Literature DB >> 33505239

Machine Learning-Based Identification of Suicidal Risk in Patients With Schizophrenia Using Multi-Level Resting-State fMRI Features.

Bartosz Bohaterewicz1,2, Anna M Sobczak1, Igor Podolak3, Bartosz Wójcik3, Dagmara Mȩtel4, Adrian A Chrobak5, Magdalena Fa Frowicz1, Marcin Siwek6, Dominika Dudek5, Tadeusz Marek1.   

Abstract

BACKGROUND: Some studies suggest that as much as 40% of all causes of death in a group of patients with schizophrenia can be attributed to suicides and compared with the general population, patients with schizophrenia have an 8.5-fold greater suicide risk (SR). There is a vital need for accurate and reliable methods to predict the SR among patients with schizophrenia based on biological measures. However, it is unknown whether the suicidal risk in schizophrenia can be related to alterations in spontaneous brain activity, or if the resting-state functional magnetic resonance imaging (rsfMRI) measures can be used alongside machine learning (ML) algorithms in order to identify patients with SR.
METHODS: Fifty-nine participants including patients with schizophrenia with and without SR as well as age and gender-matched healthy underwent 13 min resting-state functional magnetic resonance imaging. Both static and dynamic indexes of the amplitude of low-frequency fluctuation (ALFF), the fractional amplitude of low-frequency fluctuations (fALFF), regional homogeneity as well as functional connectivity (FC) were calculated and used as an input for five machine learning algorithms: Gradient boosting (GB), LASSO, Logistic Regression (LR), Random Forest and Support Vector Machine.
RESULTS: All groups revealed different intra-network functional connectivity in ventral DMN and anterior SN. The best performance was reached for the LASSO applied to FC with an accuracy of 70% and AUROC of 0.76 (p < 0.05). Significant classification ability was also reached for GB and LR using fALFF and ALFF measures.
CONCLUSION: Our findings suggest that SR in schizophrenia can be seen on the level of DMN and SN functional connectivity alterations. ML algorithms were able to significantly differentiate SR patients. Our results could be useful in developing neuromarkers of SR in schizophrenia based on non-invasive rsfMRI.
Copyright © 2021 Bohaterewicz, Sobczak, Podolak, Wójcik, Mȩtel, Chrobak, Fa̧frowicz, Siwek, Dudek and Marek.

Entities:  

Keywords:  classification; feature selection; gradient boosting; machine learning; mental pain; resting state fMRI; schizophrenia; suicidal ideations

Year:  2021        PMID: 33505239      PMCID: PMC7829970          DOI: 10.3389/fnins.2020.605697

Source DB:  PubMed          Journal:  Front Neurosci        ISSN: 1662-453X            Impact factor:   4.677


  47 in total

1.  Aberrant salience network (bilateral insula and anterior cingulate cortex) connectivity during information processing in schizophrenia.

Authors:  Thomas P White; Verghese Joseph; Susan T Francis; Peter F Liddle
Journal:  Schizophr Res       Date:  2010-08-17       Impact factor: 4.939

2.  A component based noise correction method (CompCor) for BOLD and perfusion based fMRI.

Authors:  Yashar Behzadi; Khaled Restom; Joy Liau; Thomas T Liu
Journal:  Neuroimage       Date:  2007-05-03       Impact factor: 6.556

3.  Alterations of functional connectivity and intrinsic activity within the cingulate cortex of suicidal ideators.

Authors:  Henry W Chase; Anna Maria Segreti; Timothy A Keller; Vladimir L Cherkassky; Marcel A Just; Lisa A Pan; David A Brent
Journal:  J Affect Disord       Date:  2017-01-15       Impact factor: 4.839

4.  Decoding subject-driven cognitive states with whole-brain connectivity patterns.

Authors:  W R Shirer; S Ryali; E Rykhlevskaia; V Menon; M D Greicius
Journal:  Cereb Cortex       Date:  2011-05-26       Impact factor: 5.357

5.  DPABI: Data Processing & Analysis for (Resting-State) Brain Imaging.

Authors:  Chao-Gan Yan; Xin-Di Wang; Xi-Nian Zuo; Yu-Feng Zang
Journal:  Neuroinformatics       Date:  2016-07

Review 6.  Overview of functional magnetic resonance imaging.

Authors:  Gary H Glover
Journal:  Neurosurg Clin N Am       Date:  2011-04       Impact factor: 2.509

7.  Functional network organization of the human brain.

Authors:  Jonathan D Power; Alexander L Cohen; Steven M Nelson; Gagan S Wig; Kelly Anne Barnes; Jessica A Church; Alecia C Vogel; Timothy O Laumann; Fran M Miezin; Bradley L Schlaggar; Steven E Petersen
Journal:  Neuron       Date:  2011-11-17       Impact factor: 17.173

Review 8.  Machine learning classifiers and fMRI: a tutorial overview.

Authors:  Francisco Pereira; Tom Mitchell; Matthew Botvinick
Journal:  Neuroimage       Date:  2008-11-21       Impact factor: 6.556

9.  Control-related frontal-striatal function is associated with past suicidal ideation and behavior in patients with recent-onset psychotic major mood disorders.

Authors:  Michael J Minzenberg; Tyler A Lesh; Tara A Niendam; Jong H Yoon; Yaoan Cheng; Remy N Rhoades; Cameron S Carter
Journal:  J Affect Disord       Date:  2015-09-03       Impact factor: 4.839

10.  Machine learning of neural representations of suicide and emotion concepts identifies suicidal youth.

Authors:  Marcel Adam Just; Lisa Pan; Vladimir L Cherkassky; Dana L McMakin; Christine Cha; Matthew K Nock; David Brent
Journal:  Nat Hum Behav       Date:  2017-10-30
View more
  1 in total

1.  Machine Learning of Schizophrenia Detection with Structural and Functional Neuroimaging.

Authors:  Dafa Shi; Yanfei Li; Haoran Zhang; Xiang Yao; Siyuan Wang; Guangsong Wang; Ke Ren
Journal:  Dis Markers       Date:  2021-06-09       Impact factor: 3.434

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.