Local-structure-preservation and redundancy-removal-based feature selection method and its application to the identification of biomarkers for schizophrenia
•We propose a new method, LRFS, to identify features with enhanced discriminability.•It preserves sample similarity and enhance independence among features.•It excels over 9 comparison methods across 12 datasets in group differentiation.•It detects crucial features that differentiate schizophrenia (...
Saved in:
| Published in | NeuroImage (Orlando, Fla.) Vol. 299; p. 120839 |
|---|---|
| Main Authors | , , , , |
| Format | Journal Article |
| Language | English |
| Published |
United States
Elsevier Inc
01.10.2024
Elsevier Limited Elsevier |
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | •We propose a new method, LRFS, to identify features with enhanced discriminability.•It preserves sample similarity and enhance independence among features.•It excels over 9 comparison methods across 12 datasets in group differentiation.•It detects crucial features that differentiate schizophrenia (SZ) from healthy controls.•It reveals SZ-related abnormalities that are closely linked to symptoms.
Accurate diagnosis of mental disorders is expected to be achieved through the identification of reliable neuroimaging biomarkers with the help of cutting-edge feature selection techniques. However, existing feature selection methods often fall short in capturing the local structural characteristics among samples and effectively eliminating redundant features, resulting in inadequate performance in disorder prediction. To address this gap, we propose a novel supervised method named local-structure-preservation and redundancy-removal-based feature selection (LRFS), and then apply it to the identification of meaningful biomarkers for schizophrenia (SZ). LRFS method leverages graph-based regularization to preserve original sample similarity relationships during data transformation, thus retaining crucial local structure information. Additionally, it introduces redundancy-removal regularization based on interrelationships among features to exclude similar and redundant features from high-dimensional data. Moreover, LRFS method incorporates l2,1 sparse regularization that enables selecting a sparse and noise-robust feature subset. Experimental evaluations on eight public datasets with diverse properties demonstrate the superior performance of our method over nine popular feature selection methods in identifying discriminative features, with average classification accuracy gains ranging from 1.30 % to 9.11 %. Furthermore, the LRFS method demonstrates superior discriminability in four functional magnetic resonance imaging (fMRI) datasets from 708 healthy controls (HCs) and 537 SZ patients, with an average increase in classification accuracy ranging from 1.89 % to 9.24 % compared to other nine methods. Notably, our method reveals reproducible and significant changes in SZ patients relative to HCs across the four datasets, predominantly in the thalamus-related functional network connectivity, which exhibit a significant correlation with clinical symptoms. Convergence analysis, parameter sensitivity analysis, and ablation studies further demonstrate the effectiveness and robustness of our method. In short, our proposed feature selection method effectively identifies discriminative and reliable features that hold the potential to be biomarkers, paving the way for the elucidation of brain abnormalities and the advancement of precise diagnosis of mental disorders. |
|---|---|
| AbstractList | Accurate diagnosis of mental disorders is expected to be achieved through the identification of reliable neuroimaging biomarkers with the help of cutting-edge feature selection techniques. However, existing feature selection methods often fall short in capturing the local structural characteristics among samples and effectively eliminating redundant features, resulting in inadequate performance in disorder prediction. To address this gap, we propose a novel supervised method named local-structure-preservation and redundancy-removal-based feature selection (LRFS), and then apply it to the identification of meaningful biomarkers for schizophrenia (SZ). LRFS method leverages graph-based regularization to preserve original sample similarity relationships during data transformation, thus retaining crucial local structure information. Additionally, it introduces redundancy-removal regularization based on interrelationships among features to exclude similar and redundant features from high-dimensional data. Moreover, LRFS method incorporates l
sparse regularization that enables selecting a sparse and noise-robust feature subset. Experimental evaluations on eight public datasets with diverse properties demonstrate the superior performance of our method over nine popular feature selection methods in identifying discriminative features, with average classification accuracy gains ranging from 1.30% to 9.11%. Furthermore, the LRFS method demonstrates superior discriminability in four functional magnetic resonance imaging (fMRI) datasets from 708 healthy controls (HCs) and 537 SZ patients, with an average increase in classification accuracy ranging from 1.89% to 9.24% compared to other nine methods. Notably, our method reveals reproducible and significant changes in SZ patients relative to HCs across the four datasets, predominantly in the thalamus-related functional network connectivity, which exhibit a significant correlation with clinical symptoms. Convergence analysis, parameter sensitivity analysis, and ablation studies further demonstrate the effectiveness and robustness of our method. In short, our proposed feature selection method effectively identifies discriminative and reliable features that hold the potential to be biomarkers, paving the way for the elucidation of brain abnormalities and the advancement of precise diagnosis of mental disorders. Accurate diagnosis of mental disorders is expected to be achieved through the identification of reliable neuroimaging biomarkers with the help of cutting-edge feature selection techniques. However, existing feature selection methods often fall short in capturing the local structural characteristics among samples and effectively eliminating redundant features, resulting in inadequate performance in disorder prediction. To address this gap, we propose a novel supervised method named local-structure-preservation and redundancy-removal-based feature selection (LRFS), and then apply it to the identification of meaningful biomarkers for schizophrenia (SZ). LRFS method leverages graph-based regularization to preserve original sample similarity relationships during data transformation, thus retaining crucial local structure information. Additionally, it introduces redundancy-removal regularization based on interrelationships among features to exclude similar and redundant features from high-dimensional data. Moreover, LRFS method incorporates l2,1 sparse regularization that enables selecting a sparse and noise-robust feature subset. Experimental evaluations on eight public datasets with diverse properties demonstrate the superior performance of our method over nine popular feature selection methods in identifying discriminative features, with average classification accuracy gains ranging from 1.30 % to 9.11 %. Furthermore, the LRFS method demonstrates superior discriminability in four functional magnetic resonance imaging (fMRI) datasets from 708 healthy controls (HCs) and 537 SZ patients, with an average increase in classification accuracy ranging from 1.89 % to 9.24 % compared to other nine methods. Notably, our method reveals reproducible and significant changes in SZ patients relative to HCs across the four datasets, predominantly in the thalamus-related functional network connectivity, which exhibit a significant correlation with clinical symptoms. Convergence analysis, parameter sensitivity analysis, and ablation studies further demonstrate the effectiveness and robustness of our method. In short, our proposed feature selection method effectively identifies discriminative and reliable features that hold the potential to be biomarkers, paving the way for the elucidation of brain abnormalities and the advancement of precise diagnosis of mental disorders. Accurate diagnosis of mental disorders is expected to be achieved through the identification of reliable neuroimaging biomarkers with the help of cutting-edge feature selection techniques. However, existing feature selection methods often fall short in capturing the local structural characteristics among samples and effectively eliminating redundant features, resulting in inadequate performance in disorder prediction. To address this gap, we propose a novel supervised method named local-structure-preservation and redundancy-removal-based feature selection (LRFS), and then apply it to the identification of meaningful biomarkers for schizophrenia (SZ). LRFS method leverages graph-based regularization to preserve original sample similarity relationships during data transformation, thus retaining crucial local structure information. Additionally, it introduces redundancy-removal regularization based on interrelationships among features to exclude similar and redundant features from high-dimensional data. Moreover, LRFS method incorporates l2,1 sparse regularization that enables selecting a sparse and noise-robust feature subset. Experimental evaluations on eight public datasets with diverse properties demonstrate the superior performance of our method over nine popular feature selection methods in identifying discriminative features, with average classification accuracy gains ranging from 1.30 % to 9.11 %. Furthermore, the LRFS method demonstrates superior discriminability in four functional magnetic resonance imaging (fMRI) datasets from 708 healthy controls (HCs) and 537 SZ patients, with an average increase in classification accuracy ranging from 1.89 % to 9.24 % compared to other nine methods. Notably, our method reveals reproducible and significant changes in SZ patients relative to HCs across the four datasets, predominantly in the thalamus-related functional network connectivity, which exhibit a significant correlation with clinical symptoms. Convergence analysis, parameter sensitivity analysis, and ablation studies further demonstrate the effectiveness and robustness of our method. In short, our proposed feature selection method effectively identifies discriminative and reliable features that hold the potential to be biomarkers, paving the way for the elucidation of brain abnormalities and the advancement of precise diagnosis of mental disorders.Accurate diagnosis of mental disorders is expected to be achieved through the identification of reliable neuroimaging biomarkers with the help of cutting-edge feature selection techniques. However, existing feature selection methods often fall short in capturing the local structural characteristics among samples and effectively eliminating redundant features, resulting in inadequate performance in disorder prediction. To address this gap, we propose a novel supervised method named local-structure-preservation and redundancy-removal-based feature selection (LRFS), and then apply it to the identification of meaningful biomarkers for schizophrenia (SZ). LRFS method leverages graph-based regularization to preserve original sample similarity relationships during data transformation, thus retaining crucial local structure information. Additionally, it introduces redundancy-removal regularization based on interrelationships among features to exclude similar and redundant features from high-dimensional data. Moreover, LRFS method incorporates l2,1 sparse regularization that enables selecting a sparse and noise-robust feature subset. Experimental evaluations on eight public datasets with diverse properties demonstrate the superior performance of our method over nine popular feature selection methods in identifying discriminative features, with average classification accuracy gains ranging from 1.30 % to 9.11 %. Furthermore, the LRFS method demonstrates superior discriminability in four functional magnetic resonance imaging (fMRI) datasets from 708 healthy controls (HCs) and 537 SZ patients, with an average increase in classification accuracy ranging from 1.89 % to 9.24 % compared to other nine methods. Notably, our method reveals reproducible and significant changes in SZ patients relative to HCs across the four datasets, predominantly in the thalamus-related functional network connectivity, which exhibit a significant correlation with clinical symptoms. Convergence analysis, parameter sensitivity analysis, and ablation studies further demonstrate the effectiveness and robustness of our method. In short, our proposed feature selection method effectively identifies discriminative and reliable features that hold the potential to be biomarkers, paving the way for the elucidation of brain abnormalities and the advancement of precise diagnosis of mental disorders. •We propose a new method, LRFS, to identify features with enhanced discriminability.•It preserves sample similarity and enhance independence among features.•It excels over 9 comparison methods across 12 datasets in group differentiation.•It detects crucial features that differentiate schizophrenia (SZ) from healthy controls.•It reveals SZ-related abnormalities that are closely linked to symptoms. Accurate diagnosis of mental disorders is expected to be achieved through the identification of reliable neuroimaging biomarkers with the help of cutting-edge feature selection techniques. However, existing feature selection methods often fall short in capturing the local structural characteristics among samples and effectively eliminating redundant features, resulting in inadequate performance in disorder prediction. To address this gap, we propose a novel supervised method named local-structure-preservation and redundancy-removal-based feature selection (LRFS), and then apply it to the identification of meaningful biomarkers for schizophrenia (SZ). LRFS method leverages graph-based regularization to preserve original sample similarity relationships during data transformation, thus retaining crucial local structure information. Additionally, it introduces redundancy-removal regularization based on interrelationships among features to exclude similar and redundant features from high-dimensional data. Moreover, LRFS method incorporates l2,1 sparse regularization that enables selecting a sparse and noise-robust feature subset. Experimental evaluations on eight public datasets with diverse properties demonstrate the superior performance of our method over nine popular feature selection methods in identifying discriminative features, with average classification accuracy gains ranging from 1.30 % to 9.11 %. Furthermore, the LRFS method demonstrates superior discriminability in four functional magnetic resonance imaging (fMRI) datasets from 708 healthy controls (HCs) and 537 SZ patients, with an average increase in classification accuracy ranging from 1.89 % to 9.24 % compared to other nine methods. Notably, our method reveals reproducible and significant changes in SZ patients relative to HCs across the four datasets, predominantly in the thalamus-related functional network connectivity, which exhibit a significant correlation with clinical symptoms. Convergence analysis, parameter sensitivity analysis, and ablation studies further demonstrate the effectiveness and robustness of our method. In short, our proposed feature selection method effectively identifies discriminative and reliable features that hold the potential to be biomarkers, paving the way for the elucidation of brain abnormalities and the advancement of precise diagnosis of mental disorders. Accurate diagnosis of mental disorders is expected to be achieved through the identification of reliable neuroimaging biomarkers with the help of cutting-edge feature selection techniques. However, existing feature selection methods often fall short in capturing the local structural characteristics among samples and effectively eliminating redundant features, resulting in inadequate performance in disorder prediction. To address this gap, we propose a novel supervised method named local-structure-preservation and redundancy-removal-based feature selection (LRFS), and then apply it to the identification of meaningful biomarkers for schizophrenia (SZ). LRFS method leverages graph-based regularization to preserve original sample similarity relationships during data transformation, thus retaining crucial local structure information. Additionally, it introduces redundancy-removal regularization based on interrelationships among features to exclude similar and redundant features from high-dimensional data. Moreover, LRFS method incorporates l 2 , 1 sparse regularization that enables selecting a sparse and noise-robust feature subset. Experimental evaluations on eight public datasets with diverse properties demonstrate the superior performance of our method over nine popular feature selection methods in identifying discriminative features, with average classification accuracy gains ranging from 1.30 % to 9.11 %. Furthermore, the LRFS method demonstrates superior discriminability in four functional magnetic resonance imaging (fMRI) datasets from 708 healthy controls (HCs) and 537 SZ patients, with an average increase in classification accuracy ranging from 1.89 % to 9.24 % compared to other nine methods. Notably, our method reveals reproducible and significant changes in SZ patients relative to HCs across the four datasets, predominantly in the thalamus-related functional network connectivity, which exhibit a significant correlation with clinical symptoms. Convergence analysis, parameter sensitivity analysis, and ablation studies further demonstrate the effectiveness and robustness of our method. In short, our proposed feature selection method effectively identifies discriminative and reliable features that hold the potential to be biomarkers, paving the way for the elucidation of brain abnormalities and the advancement of precise diagnosis of mental disorders. |
| ArticleNumber | 120839 |
| Author | Xing, Ying Du, Yuhui Pearlson, Godfrey D. Calhoun, Vince D. Kochunov, Peter |
| AuthorAffiliation | a School of Computer and Information Technology, Shanxi University, Taiyuan, China b Departments of Psychiatry and Neurobiology, Yale University, New Haven, CT, USA d Tri-Institutional Center for Translational Research in Neuroimaging and Data Science, Georgia State University, Georgia Institute of Technology, Emory University, Atlanta, GA, USA c Maryland Psychiatric Research Center and Department of Psychiatry, University of Maryland, School of Medicine, Baltimore, MD, USA |
| AuthorAffiliation_xml | – name: b Departments of Psychiatry and Neurobiology, Yale University, New Haven, CT, USA – name: a School of Computer and Information Technology, Shanxi University, Taiyuan, China – name: d Tri-Institutional Center for Translational Research in Neuroimaging and Data Science, Georgia State University, Georgia Institute of Technology, Emory University, Atlanta, GA, USA – name: c Maryland Psychiatric Research Center and Department of Psychiatry, University of Maryland, School of Medicine, Baltimore, MD, USA |
| Author_xml | – sequence: 1 givenname: Ying orcidid: 0000-0002-4479-686X surname: Xing fullname: Xing, Ying organization: School of Computer and Information Technology, Shanxi University, Taiyuan, China – sequence: 2 givenname: Godfrey D. surname: Pearlson fullname: Pearlson, Godfrey D. organization: Departments of Psychiatry and Neurobiology, Yale University, New Haven, CT, USA – sequence: 3 givenname: Peter surname: Kochunov fullname: Kochunov, Peter organization: Maryland Psychiatric Research Center and Department of Psychiatry, University of Maryland, School of Medicine, Baltimore, MD, USA – sequence: 4 givenname: Vince D. orcidid: 0000-0001-9058-0747 surname: Calhoun fullname: Calhoun, Vince D. organization: Tri-Institutional Center for Translational Research in Neuroimaging and Data Science, Georgia State University, Georgia Institute of Technology, Emory University, Atlanta, GA, USA – sequence: 5 givenname: Yuhui orcidid: 0000-0002-0079-8177 surname: Du fullname: Du, Yuhui email: duyuhui@sxu.edu.cn organization: School of Computer and Information Technology, Shanxi University, Taiyuan, China |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/39251116$$D View this record in MEDLINE/PubMed |
| BookMark | eNqFksuO1DAQRSM0iHnAL6BIbNik8SNO4hWCEY-RWmIDa6vaLne7SezGTloavoWPxenMDAwbVrbsc2_ZVfeyOPPBY1GUlKwooc2b_crjFIMbYIsrRli9oox0XD4pLiiRopKiZWfzXvCqo1SeF5cp7Qkhktbds-KcSyYopc1F8WsdNPRVGuOkxylidYiYMB5hdMGX4E0Z0UzegNe3VcQhHDO9gYSmtAizokzYoz7hA467YE4qN6YSDofe6cVpDOW4w9IZ9KOz96fBlhsXBojfMabShlgmvXM_w2EX0Tt4Xjy10Cd8cbdeFd8-fvh6_blaf_l0c_1uXem6lmNF0XYdEdpoZpBRSYG3rdCyaSkYYIJpwaCVkmnSdtxsWEt0wy1w7LRlQvCr4mbxNQH26hBzX-OtCuDU6SDErYI4Ot2jsjaLoIFaGFNvZNt1uuWCWcFzeY4ke71dvA7TZkCj838j9I9MH994t1PbcFSU1jKPZH7N6zuHGH5MmEY1uKSx78FjmJLiNA-8kUKwjL76B92HKfrcq5lqeCMaSTPVLZSOIaWI9uE1lKg5T2qv_uRJzXlSS56y9OXfv3kQ3gcoA-8XAPN8jg6jStqh12hczKnIDXT_r_Ib3YLoUA |
| Cites_doi | 10.1016/j.asoc.2023.110240 10.1503/jpn.230120 10.3390/ijms24032597 10.3390/healthcare10040643 10.1109/JBHI.2022.3212479 10.1109/TKDE.2023.3303425 10.1109/TNNLS.2013.2287275 10.1016/j.nicl.2020.102348 10.1023/A:1008280620621 10.1007/s12559-021-09981-z 10.1007/s00406-022-01433-5 10.1109/TCYB.2021.3139898 10.1109/TKDE.2017.2763618 10.1016/j.schres.2016.02.039 10.1016/j.patcog.2023.110072 10.1109/TNNLS.2020.3009209 10.1109/TCYB.2022.3160244 10.1016/j.neuroimage.2024.120580 10.1016/j.patcog.2015.12.008 10.1088/1361-6579/acb03c 10.1007/s10489-019-01597-z 10.1002/jmri.28650 10.1111/j.2517-6161.1996.tb02080.x 10.1001/jamapsychiatry.2023.1576 10.1016/j.patcog.2020.107663 10.1016/j.jneumeth.2017.12.005 10.1002/wps.21078 10.1093/schbul/13.2.261 10.1109/TPAMI.2019.2961877 10.1007/s10489-021-02550-9 10.1016/S2215-0366(15)00361-2 10.1007/s10994-012-5284-9 10.1016/j.neuroimage.2019.116456 10.1038/s42003-021-02592-2 10.1186/s12916-023-02941-4 10.1145/3369870 10.1001/jamapsychiatry.2015.0484 10.3389/fnins.2018.00525 10.1016/j.nicl.2020.102375 10.1038/s41583-023-00701-0 10.1016/j.nicl.2022.103135 10.1016/j.isci.2024.109319 10.1016/j.inffus.2020.01.005 10.1038/s41380-022-01635-2 |
| ContentType | Journal Article |
| Copyright | 2024 The Authors Copyright © 2024. Published by Elsevier Inc. 2024. The Authors Copyright © 2024 The Authors. Published by Elsevier Inc. All rights reserved. |
| Copyright_xml | – notice: 2024 The Authors – notice: Copyright © 2024. Published by Elsevier Inc. – notice: 2024. The Authors – notice: Copyright © 2024 The Authors. Published by Elsevier Inc. All rights reserved. |
| DBID | 6I. AAFTH NPM AAYXX CITATION 7TK 8FD FR3 K9. P64 RC3 7X8 5PM DOA |
| DOI | 10.1016/j.neuroimage.2024.120839 |
| DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access PubMed CrossRef Neurosciences Abstracts Technology Research Database Engineering Research Database ProQuest Health & Medical Complete (Alumni) Biotechnology and BioEngineering Abstracts Genetics Abstracts MEDLINE - Academic PubMed Central (Full Participant titles) DOAJ Directory of Open Access Journals |
| DatabaseTitle | PubMed CrossRef ProQuest Health & Medical Complete (Alumni) Genetics Abstracts Engineering Research Database Technology Research Database Neurosciences Abstracts Biotechnology and BioEngineering Abstracts MEDLINE - Academic |
| DatabaseTitleList | PubMed MEDLINE - Academic ProQuest Health & Medical Complete (Alumni) |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Medicine |
| EISSN | 1095-9572 |
| EndPage | 120839 |
| ExternalDocumentID | oai_doaj_org_article_ffe8ca6a45dd4b9788c7352f53cdc3e0 10_1016_j_neuroimage_2024_120839 39251116 S1053811924003367 |
| Genre | Journal Article |
| GroupedDBID | --- --K --M .1- .FO .~1 0R~ 0SF 123 1B1 1RT 1~. 1~5 4.4 457 4G. 5RE 5VS 6I. 7-5 71M 7X7 8P~ 9JM AABNK AACTN AAEDT AAEDW AAFTH AAIKJ AAKOC AALRI AAOAW AAXKI AAXLA AAXUO ABBQC ABCQJ ABFNM ABFRF ABIVO ABJNI ABMAC ABMZM ACDAQ ACGFO ACGFS ACPRK ACRLP ADBBV ADEZE ADFRT ADVLN AEBSH AEFWE AEKER AENEX AFJKZ AFKWA AFRHN AFTJW AFXIZ AGUBO AGWIK AGYEJ AHHHB AHMBA AIEXJ AIKHN AITUG AJOXV AJRQY AJUYK AKRWK ALIPV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ ANZVX AXJTR BENPR BHPHI BKOJK BLXMC BNPGV C45 CS3 DM4 DU5 EBS EFBJH EO8 EO9 EP2 EP3 F5P FDB FIRID FNPLU FYGXN G-Q GBLVA GROUPED_DOAJ HCIFZ HMQ IHE J1W KOM M2M M7P MO0 MOBAO N9A NCXOZ O-L O9- OAUVE OK1 OVD OZT P-8 P-9 P2P PC. Q38 RIG RPZ SAE SCC SDF SDG SDP SES SEW SNS SSH SSN SSZ T5K TEORI UV1 YK3 Z5R ZU3 ~G- LG5 LX8 M29 M2V M41 NPM 29N 3V. 53G 88E 8AO 8FE 8FH 8FI 8FJ AAQFI AAQXK AAYXX ABUWG ABXDB ADFGL ADMUD AFKRA AGHFR AKRLJ ASPBG AVWKF AZFZN AZQEC BBNVY BPHCQ BVXVI CAG CCPQU CITATION COF DWQXO EJD FEDTE FGOYB FYUFA G-2 GNUQQ HDW HEI HMK HMO HVGLF HZ~ LK8 M1P PQQKQ PROAC PSQYO PSYQQ R2- ROL WUQ XPP ZMT 7TK 8FD FR3 K9. P64 RC3 7X8 5PM |
| ID | FETCH-LOGICAL-c449t-1ef8805cdc2de2191a3775c9671ada252c52a7992c0783db270c63fa3e8cf2553 |
| IEDL.DBID | AIKHN |
| ISSN | 1053-8119 1095-9572 |
| IngestDate | Tue Oct 22 15:12:08 EDT 2024 Mon Oct 21 05:26:44 EDT 2024 Sat Oct 26 01:47:13 EDT 2024 Thu Oct 10 21:14:16 EDT 2024 Wed Oct 02 14:36:37 EDT 2024 Sat Nov 02 12:31:07 EDT 2024 Sat Sep 28 15:53:05 EDT 2024 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Neuroimaging Mental disorder Similarity Redundancy Regularization Classification |
| Language | English |
| License | This is an open access article under the CC BY-NC-ND license. Copyright © 2024. Published by Elsevier Inc. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c449t-1ef8805cdc2de2191a3775c9671ada252c52a7992c0783db270c63fa3e8cf2553 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0002-0079-8177 0000-0002-4479-686X 0000-0001-9058-0747 |
| OpenAccessLink | https://www.sciencedirect.com/science/article/pii/S1053811924003367 |
| PMID | 39251116 |
| PQID | 3106365691 |
| PQPubID | 2031077 |
| PageCount | 1 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_ffe8ca6a45dd4b9788c7352f53cdc3e0 pubmedcentral_primary_oai_pubmedcentral_nih_gov_11491165 proquest_miscellaneous_3102469552 proquest_journals_3106365691 crossref_primary_10_1016_j_neuroimage_2024_120839 pubmed_primary_39251116 elsevier_sciencedirect_doi_10_1016_j_neuroimage_2024_120839 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-10-01 |
| PublicationDateYYYYMMDD | 2024-10-01 |
| PublicationDate_xml | – month: 10 year: 2024 text: 2024-10-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States – name: Amsterdam |
| PublicationTitle | NeuroImage (Orlando, Fla.) |
| PublicationTitleAlternate | Neuroimage |
| PublicationYear | 2024 |
| Publisher | Elsevier Inc Elsevier Limited Elsevier |
| Publisher_xml | – name: Elsevier Inc – name: Elsevier Limited – name: Elsevier |
| References | Gao, Hu, Zhang (bib0022) 2020; 50 Gu, Han (bib0033) 2015 Huang, Liu, Zhu, Tan (bib0002) 2022 Wang, Nie, Tian, Wang, Li (bib0026) 2020 Nie, Wang, Wang, Wang, Li (bib0025) 2019; 43 Du, Fu, Xing, Lin, Pearlson, Kochunov, Hong, Qi, Salman, Abrol (bib0046) 2021; 4 Lim, Kim (bib0042) 2021; 111 Zhang, Fan, Wang, Zhou, Tao (bib0017) 2020; 32 Du, Fu, Sui, Gao, Xing, Lin, Salman, Abrol, Rahaman, Chen (bib0045) 2020; 28 Zhu, Zhang, Hu, Zhu (bib0036) 2017; 30 Du, Fu, Calhoun (bib0003) 2018; 12 Abi-Dargham, Moeller, Ali, DeLorenzo, Domschke, Horga, Jutla, Kotov, Paulus, Rubio (bib0040) 2023; 22 Li, Dong, Gai, Che, Ma, Zhao, Chu, Mao, Wang (bib0031) 2023 Han, Kim (bib0041) 2015 Nie, Huang, Cai, Ding (bib0032) 2010; 23 Liu, Wang, Zhang, Yin, Liu (bib0035) 2014; 25 Tasci, Tasci, Ayyildiz, Kamath, Barua, Tuncer, Dogan, Ciaccio, Chakraborty, Acharya (bib0014) 2023 Ayesha, Hanif, Talib (bib0016) 2020; 59 Chen, Jiang, Cao, Men, Wang (bib0051) 2024; 147 Chen, Hu, Liu, Becker, Eickhoff, Miao, Gu, Tang, Dai, Li (bib0013) 2023; 21 Li, Cheng, Wang, Morstatter, Trevino, Tang, Liu (bib0021) 2017; 50 Palaniyappan (bib0055) 2023; 48 Demšar (bib0050) 2006; 7 Xing, Kochunov, van Erp, Ma, Calhoun, Du (bib0044) 2022; 27 Xing, van Erp, Pearlson, Kochunov, Calhoun, Du (bib0001) 2024; 27 Zhou, Chen, Du, Li (bib0018) 2023; 53 Kononenko, Šimec, Robnik-Šikonja (bib0023) 1997; 7 Nie, Wang, Wang, Wang, Li (bib0034) 2020; 14 Stephan, Bach, Fletcher, Flint, Frank, Friston, Heinz, Huys, Owen, Binder (bib0004) 2016; 3 Bachli, Sedeño, Ochab, Piguet, Kumfor, Reyes, Torralva, Roca, Cardona, Campo (bib0005) 2020; 208 Baygin, Barua, Chakraborty, Tuncer, Dogan, Palmer, Tuncer, Kamath, Ciaccio, Acharya (bib0010) 2023; 44 Das, Naik, Behera (bib0019) 2022; 34 Ye, Xie (bib0039) 2012; 87 Arkin, Ruiz-Betancourt, Jamerson, Smith, Strauss, Klim, Javitt, Patel (bib0056) 2020; 27 Zhou, Xu, Cheng, Fang, Pedrycz (bib0037) 2016; 53 Dhal, Azad (bib0020) 2022; 52 Kay, Fiszbein, Opler (bib0048) 1987; 13 Ramírez, Górriz, Ortiz, Martínez-Murcia, Segovia, Salas-Gonzalez, Castillo-Barnes, Illán, Puntonet (bib0029) 2018; 302 Aydemir, Dogan, Baygin, Ooi, Barua, Tuncer, Acharya (bib0009) 2022; 10 Cao, Chen, Xing, Liang (bib0049) 2023; 36 Yang, Wu, Kong, Luo, Xie, Pan, Quan, Hu, Li, Wu (bib0008) 2024; 290 Terpou, Shaw, Théberge, Férat, Michel, McKinnon, Lanius, Ros (bib0024) 2022; 35 Wang, Li, Ruiz (bib0027) 2022; 53 Ferdinandov, Kostov, Hadzhieva, Shivarov, Petrov, Bussarsky, Pashov (bib0028) 2023; 24 He, Cai, Niyogi (bib0038) 2005; 18 Woodward, Cascio (bib0006) 2015; 72 Cui, Liu, Li, Wang, Guo, Tian, Wu, Guo, Liu, Xi (bib0054) 2016; 173 Saadatmand, MR Akbarzadeh (bib0047) 2023; 142 Shine, Lewis, Garrett, Hwang (bib0053) 2023; 24 Ranjan, Zhang, Boley (bib0043) 2014 Laumann, Zorumski, Dosenbach (bib0007) 2023; 80 Bayrakçı, Zorlu, Karakılıç, Gülyüksel, Yalınçetin, Oral, Gelal, Bora (bib0052) 2023; 273 Tejavibulya, Rolison, Gao, Liang, Peterson, Dadashkarimi, Farruggia, Hahn, Noble, Lichenstein (bib0011) 2022; 27 Omuya, Okeyo, Kimwele (bib0015) 2021; 174 Tibshirani (bib0030) 1996; 58 Zhang, Feng, Han, Gong, Duan (bib0012) 2023; 15 Aydemir (10.1016/j.neuroimage.2024.120839_bib0009) 2022; 10 Gu (10.1016/j.neuroimage.2024.120839_bib0033) 2015 Ferdinandov (10.1016/j.neuroimage.2024.120839_bib0028) 2023; 24 Ranjan (10.1016/j.neuroimage.2024.120839_bib0043) 2014 Dhal (10.1016/j.neuroimage.2024.120839_bib0020) 2022; 52 Stephan (10.1016/j.neuroimage.2024.120839_bib0004) 2016; 3 Tejavibulya (10.1016/j.neuroimage.2024.120839_bib0011) 2022; 27 Palaniyappan (10.1016/j.neuroimage.2024.120839_bib0055) 2023; 48 Zhang (10.1016/j.neuroimage.2024.120839_bib0017) 2020; 32 Han (10.1016/j.neuroimage.2024.120839_bib0041) 2015 Liu (10.1016/j.neuroimage.2024.120839_bib0035) 2014; 25 Nie (10.1016/j.neuroimage.2024.120839_bib0032) 2010; 23 Terpou (10.1016/j.neuroimage.2024.120839_bib0024) 2022; 35 Nie (10.1016/j.neuroimage.2024.120839_bib0034) 2020; 14 Du (10.1016/j.neuroimage.2024.120839_bib0003) 2018; 12 Kay (10.1016/j.neuroimage.2024.120839_bib0048) 1987; 13 He (10.1016/j.neuroimage.2024.120839_bib0038) 2005; 18 Ye (10.1016/j.neuroimage.2024.120839_bib0039) 2012; 87 Das (10.1016/j.neuroimage.2024.120839_bib0019) 2022; 34 Li (10.1016/j.neuroimage.2024.120839_bib0031) 2023 Woodward (10.1016/j.neuroimage.2024.120839_bib0006) 2015; 72 Baygin (10.1016/j.neuroimage.2024.120839_bib0010) 2023; 44 Kononenko (10.1016/j.neuroimage.2024.120839_bib0023) 1997; 7 Cui (10.1016/j.neuroimage.2024.120839_bib0054) 2016; 173 Shine (10.1016/j.neuroimage.2024.120839_bib0053) 2023; 24 Zhu (10.1016/j.neuroimage.2024.120839_bib0036) 2017; 30 Laumann (10.1016/j.neuroimage.2024.120839_bib0007) 2023; 80 Du (10.1016/j.neuroimage.2024.120839_bib0045) 2020; 28 Huang (10.1016/j.neuroimage.2024.120839_bib0002) 2022 Nie (10.1016/j.neuroimage.2024.120839_bib0025) 2019; 43 Yang (10.1016/j.neuroimage.2024.120839_bib0008) 2024; 290 Ayesha (10.1016/j.neuroimage.2024.120839_bib0016) 2020; 59 Zhou (10.1016/j.neuroimage.2024.120839_bib0037) 2016; 53 Ramírez (10.1016/j.neuroimage.2024.120839_bib0029) 2018; 302 Gao (10.1016/j.neuroimage.2024.120839_bib0022) 2020; 50 Xing (10.1016/j.neuroimage.2024.120839_bib0044) 2022; 27 Zhang (10.1016/j.neuroimage.2024.120839_bib0012) 2023; 15 Bayrakçı (10.1016/j.neuroimage.2024.120839_bib0052) 2023; 273 Wang (10.1016/j.neuroimage.2024.120839_bib0026) 2020 Demšar (10.1016/j.neuroimage.2024.120839_bib0050) 2006; 7 Abi-Dargham (10.1016/j.neuroimage.2024.120839_bib0040) 2023; 22 Li (10.1016/j.neuroimage.2024.120839_bib0021) 2017; 50 Wang (10.1016/j.neuroimage.2024.120839_bib0027) 2022; 53 Arkin (10.1016/j.neuroimage.2024.120839_bib0056) 2020; 27 Omuya (10.1016/j.neuroimage.2024.120839_bib0015) 2021; 174 Du (10.1016/j.neuroimage.2024.120839_bib0046) 2021; 4 Cao (10.1016/j.neuroimage.2024.120839_bib0049) 2023; 36 Chen (10.1016/j.neuroimage.2024.120839_bib0013) 2023; 21 Chen (10.1016/j.neuroimage.2024.120839_bib0051) 2024; 147 Tasci (10.1016/j.neuroimage.2024.120839_bib0014) 2023 Xing (10.1016/j.neuroimage.2024.120839_bib0001) 2024; 27 Saadatmand (10.1016/j.neuroimage.2024.120839_bib0047) 2023; 142 Bachli (10.1016/j.neuroimage.2024.120839_bib0005) 2020; 208 Lim (10.1016/j.neuroimage.2024.120839_bib0042) 2021; 111 Zhou (10.1016/j.neuroimage.2024.120839_bib0018) 2023; 53 Tibshirani (10.1016/j.neuroimage.2024.120839_bib0030) 1996; 58 |
| References_xml | – volume: 59 start-page: 44 year: 2020 end-page: 58 ident: bib0016 article-title: Overview and comparative study of dimensionality reduction techniques for high dimensional data publication-title: Inform. Fusion contributor: fullname: Talib – volume: 302 start-page: 47 year: 2018 end-page: 57 ident: bib0029 article-title: AsDN Initiative, Ensemble of random forests One vs. rest classifiers for MCI and AD prediction using ANOVA cortical and subcortical feature selection and partial least squares publication-title: J. Neurosci. Methods. contributor: fullname: Puntonet – volume: 35 year: 2022 ident: bib0024 article-title: Spectral decomposition of EEG microstates in post-traumatic stress disorder publication-title: NeuroImage Clin. contributor: fullname: Ros – volume: 50 start-page: 1272 year: 2020 end-page: 1288 ident: bib0022 article-title: Feature redundancy term variation for mutual information-based feature selection publication-title: Appl. Intell. contributor: fullname: Zhang – volume: 43 start-page: 2086 year: 2019 end-page: 2100 ident: bib0025 article-title: Towards robust discriminative projections learning via non-greedy ℓ2, 1-norm minmax publication-title: IEEE Trans Pattern Anal. Mach. Intell. contributor: fullname: Li – volume: 174 year: 2021 ident: bib0015 article-title: Feature selection for classification using principal component analysis and information gain publication-title: Expert Syst. Appl. contributor: fullname: Kimwele – start-page: 3009 year: 2020 end-page: 3015 ident: bib0026 article-title: Discriminative feature selection via a structured sparse subspace learning module publication-title: Twenty-ninth International Joint Conference on Artificial Intelligence contributor: fullname: Li – volume: 4 start-page: 1073 year: 2021 ident: bib0046 article-title: Evidence of shared and distinct functional and structural brain signatures in schizophrenia and autism spectrum disorder publication-title: Commun. Biol. contributor: fullname: Abrol – volume: 21 start-page: 241 year: 2023 ident: bib0013 article-title: Sampling inequalities affect generalization of neuroimaging-based diagnostic classifiers in psychiatry publication-title: BMC Med. contributor: fullname: Li – volume: 52 start-page: 4543 year: 2022 end-page: 4581 ident: bib0020 article-title: A comprehensive survey on feature selection in the various fields of machine learning publication-title: Appl. Intell. contributor: fullname: Azad – year: 2023 ident: bib0031 article-title: Diagnosis of major depressive disorder using machine learning based on multisequence MRI neuroimaging features publication-title: J. Magn. Reson. Imaging contributor: fullname: Wang – volume: 142 year: 2023 ident: bib0047 article-title: Set-based integer-coded fuzzy granular evolutionary algorithms for high-dimensional feature selection publication-title: Appl. Soft Comput. contributor: fullname: MR Akbarzadeh – volume: 24 start-page: 416 year: 2023 end-page: 430 ident: bib0053 article-title: The impact of the human thalamus on brain-wide information processing publication-title: Nat. Rev. Neurosci. contributor: fullname: Hwang – volume: 111 year: 2021 ident: bib0042 article-title: Pairwise dependence-based unsupervised feature selection publication-title: Pattern Recognit. contributor: fullname: Kim – volume: 22 start-page: 236 year: 2023 end-page: 262 ident: bib0040 article-title: Candidate biomarkers in psychiatric disorders: state of the field publication-title: World Psychiatry contributor: fullname: Rubio – volume: 34 start-page: 3851 year: 2022 end-page: 3863 ident: bib0019 article-title: A Jaya algorithm based wrapper method for optimal feature selection in supervised classification publication-title: J. King Saud Univ. Comp. Info. Sci. contributor: fullname: Behera – volume: 27 start-page: 3129 year: 2022 end-page: 3137 ident: bib0011 article-title: Predicting the future of neuroimaging predictive models in mental health publication-title: Mol. Psychiatry contributor: fullname: Lichenstein – volume: 290 year: 2024 ident: bib0008 article-title: Precise detection of awareness in disorders of consciousness using deep learning framework publication-title: Neuroimage contributor: fullname: Wu – volume: 23 start-page: 1813 year: 2010 end-page: 1821 ident: bib0032 article-title: Efficient and robust feature selection via joint ℓ2, 1-norms minimization publication-title: Advances in Neural Information Processing Systems contributor: fullname: Ding – volume: 48 start-page: E325 year: 2023 ident: bib0055 article-title: Clusters of psychosis: compensation as a contributor to the heterogeneity of schizophrenia publication-title: J. Psychiatry Neurosci. JPN contributor: fullname: Palaniyappan – volume: 208 year: 2020 ident: bib0005 article-title: Evaluating the reliability of neurocognitive biomarkers of neurodegenerative diseases across countries: a machine learning approach publication-title: Neuroimage contributor: fullname: Campo – volume: 18 year: 2005 ident: bib0038 article-title: Laplacian score for feature selection publication-title: Adv. Neural Inf. Process. Syst. contributor: fullname: Niyogi – volume: 32 start-page: 3005 year: 2020 end-page: 3019 ident: bib0017 article-title: Top-k feature selection framework using robust 0-1 integer programming publication-title: IEEE Trans. Neural Netw. Learn. Syst. contributor: fullname: Tao – volume: 7 start-page: 39 year: 1997 end-page: 55 ident: bib0023 article-title: Overcoming the myopia of inductive learning algorithms with RELIEFF publication-title: Appl. Intell. contributor: fullname: Robnik-Šikonja – volume: 147 year: 2024 ident: bib0051 article-title: A general elevating framework for label noise filters publication-title: Pattern Recognit. contributor: fullname: Wang – start-page: 5016 year: 2015 end-page: 5023 ident: bib0041 article-title: Unsupervised simultaneous orthogonal basis clustering feature selection publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition contributor: fullname: Kim – volume: 44 year: 2023 ident: bib0010 article-title: CCPNet136: automated detection of schizophrenia using carbon chain pattern and iterative TQWT technique with EEG signals publication-title: Physiol. Meas. contributor: fullname: Acharya – volume: 12 start-page: 525 year: 2018 ident: bib0003 article-title: Classification and prediction of brain disorders using functional connectivity: promising but challenging publication-title: Front. Neurosci. contributor: fullname: Calhoun – volume: 87 start-page: 303 year: 2012 end-page: 355 ident: bib0039 article-title: Learning sparse gradients for variable selection and dimension reduction publication-title: Mach. Learn. contributor: fullname: Xie – volume: 53 start-page: 87 year: 2016 end-page: 101 ident: bib0037 article-title: Global and local structure preserving sparse subspace learning: an iterative approach to unsupervised feature selection publication-title: Pattern Recognit. contributor: fullname: Pedrycz – volume: 28 year: 2020 ident: bib0045 article-title: NeuroMark: an automated and adaptive ICA based pipeline to identify reproducible fMRI markers of brain disorders publication-title: NeuroImage Clin. contributor: fullname: Chen – start-page: 1 year: 2022 end-page: 15 ident: bib0002 article-title: Multitask learning for joint diagnosis of multiple mental disorders in resting-state fMRI publication-title: IEEE Trans. Neural Netw. Learn. Syst. contributor: fullname: Tan – volume: 53 start-page: 707 year: 2022 end-page: 717 ident: bib0027 article-title: Feature selection with maximal relevance and minimal supervised redundancy publication-title: IEEE Trans. Cybern. contributor: fullname: Ruiz – volume: 25 start-page: 1083 year: 2014 end-page: 1095 ident: bib0035 article-title: Global and local structure preservation for feature selection publication-title: IEEE Trans. Neural Netw. Learn. Syst. contributor: fullname: Liu – volume: 27 year: 2024 ident: bib0001 article-title: More reliable biomarkers and more accurate prediction for mental disorders using a label-noise filtering-based dimensional prediction method publication-title: iScience contributor: fullname: Du – volume: 24 start-page: 2597 year: 2023 ident: bib0028 article-title: Reactivity graph yields interpretable IgM repertoire signatures as potential tumor biomarkers publication-title: Int. J. Mol. Sci. contributor: fullname: Pashov – volume: 72 start-page: 743 year: 2015 end-page: 744 ident: bib0006 article-title: Resting-state functional connectivity in psychiatric disorders publication-title: JAMA Psychiatry contributor: fullname: Cascio – volume: 173 start-page: 13 year: 2016 end-page: 22 ident: bib0054 article-title: Putamen-related regional and network functional deficits in first-episode schizophrenia with auditory verbal hallucinations publication-title: Schizophr. Res. contributor: fullname: Xi – start-page: 1175 year: 2015 end-page: 1184 ident: bib0033 article-title: Towards feature selection in network publication-title: Proceedings of the 20th ACM international conference on Information and knowledge management contributor: fullname: Han – volume: 50 start-page: 1 year: 2017 end-page: 45 ident: bib0021 article-title: Feature selection: a data perspective publication-title: ACM Comput. Surv. contributor: fullname: Liu – volume: 14 start-page: 1 year: 2020 end-page: 19 ident: bib0034 article-title: Adaptive local linear discriminant analysis publication-title: ACM Trans. Knowl. Discov. Data contributor: fullname: Li – year: 2023 ident: bib0014 article-title: Automated schizophrenia detection model using blood sample scattergram images and local binary pattern publication-title: Multimedia Tools and Applications contributor: fullname: Acharya – volume: 15 start-page: 1106 year: 2023 end-page: 1117 ident: bib0012 article-title: Detection of autism spectrum disorder using fMRI functional connectivity with feature selection and deep learning publication-title: Cognit. Comput. contributor: fullname: Duan – volume: 30 start-page: 517 year: 2017 end-page: 529 ident: bib0036 article-title: Local and global structure preservation for robust unsupervised spectral feature selection publication-title: IEEE Trans. Knowl. Data Eng. contributor: fullname: Zhu – volume: 273 start-page: 565 year: 2023 end-page: 574 ident: bib0052 article-title: Negative symptoms are associated with modularity and thalamic connectivity in schizophrenia publication-title: Eur. Arch. Psychiatry Clin. Neurosci. contributor: fullname: Bora – volume: 7 start-page: 1 year: 2006 end-page: 30 ident: bib0050 article-title: Statistical comparisons of classifiers over multiple data sets publication-title: J. Mach. Learn. Res. contributor: fullname: Demšar – volume: 3 start-page: 77 year: 2016 end-page: 83 ident: bib0004 article-title: Charting the landscape of priority problems in psychiatry, part 1: classification and diagnosis publication-title: Lancet Psychiatry contributor: fullname: Binder – volume: 13 start-page: 261 year: 1987 end-page: 276 ident: bib0048 article-title: The positive and negative syndrome scale (PANSS) for schizophrenia publication-title: Schizophr. Bull. contributor: fullname: Opler – volume: 53 start-page: 4232 year: 2023 end-page: 4244 ident: bib0018 article-title: Balanced spectral feature selection publication-title: IEEE Trans. Cybern. contributor: fullname: Li – volume: 10 year: 2022 ident: bib0009 article-title: CGP17Pat: automated schizophrenia detection based on a cyclic group of prime order patterns using EEG signals publication-title: Healthcare contributor: fullname: Acharya – start-page: 729 year: 2014 end-page: 749 ident: bib0043 article-title: Incremental computation of pseudo-inverse of laplacian publication-title: International Conference on Combinatorial Optimization and Applications contributor: fullname: Boley – volume: 80 start-page: 763 year: 2023 end-page: 764 ident: bib0007 article-title: Precision neuroimaging for localization-related psychiatry publication-title: JAMA Psychiatry contributor: fullname: Dosenbach – volume: 27 start-page: 215 year: 2022 end-page: 226 ident: bib0044 article-title: A novel neighborhood rough set-based feature selection method and its application to biomarker identification of schizophrenia publication-title: IEEE J. Biomed. Health Inform. contributor: fullname: Du – volume: 58 start-page: 267 year: 1996 end-page: 288 ident: bib0030 article-title: Regression shrinkage and selection via the lasso publication-title: J. R. Stat. Soc. Ser. B (Method.) contributor: fullname: Tibshirani – volume: 27 year: 2020 ident: bib0056 article-title: Deficits and compensation: attentional control cortical networks in schizophrenia publication-title: NeuroImage Clin. contributor: fullname: Patel – volume: 36 start-page: 1084 year: 2023 end-page: 1098 ident: bib0049 article-title: Efficient classification by removing bayesian confusing samples publication-title: IEEE Trans. Knowl. Data Eng. contributor: fullname: Liang – volume: 142 year: 2023 ident: 10.1016/j.neuroimage.2024.120839_bib0047 article-title: Set-based integer-coded fuzzy granular evolutionary algorithms for high-dimensional feature selection publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2023.110240 contributor: fullname: Saadatmand – volume: 48 start-page: E325 year: 2023 ident: 10.1016/j.neuroimage.2024.120839_bib0055 article-title: Clusters of psychosis: compensation as a contributor to the heterogeneity of schizophrenia publication-title: J. Psychiatry Neurosci. JPN doi: 10.1503/jpn.230120 contributor: fullname: Palaniyappan – start-page: 3009 year: 2020 ident: 10.1016/j.neuroimage.2024.120839_bib0026 article-title: Discriminative feature selection via a structured sparse subspace learning module contributor: fullname: Wang – volume: 24 start-page: 2597 year: 2023 ident: 10.1016/j.neuroimage.2024.120839_bib0028 article-title: Reactivity graph yields interpretable IgM repertoire signatures as potential tumor biomarkers publication-title: Int. J. Mol. Sci. doi: 10.3390/ijms24032597 contributor: fullname: Ferdinandov – volume: 10 year: 2022 ident: 10.1016/j.neuroimage.2024.120839_bib0009 article-title: CGP17Pat: automated schizophrenia detection based on a cyclic group of prime order patterns using EEG signals publication-title: Healthcare doi: 10.3390/healthcare10040643 contributor: fullname: Aydemir – volume: 27 start-page: 215 year: 2022 ident: 10.1016/j.neuroimage.2024.120839_bib0044 article-title: A novel neighborhood rough set-based feature selection method and its application to biomarker identification of schizophrenia publication-title: IEEE J. Biomed. Health Inform. doi: 10.1109/JBHI.2022.3212479 contributor: fullname: Xing – volume: 36 start-page: 1084 year: 2023 ident: 10.1016/j.neuroimage.2024.120839_bib0049 article-title: Efficient classification by removing bayesian confusing samples publication-title: IEEE Trans. Knowl. Data Eng. doi: 10.1109/TKDE.2023.3303425 contributor: fullname: Cao – volume: 25 start-page: 1083 year: 2014 ident: 10.1016/j.neuroimage.2024.120839_bib0035 article-title: Global and local structure preservation for feature selection publication-title: IEEE Trans. Neural Netw. Learn. Syst. doi: 10.1109/TNNLS.2013.2287275 contributor: fullname: Liu – volume: 27 year: 2020 ident: 10.1016/j.neuroimage.2024.120839_bib0056 article-title: Deficits and compensation: attentional control cortical networks in schizophrenia publication-title: NeuroImage Clin. doi: 10.1016/j.nicl.2020.102348 contributor: fullname: Arkin – volume: 7 start-page: 39 year: 1997 ident: 10.1016/j.neuroimage.2024.120839_bib0023 article-title: Overcoming the myopia of inductive learning algorithms with RELIEFF publication-title: Appl. Intell. doi: 10.1023/A:1008280620621 contributor: fullname: Kononenko – volume: 15 start-page: 1106 year: 2023 ident: 10.1016/j.neuroimage.2024.120839_bib0012 article-title: Detection of autism spectrum disorder using fMRI functional connectivity with feature selection and deep learning publication-title: Cognit. Comput. doi: 10.1007/s12559-021-09981-z contributor: fullname: Zhang – volume: 273 start-page: 565 year: 2023 ident: 10.1016/j.neuroimage.2024.120839_bib0052 article-title: Negative symptoms are associated with modularity and thalamic connectivity in schizophrenia publication-title: Eur. Arch. Psychiatry Clin. Neurosci. doi: 10.1007/s00406-022-01433-5 contributor: fullname: Bayrakçı – volume: 53 start-page: 707 year: 2022 ident: 10.1016/j.neuroimage.2024.120839_bib0027 article-title: Feature selection with maximal relevance and minimal supervised redundancy publication-title: IEEE Trans. Cybern. doi: 10.1109/TCYB.2021.3139898 contributor: fullname: Wang – volume: 30 start-page: 517 year: 2017 ident: 10.1016/j.neuroimage.2024.120839_bib0036 article-title: Local and global structure preservation for robust unsupervised spectral feature selection publication-title: IEEE Trans. Knowl. Data Eng. doi: 10.1109/TKDE.2017.2763618 contributor: fullname: Zhu – volume: 173 start-page: 13 year: 2016 ident: 10.1016/j.neuroimage.2024.120839_bib0054 article-title: Putamen-related regional and network functional deficits in first-episode schizophrenia with auditory verbal hallucinations publication-title: Schizophr. Res. doi: 10.1016/j.schres.2016.02.039 contributor: fullname: Cui – volume: 147 year: 2024 ident: 10.1016/j.neuroimage.2024.120839_bib0051 article-title: A general elevating framework for label noise filters publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2023.110072 contributor: fullname: Chen – volume: 32 start-page: 3005 year: 2020 ident: 10.1016/j.neuroimage.2024.120839_bib0017 article-title: Top-k feature selection framework using robust 0-1 integer programming publication-title: IEEE Trans. Neural Netw. Learn. Syst. doi: 10.1109/TNNLS.2020.3009209 contributor: fullname: Zhang – volume: 53 start-page: 4232 year: 2023 ident: 10.1016/j.neuroimage.2024.120839_bib0018 article-title: Balanced spectral feature selection publication-title: IEEE Trans. Cybern. doi: 10.1109/TCYB.2022.3160244 contributor: fullname: Zhou – start-page: 5016 year: 2015 ident: 10.1016/j.neuroimage.2024.120839_bib0041 article-title: Unsupervised simultaneous orthogonal basis clustering feature selection contributor: fullname: Han – volume: 34 start-page: 3851 year: 2022 ident: 10.1016/j.neuroimage.2024.120839_bib0019 article-title: A Jaya algorithm based wrapper method for optimal feature selection in supervised classification publication-title: J. King Saud Univ. Comp. Info. Sci. contributor: fullname: Das – volume: 290 year: 2024 ident: 10.1016/j.neuroimage.2024.120839_bib0008 article-title: Precise detection of awareness in disorders of consciousness using deep learning framework publication-title: Neuroimage doi: 10.1016/j.neuroimage.2024.120580 contributor: fullname: Yang – volume: 53 start-page: 87 year: 2016 ident: 10.1016/j.neuroimage.2024.120839_bib0037 article-title: Global and local structure preserving sparse subspace learning: an iterative approach to unsupervised feature selection publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2015.12.008 contributor: fullname: Zhou – volume: 44 year: 2023 ident: 10.1016/j.neuroimage.2024.120839_bib0010 article-title: CCPNet136: automated detection of schizophrenia using carbon chain pattern and iterative TQWT technique with EEG signals publication-title: Physiol. Meas. doi: 10.1088/1361-6579/acb03c contributor: fullname: Baygin – volume: 50 start-page: 1272 year: 2020 ident: 10.1016/j.neuroimage.2024.120839_bib0022 article-title: Feature redundancy term variation for mutual information-based feature selection publication-title: Appl. Intell. doi: 10.1007/s10489-019-01597-z contributor: fullname: Gao – year: 2023 ident: 10.1016/j.neuroimage.2024.120839_bib0031 article-title: Diagnosis of major depressive disorder using machine learning based on multisequence MRI neuroimaging features publication-title: J. Magn. Reson. Imaging doi: 10.1002/jmri.28650 contributor: fullname: Li – volume: 58 start-page: 267 year: 1996 ident: 10.1016/j.neuroimage.2024.120839_bib0030 article-title: Regression shrinkage and selection via the lasso publication-title: J. R. Stat. Soc. Ser. B (Method.) doi: 10.1111/j.2517-6161.1996.tb02080.x contributor: fullname: Tibshirani – volume: 80 start-page: 763 year: 2023 ident: 10.1016/j.neuroimage.2024.120839_bib0007 article-title: Precision neuroimaging for localization-related psychiatry publication-title: JAMA Psychiatry doi: 10.1001/jamapsychiatry.2023.1576 contributor: fullname: Laumann – start-page: 729 year: 2014 ident: 10.1016/j.neuroimage.2024.120839_bib0043 article-title: Incremental computation of pseudo-inverse of laplacian contributor: fullname: Ranjan – volume: 111 year: 2021 ident: 10.1016/j.neuroimage.2024.120839_bib0042 article-title: Pairwise dependence-based unsupervised feature selection publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2020.107663 contributor: fullname: Lim – start-page: 1 year: 2022 ident: 10.1016/j.neuroimage.2024.120839_bib0002 article-title: Multitask learning for joint diagnosis of multiple mental disorders in resting-state fMRI publication-title: IEEE Trans. Neural Netw. Learn. Syst. contributor: fullname: Huang – volume: 302 start-page: 47 year: 2018 ident: 10.1016/j.neuroimage.2024.120839_bib0029 article-title: AsDN Initiative, Ensemble of random forests One vs. rest classifiers for MCI and AD prediction using ANOVA cortical and subcortical feature selection and partial least squares publication-title: J. Neurosci. Methods. doi: 10.1016/j.jneumeth.2017.12.005 contributor: fullname: Ramírez – volume: 22 start-page: 236 year: 2023 ident: 10.1016/j.neuroimage.2024.120839_bib0040 article-title: Candidate biomarkers in psychiatric disorders: state of the field publication-title: World Psychiatry doi: 10.1002/wps.21078 contributor: fullname: Abi-Dargham – volume: 13 start-page: 261 year: 1987 ident: 10.1016/j.neuroimage.2024.120839_bib0048 article-title: The positive and negative syndrome scale (PANSS) for schizophrenia publication-title: Schizophr. Bull. doi: 10.1093/schbul/13.2.261 contributor: fullname: Kay – volume: 43 start-page: 2086 year: 2019 ident: 10.1016/j.neuroimage.2024.120839_bib0025 article-title: Towards robust discriminative projections learning via non-greedy ℓ2, 1-norm minmax publication-title: IEEE Trans Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2019.2961877 contributor: fullname: Nie – start-page: 1175 year: 2015 ident: 10.1016/j.neuroimage.2024.120839_bib0033 article-title: Towards feature selection in network contributor: fullname: Gu – volume: 52 start-page: 4543 year: 2022 ident: 10.1016/j.neuroimage.2024.120839_bib0020 article-title: A comprehensive survey on feature selection in the various fields of machine learning publication-title: Appl. Intell. doi: 10.1007/s10489-021-02550-9 contributor: fullname: Dhal – year: 2023 ident: 10.1016/j.neuroimage.2024.120839_bib0014 article-title: Automated schizophrenia detection model using blood sample scattergram images and local binary pattern contributor: fullname: Tasci – volume: 3 start-page: 77 year: 2016 ident: 10.1016/j.neuroimage.2024.120839_bib0004 article-title: Charting the landscape of priority problems in psychiatry, part 1: classification and diagnosis publication-title: Lancet Psychiatry doi: 10.1016/S2215-0366(15)00361-2 contributor: fullname: Stephan – volume: 174 year: 2021 ident: 10.1016/j.neuroimage.2024.120839_bib0015 article-title: Feature selection for classification using principal component analysis and information gain publication-title: Expert Syst. Appl. contributor: fullname: Omuya – volume: 87 start-page: 303 year: 2012 ident: 10.1016/j.neuroimage.2024.120839_bib0039 article-title: Learning sparse gradients for variable selection and dimension reduction publication-title: Mach. Learn. doi: 10.1007/s10994-012-5284-9 contributor: fullname: Ye – volume: 208 year: 2020 ident: 10.1016/j.neuroimage.2024.120839_bib0005 article-title: Evaluating the reliability of neurocognitive biomarkers of neurodegenerative diseases across countries: a machine learning approach publication-title: Neuroimage doi: 10.1016/j.neuroimage.2019.116456 contributor: fullname: Bachli – volume: 4 start-page: 1073 year: 2021 ident: 10.1016/j.neuroimage.2024.120839_bib0046 article-title: Evidence of shared and distinct functional and structural brain signatures in schizophrenia and autism spectrum disorder publication-title: Commun. Biol. doi: 10.1038/s42003-021-02592-2 contributor: fullname: Du – volume: 21 start-page: 241 year: 2023 ident: 10.1016/j.neuroimage.2024.120839_bib0013 article-title: Sampling inequalities affect generalization of neuroimaging-based diagnostic classifiers in psychiatry publication-title: BMC Med. doi: 10.1186/s12916-023-02941-4 contributor: fullname: Chen – volume: 14 start-page: 1 year: 2020 ident: 10.1016/j.neuroimage.2024.120839_bib0034 article-title: Adaptive local linear discriminant analysis publication-title: ACM Trans. Knowl. Discov. Data doi: 10.1145/3369870 contributor: fullname: Nie – volume: 72 start-page: 743 year: 2015 ident: 10.1016/j.neuroimage.2024.120839_bib0006 article-title: Resting-state functional connectivity in psychiatric disorders publication-title: JAMA Psychiatry doi: 10.1001/jamapsychiatry.2015.0484 contributor: fullname: Woodward – volume: 12 start-page: 525 year: 2018 ident: 10.1016/j.neuroimage.2024.120839_bib0003 article-title: Classification and prediction of brain disorders using functional connectivity: promising but challenging publication-title: Front. Neurosci. doi: 10.3389/fnins.2018.00525 contributor: fullname: Du – volume: 7 start-page: 1 year: 2006 ident: 10.1016/j.neuroimage.2024.120839_bib0050 article-title: Statistical comparisons of classifiers over multiple data sets publication-title: J. Mach. Learn. Res. contributor: fullname: Demšar – volume: 28 year: 2020 ident: 10.1016/j.neuroimage.2024.120839_bib0045 article-title: NeuroMark: an automated and adaptive ICA based pipeline to identify reproducible fMRI markers of brain disorders publication-title: NeuroImage Clin. doi: 10.1016/j.nicl.2020.102375 contributor: fullname: Du – volume: 24 start-page: 416 year: 2023 ident: 10.1016/j.neuroimage.2024.120839_bib0053 article-title: The impact of the human thalamus on brain-wide information processing publication-title: Nat. Rev. Neurosci. doi: 10.1038/s41583-023-00701-0 contributor: fullname: Shine – volume: 18 year: 2005 ident: 10.1016/j.neuroimage.2024.120839_bib0038 article-title: Laplacian score for feature selection publication-title: Adv. Neural Inf. Process. Syst. contributor: fullname: He – volume: 50 start-page: 1 year: 2017 ident: 10.1016/j.neuroimage.2024.120839_bib0021 article-title: Feature selection: a data perspective publication-title: ACM Comput. Surv. contributor: fullname: Li – volume: 35 year: 2022 ident: 10.1016/j.neuroimage.2024.120839_bib0024 article-title: Spectral decomposition of EEG microstates in post-traumatic stress disorder publication-title: NeuroImage Clin. doi: 10.1016/j.nicl.2022.103135 contributor: fullname: Terpou – volume: 23 start-page: 1813 year: 2010 ident: 10.1016/j.neuroimage.2024.120839_bib0032 article-title: Efficient and robust feature selection via joint ℓ2, 1-norms minimization contributor: fullname: Nie – volume: 27 year: 2024 ident: 10.1016/j.neuroimage.2024.120839_bib0001 article-title: More reliable biomarkers and more accurate prediction for mental disorders using a label-noise filtering-based dimensional prediction method publication-title: iScience doi: 10.1016/j.isci.2024.109319 contributor: fullname: Xing – volume: 59 start-page: 44 year: 2020 ident: 10.1016/j.neuroimage.2024.120839_bib0016 article-title: Overview and comparative study of dimensionality reduction techniques for high dimensional data publication-title: Inform. Fusion doi: 10.1016/j.inffus.2020.01.005 contributor: fullname: Ayesha – volume: 27 start-page: 3129 year: 2022 ident: 10.1016/j.neuroimage.2024.120839_bib0011 article-title: Predicting the future of neuroimaging predictive models in mental health publication-title: Mol. Psychiatry doi: 10.1038/s41380-022-01635-2 contributor: fullname: Tejavibulya |
| SSID | ssj0009148 |
| Score | 2.5018811 |
| Snippet | •We propose a new method, LRFS, to identify features with enhanced discriminability.•It preserves sample similarity and enhance independence among features.•It... Accurate diagnosis of mental disorders is expected to be achieved through the identification of reliable neuroimaging biomarkers with the help of cutting-edge... |
| SourceID | doaj pubmedcentral proquest crossref pubmed elsevier |
| SourceType | Open Website Open Access Repository Aggregation Database Index Database Publisher |
| StartPage | 120839 |
| SubjectTerms | Biomarkers Classification Datasets Diagnosis Feature selection Functional magnetic resonance imaging Information theory Magnetic resonance imaging Medical imaging Mental disorder Mental disorders Methods Neural networks Neuroimaging Pathogenesis Preservation Redundancy Regularization Schizophrenia Sensitivity analysis Similarity Sparsity Variance analysis |
| SummonAdditionalLinks | – databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Nb9QwELVQD4gL4ptAQUbiaqgd21mLEyCqClFOVOrN8qcIUhO02f4bfiwzdrJs4AAHrrETxZ6x50388oaQlzom73PkLEmOotreMe9MZCploWMnPS8iSeef9dmF_HipLg9KfSEnrMoD14l7nXPaBKedVDFKDznPJnQAGrJqQwxtqtn6iVmSqUVuF1D-zNupbK6iDtlfwRqFnFDIV1wA9jCrYFQ0-1cx6U_M-Tt18iAWnd4ht2cQSd_Wl79LbqThHrl5Ph-T3yc_PmGEYlUb9nqbGLJdl6-v1A2RbhP-PYY7K9umqxHcjWE8izSnovRJp1IfB7vXGtPlrn430YMTb7obKeBH2seZclSvjpniT_3I-9lOFEAxnQ6ZfQ_IxemHL-_P2FyGgQUpzY7xlGGRK5huERNscNy1XaeC0R130QklghKuM0YEPBKMXnQnQbfZtWC4DBlL-5AcDeOQHhMKZvTCSWjftBKAl_exNVjuJAPK8DI0hC_2sN-r2oZdaGjf7C8bWrShrTZsyDs03L4_6mWXC-BFdvYi-zcvasibxex2hh4VUsCj-n94hePFU-y8BUwWcLNuAS0b3pAX-2ZYvHgi44Y0Xpc-QmqjlGjIo-pY-3EAcAUwzHVDNiuXWw103TL0X4tAOOS4BmWVnvyPqXlKbuFQK4HxmByB66ZnAMR2_nlZcz8BohU5vQ priority: 102 providerName: Directory of Open Access Journals |
| Title | Local-structure-preservation and redundancy-removal-based feature selection method and its application to the identification of biomarkers for schizophrenia |
| URI | https://dx.doi.org/10.1016/j.neuroimage.2024.120839 https://www.ncbi.nlm.nih.gov/pubmed/39251116 https://www.proquest.com/docview/3106365691 https://www.proquest.com/docview/3102469552 https://pubmed.ncbi.nlm.nih.gov/PMC11491165 https://doaj.org/article/ffe8ca6a45dd4b9788c7352f53cdc3e0 |
| Volume | 299 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9QwELb6kBAXxJtAWRmJq7u1YycbcSoV1fJoL1Cpt8iObRqkJlV2e-WX8GOZsZ3tBi5IHNd2spnMeOabePyZkLeFdcZ4y5mTHEm1jWZGV5Yp50VhS2l4IEk6Oy-WF_LTpbrcISfjXhgsq0y-P_r04K1Tyzy9zflN286_AjKAcIMJBB5IVpS7ZB_CkQDT3j_--Hl5fse9y2XcEadyhhekgp5Y5hVoI9trmLyQLAp5yAWAkmoSpQKZ_yRY_Q1G_6yp3ApSpw_Jg4Qu6XEU4BHZcd1jcu8srZ8_Ib--YOhikTT2dnAMy2DHz7JUd5YODreVoctlg7vuwQ4ZBjpLvQsUoHQVDs7B4fHw6XBVu17RraVwuu4pAEva2lSLFFt7T3G3PxYEDSsKaJmutkv-npKL0w_fTpYsnc_AGimrNePOw-xXjW2EdeD5uM7LUjVVUXJttVCiUUKXVSUaXCu0RpRHTZF7nbtF4yGVyZ-Rva7v3AtCCy2N0BL6F7kERGaMzSs8B8UD_DCyyQgf9VHfRBqOeqxP-1Hf6bBGHdZRhxl5j4rbjEci7dDQD9_rZEm19_AwGv5eWSsNpNSLpgRM6lUOYuXuKCPvRrXXE7uEW7X_8AgHo6XUyTesagDURQ4wuuIZebPphlmNSzW6c_1tGCNkUSklMvI8GtZGDkC0gJJ5kZHFxOQmgk57uvYqMIdD8lsh39LL_5LqFbmPv2JJ4wHZA5t1rwGarc2M7B7-5LM0AWfhA8dv9GxAQA |
| link.rule.ids | 230,315,783,787,867,888,2109,4510,24129,27937,27938,45598,45692 |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Nb9QwELVKkaAXxDeBAkbi6m7t2MlanKCiWmC3F1qpN8uOnRKkJtXu9tpfwo9lxk62G7ggcbW9ib0znnmOn58JeV_44FztOQuSo6i2s8xZ7ZkKtSh8KR2PIkmLk2J2Jr-eq_MdcjSchUFaZR_7U0yP0bovmfT_5uSqaSbfARlAusEFBF5IVpR3yF2JcuPg1Ac3tzwPzWU6D6dyhs17Ok8ieUXRyOYSpi4sFYU84AIgiR7lqCjlP0pVf0PRPxmVWynq-CF50GNL-jF1_xHZCe1jcm_R754_Ib_mmLhYkoy9XgaGJNjhoyy1rafLgIfKMOCyZbjswAsZpjlP6xAFQOkqXpuDzdPV0_FXzXpFtzbC6bqjACtp43smUirtaopn_ZEOtFxRwMp0tU34e0rOjj-fHs1YfzsDq6TUa8ZDDXNfVb4SPkDc4zYvS1XpouTWW6FEpYQttRYV7hR6J8rDqshrm4dpVcNCJn9GdtuuDS8ILax0wkqon-YS8JhzPtd4C0oN4MPJKiN8sIe5SiIcZmCn_TS3NjRoQ5NsmJFPaLhNe5TRjgXd8sL0fmTqGjpj4fXKe-lgQT2tSkCktcphWHk4zMiHwexm5JXwqOYfurA_eIrpI8PKAJwucgDRmmfk3aYa5jRu1Ng2dNexjZCFVkpk5HlyrM04AM8CRuZFRqYjlxsNdFzTNj-ibjgsfTWqLb38r1G9Jfdnp4u5mX85-faK7GFNIjfuk13w3_AaQNravYmT8Ddv8kAk |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Local-structure-preservation+and+redundancy-removal-based+feature+selection+method+and+its+application+to+the+identification+of+biomarkers+for+schizophrenia&rft.jtitle=NeuroImage+%28Orlando%2C+Fla.%29&rft.au=Xing%2C+Ying&rft.au=Pearlson%2C+Godfrey+D.&rft.au=Kochunov%2C+Peter&rft.au=Calhoun%2C+Vince+D.&rft.date=2024-10-01&rft.issn=1053-8119&rft.volume=299&rft.spage=120839&rft_id=info:doi/10.1016%2Fj.neuroimage.2024.120839&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_neuroimage_2024_120839 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1053-8119&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1053-8119&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1053-8119&client=summon |