Automated Identification of Potential Conflict-of-Interest in Biomedical Articles Using Hybrid Deep Neural Network View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2018-07-08

AUTHORS

Incheol Kim , George R. Thoma

ABSTRACT

Conflicts-of-interest (COI) in biomedical research may cause ethical risks, including pro-industry conclusions, restrictions on the behavior of investigators, and the use of biased study designs. To ensure the impartiality and objectivity in research, many journal publishers require authors to provide a COI statement within the body text of their articles at the time of peer-review and publication. However, author’s self-reported COI disclosure often does not explicitly appear in their article, and may not be very accurate or reliable. In this study, we present a two-stage machine learning scheme using a hybrid deep learning neural network (HDNN) that combines a multi-channel convolutional neural network (CNN) and a feed-forward neural network (FNN), to automatically identify a potential COI in online biomedical articles. HDNN is designed to simultaneously learn a syntactic and semantic representation of text, relationships between neighboring words in a sentence, and handcrafted input features, and achieves a better performance overall (accuracy exceeding 96.8%) than other classifiers such as support vector machine (SVM), single/multi-channel CNNs, Long Short-term Memory (LSTM), and an Ensemble model in a series of classification experiments. More... »

PAGES

99-112

References to SciGraph publications

  • 2000-11-17. Experiments on the Use of Feature Selection and Negative Evidence in Automated Text Categorization in RESEARCH AND ADVANCED TECHNOLOGY FOR DIGITAL LIBRARIES
  • 2015-05. Deep learning in NATURE
  • Book

    TITLE

    Machine Learning and Data Mining in Pattern Recognition

    ISBN

    978-3-319-96135-4
    978-3-319-96136-1

    Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/978-3-319-96136-1_9

    DOI

    http://dx.doi.org/10.1007/978-3-319-96136-1_9

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1105406593


    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": "United States National Library of Medicine", 
              "id": "https://www.grid.ac/institutes/grid.280285.5", 
              "name": [
                "Lister Hill National Center for Biomedical Communications, National Library of Medicine, 8600 Rockville Pike, 20894, Bethesda, MD, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Kim", 
            "givenName": "Incheol", 
            "id": "sg:person.010347024503.32", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010347024503.32"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "United States National Library of Medicine", 
              "id": "https://www.grid.ac/institutes/grid.280285.5", 
              "name": [
                "Lister Hill National Center for Biomedical Communications, National Library of Medicine, 8600 Rockville Pike, 20894, Bethesda, MD, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Thoma", 
            "givenName": "George R.", 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/3-540-45268-0_6", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1001734615", 
              "https://doi.org/10.1007/3-540-45268-0_6"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-45268-0_6", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1001734615", 
              "https://doi.org/10.1007/3-540-45268-0_6"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/nature14539", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1010020120", 
              "https://doi.org/10.1038/nature14539"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1162/neco.1997.9.8.1735", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1038140272"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.3115/v1/d14-1162", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1099110523"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.3115/v1/d14-1162", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1099110523"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.3115/v1/d14-1181", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1099110546"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.3115/v1/d14-1181", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1099110546"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.3115/v1/p15-1026", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1099115033"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.3115/v1/p15-1026", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1099115033"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.3115/v1/p14-5010", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1099127825"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.3115/v1/p14-5010", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1099127825"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.18653/v1/s17-2154", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1100731850"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2018-07-08", 
        "datePublishedReg": "2018-07-08", 
        "description": "Conflicts-of-interest (COI) in biomedical research may cause ethical risks, including pro-industry conclusions, restrictions on the behavior of investigators, and the use of biased study designs. To ensure the impartiality and objectivity in research, many journal publishers require authors to provide a COI statement within the body text of their articles at the time of peer-review and publication. However, author\u2019s self-reported COI disclosure often does not explicitly appear in their article, and may not be very accurate or reliable. In this study, we present a two-stage machine learning scheme using a hybrid deep learning neural network (HDNN) that combines a multi-channel convolutional neural network (CNN) and a feed-forward neural network (FNN), to automatically identify a potential COI in online biomedical articles. HDNN is designed to simultaneously learn a syntactic and semantic representation of text, relationships between neighboring words in a sentence, and handcrafted input features, and achieves a better performance overall (accuracy exceeding 96.8%) than other classifiers such as support vector machine (SVM), single/multi-channel CNNs, Long Short-term Memory (LSTM), and an Ensemble model in a series of classification experiments.", 
        "editor": [
          {
            "familyName": "Perner", 
            "givenName": "Petra", 
            "type": "Person"
          }
        ], 
        "genre": "chapter", 
        "id": "sg:pub.10.1007/978-3-319-96136-1_9", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isPartOf": {
          "isbn": [
            "978-3-319-96135-4", 
            "978-3-319-96136-1"
          ], 
          "name": "Machine Learning and Data Mining in Pattern Recognition", 
          "type": "Book"
        }, 
        "name": "Automated Identification of Potential Conflict-of-Interest in Biomedical Articles Using Hybrid Deep Neural Network", 
        "pagination": "99-112", 
        "productId": [
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/978-3-319-96136-1_9"
            ]
          }, 
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "c2bdff01b0b0805807decc46e9d5144c53b6d86eeb15b9c36820829f0d3fb373"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1105406593"
            ]
          }
        ], 
        "publisher": {
          "location": "Cham", 
          "name": "Springer International Publishing", 
          "type": "Organisation"
        }, 
        "sameAs": [
          "https://doi.org/10.1007/978-3-319-96136-1_9", 
          "https://app.dimensions.ai/details/publication/pub.1105406593"
        ], 
        "sdDataset": "chapters", 
        "sdDatePublished": "2019-04-16T05:00", 
        "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/v90/0000000325_0000000325/records_100791_00000000.jsonl", 
        "type": "Chapter", 
        "url": "https://link.springer.com/10.1007%2F978-3-319-96136-1_9"
      }
    ]
     

    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.10.1007/978-3-319-96136-1_9'

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

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-96136-1_9'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-96136-1_9'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-96136-1_9'


     

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

    97 TRIPLES      23 PREDICATES      34 URIs      19 LITERALS      8 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/978-3-319-96136-1_9 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author N16862c0869d745b2829a03bf72b212a9
    4 schema:citation sg:pub.10.1007/3-540-45268-0_6
    5 sg:pub.10.1038/nature14539
    6 https://doi.org/10.1162/neco.1997.9.8.1735
    7 https://doi.org/10.18653/v1/s17-2154
    8 https://doi.org/10.3115/v1/d14-1162
    9 https://doi.org/10.3115/v1/d14-1181
    10 https://doi.org/10.3115/v1/p14-5010
    11 https://doi.org/10.3115/v1/p15-1026
    12 schema:datePublished 2018-07-08
    13 schema:datePublishedReg 2018-07-08
    14 schema:description Conflicts-of-interest (COI) in biomedical research may cause ethical risks, including pro-industry conclusions, restrictions on the behavior of investigators, and the use of biased study designs. To ensure the impartiality and objectivity in research, many journal publishers require authors to provide a COI statement within the body text of their articles at the time of peer-review and publication. However, author’s self-reported COI disclosure often does not explicitly appear in their article, and may not be very accurate or reliable. In this study, we present a two-stage machine learning scheme using a hybrid deep learning neural network (HDNN) that combines a multi-channel convolutional neural network (CNN) and a feed-forward neural network (FNN), to automatically identify a potential COI in online biomedical articles. HDNN is designed to simultaneously learn a syntactic and semantic representation of text, relationships between neighboring words in a sentence, and handcrafted input features, and achieves a better performance overall (accuracy exceeding 96.8%) than other classifiers such as support vector machine (SVM), single/multi-channel CNNs, Long Short-term Memory (LSTM), and an Ensemble model in a series of classification experiments.
    15 schema:editor N4b332885fcc8485aa6f91a13a306e5ff
    16 schema:genre chapter
    17 schema:inLanguage en
    18 schema:isAccessibleForFree false
    19 schema:isPartOf N8d340c08952a47de819169be9c34c1f0
    20 schema:name Automated Identification of Potential Conflict-of-Interest in Biomedical Articles Using Hybrid Deep Neural Network
    21 schema:pagination 99-112
    22 schema:productId N1f6cdaf5dd6f49a38364f30bc78e7a01
    23 N45848b491a7c4f2c9a8dd181740a73dc
    24 N5983872af92a478aa04b1122b30346e3
    25 schema:publisher N5de57acb1fe14be7a26fd0028da0eb0d
    26 schema:sameAs https://app.dimensions.ai/details/publication/pub.1105406593
    27 https://doi.org/10.1007/978-3-319-96136-1_9
    28 schema:sdDatePublished 2019-04-16T05:00
    29 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    30 schema:sdPublisher N69e3508352534ecca7b9e853440041f7
    31 schema:url https://link.springer.com/10.1007%2F978-3-319-96136-1_9
    32 sgo:license sg:explorer/license/
    33 sgo:sdDataset chapters
    34 rdf:type schema:Chapter
    35 N16862c0869d745b2829a03bf72b212a9 rdf:first sg:person.010347024503.32
    36 rdf:rest N96a85d131f924320b496e62588e0081d
    37 N1f6cdaf5dd6f49a38364f30bc78e7a01 schema:name dimensions_id
    38 schema:value pub.1105406593
    39 rdf:type schema:PropertyValue
    40 N33c33327c29344798489136dc284f3c5 schema:familyName Perner
    41 schema:givenName Petra
    42 rdf:type schema:Person
    43 N45848b491a7c4f2c9a8dd181740a73dc schema:name readcube_id
    44 schema:value c2bdff01b0b0805807decc46e9d5144c53b6d86eeb15b9c36820829f0d3fb373
    45 rdf:type schema:PropertyValue
    46 N4b332885fcc8485aa6f91a13a306e5ff rdf:first N33c33327c29344798489136dc284f3c5
    47 rdf:rest rdf:nil
    48 N5983872af92a478aa04b1122b30346e3 schema:name doi
    49 schema:value 10.1007/978-3-319-96136-1_9
    50 rdf:type schema:PropertyValue
    51 N5de57acb1fe14be7a26fd0028da0eb0d schema:location Cham
    52 schema:name Springer International Publishing
    53 rdf:type schema:Organisation
    54 N69e3508352534ecca7b9e853440041f7 schema:name Springer Nature - SN SciGraph project
    55 rdf:type schema:Organization
    56 N8d340c08952a47de819169be9c34c1f0 schema:isbn 978-3-319-96135-4
    57 978-3-319-96136-1
    58 schema:name Machine Learning and Data Mining in Pattern Recognition
    59 rdf:type schema:Book
    60 N96a85d131f924320b496e62588e0081d rdf:first Nb5adf70768a5487292c6c5b4c04426ea
    61 rdf:rest rdf:nil
    62 Nb5adf70768a5487292c6c5b4c04426ea schema:affiliation https://www.grid.ac/institutes/grid.280285.5
    63 schema:familyName Thoma
    64 schema:givenName George R.
    65 rdf:type schema:Person
    66 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    67 schema:name Information and Computing Sciences
    68 rdf:type schema:DefinedTerm
    69 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    70 schema:name Artificial Intelligence and Image Processing
    71 rdf:type schema:DefinedTerm
    72 sg:person.010347024503.32 schema:affiliation https://www.grid.ac/institutes/grid.280285.5
    73 schema:familyName Kim
    74 schema:givenName Incheol
    75 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010347024503.32
    76 rdf:type schema:Person
    77 sg:pub.10.1007/3-540-45268-0_6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1001734615
    78 https://doi.org/10.1007/3-540-45268-0_6
    79 rdf:type schema:CreativeWork
    80 sg:pub.10.1038/nature14539 schema:sameAs https://app.dimensions.ai/details/publication/pub.1010020120
    81 https://doi.org/10.1038/nature14539
    82 rdf:type schema:CreativeWork
    83 https://doi.org/10.1162/neco.1997.9.8.1735 schema:sameAs https://app.dimensions.ai/details/publication/pub.1038140272
    84 rdf:type schema:CreativeWork
    85 https://doi.org/10.18653/v1/s17-2154 schema:sameAs https://app.dimensions.ai/details/publication/pub.1100731850
    86 rdf:type schema:CreativeWork
    87 https://doi.org/10.3115/v1/d14-1162 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099110523
    88 rdf:type schema:CreativeWork
    89 https://doi.org/10.3115/v1/d14-1181 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099110546
    90 rdf:type schema:CreativeWork
    91 https://doi.org/10.3115/v1/p14-5010 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099127825
    92 rdf:type schema:CreativeWork
    93 https://doi.org/10.3115/v1/p15-1026 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099115033
    94 rdf:type schema:CreativeWork
    95 https://www.grid.ac/institutes/grid.280285.5 schema:alternateName United States National Library of Medicine
    96 schema:name Lister Hill National Center for Biomedical Communications, National Library of Medicine, 8600 Rockville Pike, 20894, Bethesda, MD, USA
    97 rdf:type schema:Organization
     




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


    ...