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


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2019-03-27

AUTHORS

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

ABSTRACT

An important problem that hinders the use of supervised classification algorithms for brain imaging is that the number of variables per single subject far exceeds the number of training subjects available. Deriving multivariate measures of variable importance becomes a challenge in such scenarios. This paper proposes a new measure of variable importance termed sign-consistency bagging (SCB). The SCB captures variable importance by analyzing the sign consistency of the corresponding weights in an ensemble of linear support vector machine (SVM) classifiers. Further, the SCB variable importances are enhanced by means of transductive conformal analysis. This extra step is important when the data can be assumed to be heterogeneous. Finally, the proposal of these SCB variable importance measures is completed with the derivation of a parametric hypothesis test of variable importance. The new importance measures were compared with a t-test based univariate and an SVM-based multivariate variable importances using anatomical and functional magnetic resonance imaging data. The obtained results demonstrated that the new SCB based importance measures were superior to the compared methods in terms of reproducibility and classification accuracy. More... »

PAGES

1-17

References to SciGraph publications

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s12021-019-9415-3

DOI

http://dx.doi.org/10.1007/s12021-019-9415-3

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1113047039

PUBMED

https://www.ncbi.nlm.nih.gov/pubmed/30919255


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Artificial Intelligence and Image Processing", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Carlos III University of Madrid", 
          "id": "https://www.grid.ac/institutes/grid.7840.b", 
          "name": [
            "Department of Signal Processing and Communications, Universidad Carlos III de Madrid, Legan\u00e9s, Spain"
          ], 
          "type": "Organization"
        }, 
        "familyName": "G\u00f3mez-Verdejo", 
        "givenName": "Vanessa", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Carlos III University of Madrid", 
          "id": "https://www.grid.ac/institutes/grid.7840.b", 
          "name": [
            "Department of Signal Processing and Communications, Universidad Carlos III de Madrid, Legan\u00e9s, Spain"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Parrado-Hern\u00e1ndez", 
        "givenName": "Emilio", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University of Eastern Finland", 
          "id": "https://www.grid.ac/institutes/grid.9668.1", 
          "name": [
            "A.I. Virtanen Institute for Molecular Sciences, University of Eastern Finland, Kuopio, Finland"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Tohka", 
        "givenName": "Jussi", 
        "type": "Person"
      }, 
      {
        "familyName": "Alzheimer\u2019s Disease Neuroimaging Initiative", 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1016/j.neuroimage.2010.07.074", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1001852368"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s12021-015-9292-3", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1001923510", 
          "https://doi.org/10.1007/s12021-015-9292-3"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.3389/fpsyt.2012.00053", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1003580831"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1186/1471-2105-7-3", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1004156594", 
          "https://doi.org/10.1186/1471-2105-7-3"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1186/1471-2105-7-3", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1004156594", 
          "https://doi.org/10.1186/1471-2105-7-3"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neuroimage.2014.10.002", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1004724462"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1006/nimg.2001.0978", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1008623590"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neuroimage.2011.10.018", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1009534385"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/1961189.1961199", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1013637525"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.media.2015.06.008", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1014825862"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1023/a:1009013718684", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1014936191", 
          "https://doi.org/10.1023/a:1009013718684"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neuroimage.2015.02.046", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1014984110"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neuroimage.2012.12.062", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1015388408"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neuroimage.2013.03.066", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1015889618"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/502512.502547", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1017132117"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neuroimage.2013.10.067", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1017153482"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.mri.2009.06.004", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1017632391"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s12021-013-9204-3", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1017882056", 
          "https://doi.org/10.1007/s12021-013-9204-3"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1023/a:1024068626366", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1019095106", 
          "https://doi.org/10.1023/a:1024068626366"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.patrec.2010.03.014", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1021405554"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1371/journal.pone.0022193", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1021731017"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.media.2014.01.006", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1022770308"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neuroimage.2016.10.038", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1023917129"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.schres.2014.03.033", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1024360951"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1023/a:1010933404324", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1024739340", 
          "https://doi.org/10.1023/a:1010933404324"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neunet.2015.04.002", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1025261087"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1023/a:1018628609742", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1025353016", 
          "https://doi.org/10.1023/a:1018628609742"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neuroimage.2011.11.066", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1025501769"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.schres.2015.04.034", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1027270079"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neuroimage.2015.05.018", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1027402029"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-540-24775-3_3", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1029295303", 
          "https://doi.org/10.1007/978-3-540-24775-3_3"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1371/journal.pone.0067346", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1031969002"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neuroimage.2010.07.033", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1034133947"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neuroimage.2010.07.033", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1034133947"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-642-23783-6_29", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1039240250", 
          "https://doi.org/10.1007/978-3-642-23783-6_29"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-642-23783-6_29", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1039240250", 
          "https://doi.org/10.1007/978-3-642-23783-6_29"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.3389/fninf.2015.00008", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1039949008"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neuroimage.2007.03.072", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1040107407"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1093/bioinformatics/btq134", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1040585611"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.csda.2012.09.020", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1040900298"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1186/1471-2105-9-307", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1042870683", 
          "https://doi.org/10.1186/1471-2105-9-307"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1111/j.1467-9868.2005.00503.x", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1043971564"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neuroimage.2015.07.071", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1047038575"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.patcog.2015.05.005", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1047926278"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neuroimage.2013.07.050", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1048390271"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1023/a:1012487302797", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1048573168", 
          "https://doi.org/10.1023/a:1012487302797"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.csda.2007.08.015", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1049823578"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neuroimage.2005.06.070", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1050103020"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neuroimage.2005.06.070", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1050103020"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.2174/138920211796429763", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1052241375"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tmi.2011.2113378", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061695704"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1142/s0218001497000597", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1062951150"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/prni.2016.7552333", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093195726"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icpr.1994.576361", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094517408"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1111/j.2517-6161.1995.tb02031.x", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1110458929"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1111/j.2517-6161.1995.tb02031.x", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1110458929"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2019-03-27", 
    "datePublishedReg": "2019-03-27", 
    "description": "An important problem that hinders the use of supervised classification algorithms for brain imaging is that the number of variables per single subject far exceeds the number of training subjects available. Deriving multivariate measures of variable importance becomes a challenge in such scenarios. This paper proposes a new measure of variable importance termed sign-consistency bagging (SCB). The SCB captures variable importance by analyzing the sign consistency of the corresponding weights in an ensemble of linear support vector machine (SVM) classifiers. Further, the SCB variable importances are enhanced by means of transductive conformal analysis. This extra step is important when the data can be assumed to be heterogeneous. Finally, the proposal of these SCB variable importance measures is completed with the derivation of a parametric hypothesis test of variable importance. The new importance measures were compared with a t-test based univariate and an SVM-based multivariate variable importances using anatomical and functional magnetic resonance imaging data. The obtained results demonstrated that the new SCB based importance measures were superior to the compared methods in terms of reproducibility and classification accuracy.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1007/s12021-019-9415-3", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isFundedItemOf": [
      {
        "id": "sg:grant.2687006", 
        "type": "MonetaryGrant"
      }, 
      {
        "id": "sg:grant.7132465", 
        "type": "MonetaryGrant"
      }
    ], 
    "isPartOf": [
      {
        "id": "sg:journal.1030723", 
        "issn": [
          "1539-2791", 
          "1559-0089"
        ], 
        "name": "Neuroinformatics", 
        "type": "Periodical"
      }
    ], 
    "name": "Sign-Consistency Based Variable Importance for Machine Learning in Brain Imaging", 
    "pagination": "1-17", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "b6ac4d8fc4ea24376fb17e1e70015e88d39e6e42bd4d1d5728a7f72f0e852005"
        ]
      }, 
      {
        "name": "pubmed_id", 
        "type": "PropertyValue", 
        "value": [
          "30919255"
        ]
      }, 
      {
        "name": "nlm_unique_id", 
        "type": "PropertyValue", 
        "value": [
          "101142069"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s12021-019-9415-3"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1113047039"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s12021-019-9415-3", 
      "https://app.dimensions.ai/details/publication/pub.1113047039"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-11T13:25", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000369_0000000369/records_68975_00000001.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://link.springer.com/10.1007%2Fs12021-019-9415-3"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/s12021-019-9415-3'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/s12021-019-9415-3'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s12021-019-9415-3'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s12021-019-9415-3'


 

This table displays all metadata directly associated to this object as RDF triples.

249 TRIPLES      21 PREDICATES      77 URIs      18 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s12021-019-9415-3 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N9bf33147a4ca408fb89975417b181dc6
4 schema:citation sg:pub.10.1007/978-3-540-24775-3_3
5 sg:pub.10.1007/978-3-642-23783-6_29
6 sg:pub.10.1007/s12021-013-9204-3
7 sg:pub.10.1007/s12021-015-9292-3
8 sg:pub.10.1023/a:1009013718684
9 sg:pub.10.1023/a:1010933404324
10 sg:pub.10.1023/a:1012487302797
11 sg:pub.10.1023/a:1018628609742
12 sg:pub.10.1023/a:1024068626366
13 sg:pub.10.1186/1471-2105-7-3
14 sg:pub.10.1186/1471-2105-9-307
15 https://doi.org/10.1006/nimg.2001.0978
16 https://doi.org/10.1016/j.csda.2007.08.015
17 https://doi.org/10.1016/j.csda.2012.09.020
18 https://doi.org/10.1016/j.media.2014.01.006
19 https://doi.org/10.1016/j.media.2015.06.008
20 https://doi.org/10.1016/j.mri.2009.06.004
21 https://doi.org/10.1016/j.neunet.2015.04.002
22 https://doi.org/10.1016/j.neuroimage.2005.06.070
23 https://doi.org/10.1016/j.neuroimage.2007.03.072
24 https://doi.org/10.1016/j.neuroimage.2010.07.033
25 https://doi.org/10.1016/j.neuroimage.2010.07.074
26 https://doi.org/10.1016/j.neuroimage.2011.10.018
27 https://doi.org/10.1016/j.neuroimage.2011.11.066
28 https://doi.org/10.1016/j.neuroimage.2012.12.062
29 https://doi.org/10.1016/j.neuroimage.2013.03.066
30 https://doi.org/10.1016/j.neuroimage.2013.07.050
31 https://doi.org/10.1016/j.neuroimage.2013.10.067
32 https://doi.org/10.1016/j.neuroimage.2014.10.002
33 https://doi.org/10.1016/j.neuroimage.2015.02.046
34 https://doi.org/10.1016/j.neuroimage.2015.05.018
35 https://doi.org/10.1016/j.neuroimage.2015.07.071
36 https://doi.org/10.1016/j.neuroimage.2016.10.038
37 https://doi.org/10.1016/j.patcog.2015.05.005
38 https://doi.org/10.1016/j.patrec.2010.03.014
39 https://doi.org/10.1016/j.schres.2014.03.033
40 https://doi.org/10.1016/j.schres.2015.04.034
41 https://doi.org/10.1093/bioinformatics/btq134
42 https://doi.org/10.1109/icpr.1994.576361
43 https://doi.org/10.1109/prni.2016.7552333
44 https://doi.org/10.1109/tmi.2011.2113378
45 https://doi.org/10.1111/j.1467-9868.2005.00503.x
46 https://doi.org/10.1111/j.2517-6161.1995.tb02031.x
47 https://doi.org/10.1142/s0218001497000597
48 https://doi.org/10.1145/1961189.1961199
49 https://doi.org/10.1145/502512.502547
50 https://doi.org/10.1371/journal.pone.0022193
51 https://doi.org/10.1371/journal.pone.0067346
52 https://doi.org/10.2174/138920211796429763
53 https://doi.org/10.3389/fninf.2015.00008
54 https://doi.org/10.3389/fpsyt.2012.00053
55 schema:datePublished 2019-03-27
56 schema:datePublishedReg 2019-03-27
57 schema:description An important problem that hinders the use of supervised classification algorithms for brain imaging is that the number of variables per single subject far exceeds the number of training subjects available. Deriving multivariate measures of variable importance becomes a challenge in such scenarios. This paper proposes a new measure of variable importance termed sign-consistency bagging (SCB). The SCB captures variable importance by analyzing the sign consistency of the corresponding weights in an ensemble of linear support vector machine (SVM) classifiers. Further, the SCB variable importances are enhanced by means of transductive conformal analysis. This extra step is important when the data can be assumed to be heterogeneous. Finally, the proposal of these SCB variable importance measures is completed with the derivation of a parametric hypothesis test of variable importance. The new importance measures were compared with a t-test based univariate and an SVM-based multivariate variable importances using anatomical and functional magnetic resonance imaging data. The obtained results demonstrated that the new SCB based importance measures were superior to the compared methods in terms of reproducibility and classification accuracy.
58 schema:genre research_article
59 schema:inLanguage en
60 schema:isAccessibleForFree false
61 schema:isPartOf sg:journal.1030723
62 schema:name Sign-Consistency Based Variable Importance for Machine Learning in Brain Imaging
63 schema:pagination 1-17
64 schema:productId N07fb3644d90e4657939a85e75b0b5131
65 N5f746bc812a84da78684556d2f8aa0db
66 N6d3825aef487476fb610da7dcb40a9e9
67 N710b0842e5cd4948a249634edd851dc5
68 N8ec5c721e84546369bcd62ae22c73caa
69 schema:sameAs https://app.dimensions.ai/details/publication/pub.1113047039
70 https://doi.org/10.1007/s12021-019-9415-3
71 schema:sdDatePublished 2019-04-11T13:25
72 schema:sdLicense https://scigraph.springernature.com/explorer/license/
73 schema:sdPublisher N473761f1bbb746ebb3171059ea8a2325
74 schema:url https://link.springer.com/10.1007%2Fs12021-019-9415-3
75 sgo:license sg:explorer/license/
76 sgo:sdDataset articles
77 rdf:type schema:ScholarlyArticle
78 N07fb3644d90e4657939a85e75b0b5131 schema:name dimensions_id
79 schema:value pub.1113047039
80 rdf:type schema:PropertyValue
81 N473761f1bbb746ebb3171059ea8a2325 schema:name Springer Nature - SN SciGraph project
82 rdf:type schema:Organization
83 N5a6e7618c521442dacd9ab52709bde0b schema:affiliation https://www.grid.ac/institutes/grid.9668.1
84 schema:familyName Tohka
85 schema:givenName Jussi
86 rdf:type schema:Person
87 N5f746bc812a84da78684556d2f8aa0db schema:name nlm_unique_id
88 schema:value 101142069
89 rdf:type schema:PropertyValue
90 N6d3825aef487476fb610da7dcb40a9e9 schema:name pubmed_id
91 schema:value 30919255
92 rdf:type schema:PropertyValue
93 N710b0842e5cd4948a249634edd851dc5 schema:name doi
94 schema:value 10.1007/s12021-019-9415-3
95 rdf:type schema:PropertyValue
96 N7f0ec8544d594cc491ff789800c887be schema:affiliation https://www.grid.ac/institutes/grid.7840.b
97 schema:familyName Parrado-Hernández
98 schema:givenName Emilio
99 rdf:type schema:Person
100 N87856979024f40b88a19fcf2e54d8295 schema:familyName Alzheimer’s Disease Neuroimaging Initiative
101 rdf:type schema:Person
102 N8ec5c721e84546369bcd62ae22c73caa schema:name readcube_id
103 schema:value b6ac4d8fc4ea24376fb17e1e70015e88d39e6e42bd4d1d5728a7f72f0e852005
104 rdf:type schema:PropertyValue
105 N97606dcfa4c742a89e014d18bdaf9a67 rdf:first N7f0ec8544d594cc491ff789800c887be
106 rdf:rest Nf575cd9675f6485f951d60dbe42b0e95
107 N9bf33147a4ca408fb89975417b181dc6 rdf:first Ndc3a9a24a1974d58b92279b8e6a99a72
108 rdf:rest N97606dcfa4c742a89e014d18bdaf9a67
109 Na13c6d33ab7c44b29579bcc3c98d92ef rdf:first N87856979024f40b88a19fcf2e54d8295
110 rdf:rest rdf:nil
111 Ndc3a9a24a1974d58b92279b8e6a99a72 schema:affiliation https://www.grid.ac/institutes/grid.7840.b
112 schema:familyName Gómez-Verdejo
113 schema:givenName Vanessa
114 rdf:type schema:Person
115 Nf575cd9675f6485f951d60dbe42b0e95 rdf:first N5a6e7618c521442dacd9ab52709bde0b
116 rdf:rest Na13c6d33ab7c44b29579bcc3c98d92ef
117 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
118 schema:name Information and Computing Sciences
119 rdf:type schema:DefinedTerm
120 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
121 schema:name Artificial Intelligence and Image Processing
122 rdf:type schema:DefinedTerm
123 sg:grant.2687006 http://pending.schema.org/fundedItem sg:pub.10.1007/s12021-019-9415-3
124 rdf:type schema:MonetaryGrant
125 sg:grant.7132465 http://pending.schema.org/fundedItem sg:pub.10.1007/s12021-019-9415-3
126 rdf:type schema:MonetaryGrant
127 sg:journal.1030723 schema:issn 1539-2791
128 1559-0089
129 schema:name Neuroinformatics
130 rdf:type schema:Periodical
131 sg:pub.10.1007/978-3-540-24775-3_3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1029295303
132 https://doi.org/10.1007/978-3-540-24775-3_3
133 rdf:type schema:CreativeWork
134 sg:pub.10.1007/978-3-642-23783-6_29 schema:sameAs https://app.dimensions.ai/details/publication/pub.1039240250
135 https://doi.org/10.1007/978-3-642-23783-6_29
136 rdf:type schema:CreativeWork
137 sg:pub.10.1007/s12021-013-9204-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017882056
138 https://doi.org/10.1007/s12021-013-9204-3
139 rdf:type schema:CreativeWork
140 sg:pub.10.1007/s12021-015-9292-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1001923510
141 https://doi.org/10.1007/s12021-015-9292-3
142 rdf:type schema:CreativeWork
143 sg:pub.10.1023/a:1009013718684 schema:sameAs https://app.dimensions.ai/details/publication/pub.1014936191
144 https://doi.org/10.1023/a:1009013718684
145 rdf:type schema:CreativeWork
146 sg:pub.10.1023/a:1010933404324 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024739340
147 https://doi.org/10.1023/a:1010933404324
148 rdf:type schema:CreativeWork
149 sg:pub.10.1023/a:1012487302797 schema:sameAs https://app.dimensions.ai/details/publication/pub.1048573168
150 https://doi.org/10.1023/a:1012487302797
151 rdf:type schema:CreativeWork
152 sg:pub.10.1023/a:1018628609742 schema:sameAs https://app.dimensions.ai/details/publication/pub.1025353016
153 https://doi.org/10.1023/a:1018628609742
154 rdf:type schema:CreativeWork
155 sg:pub.10.1023/a:1024068626366 schema:sameAs https://app.dimensions.ai/details/publication/pub.1019095106
156 https://doi.org/10.1023/a:1024068626366
157 rdf:type schema:CreativeWork
158 sg:pub.10.1186/1471-2105-7-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1004156594
159 https://doi.org/10.1186/1471-2105-7-3
160 rdf:type schema:CreativeWork
161 sg:pub.10.1186/1471-2105-9-307 schema:sameAs https://app.dimensions.ai/details/publication/pub.1042870683
162 https://doi.org/10.1186/1471-2105-9-307
163 rdf:type schema:CreativeWork
164 https://doi.org/10.1006/nimg.2001.0978 schema:sameAs https://app.dimensions.ai/details/publication/pub.1008623590
165 rdf:type schema:CreativeWork
166 https://doi.org/10.1016/j.csda.2007.08.015 schema:sameAs https://app.dimensions.ai/details/publication/pub.1049823578
167 rdf:type schema:CreativeWork
168 https://doi.org/10.1016/j.csda.2012.09.020 schema:sameAs https://app.dimensions.ai/details/publication/pub.1040900298
169 rdf:type schema:CreativeWork
170 https://doi.org/10.1016/j.media.2014.01.006 schema:sameAs https://app.dimensions.ai/details/publication/pub.1022770308
171 rdf:type schema:CreativeWork
172 https://doi.org/10.1016/j.media.2015.06.008 schema:sameAs https://app.dimensions.ai/details/publication/pub.1014825862
173 rdf:type schema:CreativeWork
174 https://doi.org/10.1016/j.mri.2009.06.004 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017632391
175 rdf:type schema:CreativeWork
176 https://doi.org/10.1016/j.neunet.2015.04.002 schema:sameAs https://app.dimensions.ai/details/publication/pub.1025261087
177 rdf:type schema:CreativeWork
178 https://doi.org/10.1016/j.neuroimage.2005.06.070 schema:sameAs https://app.dimensions.ai/details/publication/pub.1050103020
179 rdf:type schema:CreativeWork
180 https://doi.org/10.1016/j.neuroimage.2007.03.072 schema:sameAs https://app.dimensions.ai/details/publication/pub.1040107407
181 rdf:type schema:CreativeWork
182 https://doi.org/10.1016/j.neuroimage.2010.07.033 schema:sameAs https://app.dimensions.ai/details/publication/pub.1034133947
183 rdf:type schema:CreativeWork
184 https://doi.org/10.1016/j.neuroimage.2010.07.074 schema:sameAs https://app.dimensions.ai/details/publication/pub.1001852368
185 rdf:type schema:CreativeWork
186 https://doi.org/10.1016/j.neuroimage.2011.10.018 schema:sameAs https://app.dimensions.ai/details/publication/pub.1009534385
187 rdf:type schema:CreativeWork
188 https://doi.org/10.1016/j.neuroimage.2011.11.066 schema:sameAs https://app.dimensions.ai/details/publication/pub.1025501769
189 rdf:type schema:CreativeWork
190 https://doi.org/10.1016/j.neuroimage.2012.12.062 schema:sameAs https://app.dimensions.ai/details/publication/pub.1015388408
191 rdf:type schema:CreativeWork
192 https://doi.org/10.1016/j.neuroimage.2013.03.066 schema:sameAs https://app.dimensions.ai/details/publication/pub.1015889618
193 rdf:type schema:CreativeWork
194 https://doi.org/10.1016/j.neuroimage.2013.07.050 schema:sameAs https://app.dimensions.ai/details/publication/pub.1048390271
195 rdf:type schema:CreativeWork
196 https://doi.org/10.1016/j.neuroimage.2013.10.067 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017153482
197 rdf:type schema:CreativeWork
198 https://doi.org/10.1016/j.neuroimage.2014.10.002 schema:sameAs https://app.dimensions.ai/details/publication/pub.1004724462
199 rdf:type schema:CreativeWork
200 https://doi.org/10.1016/j.neuroimage.2015.02.046 schema:sameAs https://app.dimensions.ai/details/publication/pub.1014984110
201 rdf:type schema:CreativeWork
202 https://doi.org/10.1016/j.neuroimage.2015.05.018 schema:sameAs https://app.dimensions.ai/details/publication/pub.1027402029
203 rdf:type schema:CreativeWork
204 https://doi.org/10.1016/j.neuroimage.2015.07.071 schema:sameAs https://app.dimensions.ai/details/publication/pub.1047038575
205 rdf:type schema:CreativeWork
206 https://doi.org/10.1016/j.neuroimage.2016.10.038 schema:sameAs https://app.dimensions.ai/details/publication/pub.1023917129
207 rdf:type schema:CreativeWork
208 https://doi.org/10.1016/j.patcog.2015.05.005 schema:sameAs https://app.dimensions.ai/details/publication/pub.1047926278
209 rdf:type schema:CreativeWork
210 https://doi.org/10.1016/j.patrec.2010.03.014 schema:sameAs https://app.dimensions.ai/details/publication/pub.1021405554
211 rdf:type schema:CreativeWork
212 https://doi.org/10.1016/j.schres.2014.03.033 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024360951
213 rdf:type schema:CreativeWork
214 https://doi.org/10.1016/j.schres.2015.04.034 schema:sameAs https://app.dimensions.ai/details/publication/pub.1027270079
215 rdf:type schema:CreativeWork
216 https://doi.org/10.1093/bioinformatics/btq134 schema:sameAs https://app.dimensions.ai/details/publication/pub.1040585611
217 rdf:type schema:CreativeWork
218 https://doi.org/10.1109/icpr.1994.576361 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094517408
219 rdf:type schema:CreativeWork
220 https://doi.org/10.1109/prni.2016.7552333 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093195726
221 rdf:type schema:CreativeWork
222 https://doi.org/10.1109/tmi.2011.2113378 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061695704
223 rdf:type schema:CreativeWork
224 https://doi.org/10.1111/j.1467-9868.2005.00503.x schema:sameAs https://app.dimensions.ai/details/publication/pub.1043971564
225 rdf:type schema:CreativeWork
226 https://doi.org/10.1111/j.2517-6161.1995.tb02031.x schema:sameAs https://app.dimensions.ai/details/publication/pub.1110458929
227 rdf:type schema:CreativeWork
228 https://doi.org/10.1142/s0218001497000597 schema:sameAs https://app.dimensions.ai/details/publication/pub.1062951150
229 rdf:type schema:CreativeWork
230 https://doi.org/10.1145/1961189.1961199 schema:sameAs https://app.dimensions.ai/details/publication/pub.1013637525
231 rdf:type schema:CreativeWork
232 https://doi.org/10.1145/502512.502547 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017132117
233 rdf:type schema:CreativeWork
234 https://doi.org/10.1371/journal.pone.0022193 schema:sameAs https://app.dimensions.ai/details/publication/pub.1021731017
235 rdf:type schema:CreativeWork
236 https://doi.org/10.1371/journal.pone.0067346 schema:sameAs https://app.dimensions.ai/details/publication/pub.1031969002
237 rdf:type schema:CreativeWork
238 https://doi.org/10.2174/138920211796429763 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052241375
239 rdf:type schema:CreativeWork
240 https://doi.org/10.3389/fninf.2015.00008 schema:sameAs https://app.dimensions.ai/details/publication/pub.1039949008
241 rdf:type schema:CreativeWork
242 https://doi.org/10.3389/fpsyt.2012.00053 schema:sameAs https://app.dimensions.ai/details/publication/pub.1003580831
243 rdf:type schema:CreativeWork
244 https://www.grid.ac/institutes/grid.7840.b schema:alternateName Carlos III University of Madrid
245 schema:name Department of Signal Processing and Communications, Universidad Carlos III de Madrid, Leganés, Spain
246 rdf:type schema:Organization
247 https://www.grid.ac/institutes/grid.9668.1 schema:alternateName University of Eastern Finland
248 schema:name A.I. Virtanen Institute for Molecular Sciences, University of Eastern Finland, Kuopio, Finland
249 rdf:type schema:Organization
 




Preview window. Press ESC to close (or click here)


...