang Y, Miao K, Gong Z JAMA Netw Open. 2023; 6(3):e231671.

PMID: 36877519 PMC: 9989906. DOI: 10.1001/jamanetworkopen.2023.1671.


Feature Selection is Critical for 2-Year Prognosis in Advanced Stage High Grade Serous Ovarian Cancer by Using Machine Learning.

Laios A, Katsenou A, Tan Y, Johnson R, Otify M, Kaufmann A Cancer Control. 2021; 28:10732748211044678.

PMID: 34693730 PMC: 8549478. DOI: 10.1177/10732748211044678.

References
1.
Cheng C, Chen J, Cao X, Guo H . Comparison of Local Information Indices Applied in Resting State Functional Brain Network Connectivity Prediction. Front Neurosci. 2017; 10:585. PMC: 5186779. DOI: 10.3389/fnins.2016.00585. View

2.
Pereira F, Mitchell T, Botvinick M . Machine learning classifiers and fMRI: a tutorial overview. Neuroimage. 2008; 45(1 Suppl):S199-209. PMC: 2892746. DOI: 10.1016/j.neuroimage.2008.11.007. View

3.
Ou J, Xie L, Li X, Zhu D, Terry D, Puente A . Atomic connectomics signatures for characterization and differentiation of mild cognitive impairment. Brain Imaging Behav. 2014; 9(4):663-77. DOI: 10.1007/s11682-014-9320-1. View

4.
Kloppel S, Abdulkadir A, Jack Jr C, Koutsouleris N, Mourao-Miranda J, Vemuri P . Diagnostic neuroimaging across diseases. Neuroimage. 2011; 61(2):457-63. PMC: 3420067. DOI: 10.1016/j.neuroimage.2011.11.002. View

5.
Beheshti I, Demirel H . Feature-ranking-based Alzheimer's disease classification from structural MRI. Magn Reson Imaging. 2015; 34(3):252-63. DOI: 10.1016/j.mri.2015.11.009. View