Academic Journal
View in EDS
Linked Full Text

Deep learning models can predict violence and threats against healthcare providers using clinical notes

Bibliographic Details
Title: Deep learning models can predict violence and threats against healthcare providers using clinical notes
Authors: Nicholas J. Dobbins, Jacqueline Chipkin, Tim Byrne, Omar Ghabra, Julia Siar, Mitchell Sauder, R. Michael Huijon, Taylor M. Black
Source: npj Mental Health Research, Vol 3, Iss 1, Pp 1-8 (2024)
Publisher Information: Nature Portfolio, 2024.
Publication Year: 2024
Collection: LCC:Therapeutics. Psychotherapy
Subject Terms: Therapeutics. Psychotherapy, RC475-489
More Details: Abstract Violence, verbal abuse, threats, and sexual harassment of healthcare providers by patients is a major challenge for healthcare organizations around the world, contributing to staff turnover, distress, absenteeism, reduced job satisfaction, and worsening mental and physical health. To enable interventions prior to possible violent episodes, we trained two deep learning models to predict violence against healthcare workers 3 days prior to violent events for case and control patients. The first model is a document classification model using clinical notes, and the second is a baseline regression model using largely structured data. Our document classification model achieved an F1 score of 0.75 while our model using structured data achieved an F1 of 0.72, both exceeding the predictive performance of a psychiatry team who reviewed the same documents (0.5 F1). To aid in the explainability and understanding of risk factors for violent events, we additionally trained a named entity recognition classifier on annotations of the same corpus, which achieved an overall F1 of 0.7. This study demonstrates the first deep learning model capable of predicting violent events within healthcare settings using clinical notes, surpassing the first published baseline of human experts. We anticipate our methods can be generalized and extended to enable intervention at other hospital systems.
Document Type: article
File Description: electronic resource
Language: English
ISSN: 2731-4251
Relation: https://doaj.org/toc/2731-4251
DOI: 10.1038/s44184-024-00105-7
Access URL: https://doaj.org/article/f4f839b28d394e4b9bbd7e3473d55876
Accession Number: edsdoj.f4f839b28d394e4b9bbd7e3473d55876
Database: Directory of Open Access Journals
FullText Links:
  – Type: other
    Url: https://resolver.ebsco.com:443/public/rma-ftfapi/ejs/direct?AccessToken=4DF9820FEE6C25CFC6A2&Show=Object
Text:
  Availability: 0
CustomLinks:
  – Url: https://resolver.ebsco.com/c/xy5jbn/result?sid=EBSCO:edsdoj&genre=article&issn=27314251&ISBN=&volume=3&issue=1&date=20241201&spage=1&pages=1-8&title=npj Mental Health Research&atitle=Deep%20learning%20models%20can%20predict%20violence%20and%20threats%20against%20healthcare%20providers%20using%20clinical%20notes&aulast=Nicholas%20J.%20Dobbins&id=DOI:10.1038/s44184-024-00105-7
    Name: Full Text Finder (for New FTF UI) (s8985755)
    Category: fullText
    Text: Find It @ SCU Libraries
    MouseOverText: Find It @ SCU Libraries
  – Url: https://doaj.org/article/f4f839b28d394e4b9bbd7e3473d55876
    Name: EDS - DOAJ (s8985755)
    Category: fullText
    Text: View record from DOAJ
    MouseOverText: View record from DOAJ
Header DbId: edsdoj
DbLabel: Directory of Open Access Journals
An: edsdoj.f4f839b28d394e4b9bbd7e3473d55876
RelevancyScore: 1063
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 1063.04321289063
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Deep learning models can predict violence and threats against healthcare providers using clinical notes
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Nicholas+J%2E+Dobbins%22">Nicholas J. Dobbins</searchLink><br /><searchLink fieldCode="AR" term="%22Jacqueline+Chipkin%22">Jacqueline Chipkin</searchLink><br /><searchLink fieldCode="AR" term="%22Tim+Byrne%22">Tim Byrne</searchLink><br /><searchLink fieldCode="AR" term="%22Omar+Ghabra%22">Omar Ghabra</searchLink><br /><searchLink fieldCode="AR" term="%22Julia+Siar%22">Julia Siar</searchLink><br /><searchLink fieldCode="AR" term="%22Mitchell+Sauder%22">Mitchell Sauder</searchLink><br /><searchLink fieldCode="AR" term="%22R%2E+Michael+Huijon%22">R. Michael Huijon</searchLink><br /><searchLink fieldCode="AR" term="%22Taylor+M%2E+Black%22">Taylor M. Black</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: npj Mental Health Research, Vol 3, Iss 1, Pp 1-8 (2024)
– Name: Publisher
  Label: Publisher Information
  Group: PubInfo
  Data: Nature Portfolio, 2024.
– Name: DatePubCY
  Label: Publication Year
  Group: Date
  Data: 2024
– Name: Subset
  Label: Collection
  Group: HoldingsInfo
  Data: LCC:Therapeutics. Psychotherapy
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Therapeutics%2E+Psychotherapy%22">Therapeutics. Psychotherapy</searchLink><br /><searchLink fieldCode="DE" term="%22RC475-489%22">RC475-489</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: Abstract Violence, verbal abuse, threats, and sexual harassment of healthcare providers by patients is a major challenge for healthcare organizations around the world, contributing to staff turnover, distress, absenteeism, reduced job satisfaction, and worsening mental and physical health. To enable interventions prior to possible violent episodes, we trained two deep learning models to predict violence against healthcare workers 3 days prior to violent events for case and control patients. The first model is a document classification model using clinical notes, and the second is a baseline regression model using largely structured data. Our document classification model achieved an F1 score of 0.75 while our model using structured data achieved an F1 of 0.72, both exceeding the predictive performance of a psychiatry team who reviewed the same documents (0.5 F1). To aid in the explainability and understanding of risk factors for violent events, we additionally trained a named entity recognition classifier on annotations of the same corpus, which achieved an overall F1 of 0.7. This study demonstrates the first deep learning model capable of predicting violent events within healthcare settings using clinical notes, surpassing the first published baseline of human experts. We anticipate our methods can be generalized and extended to enable intervention at other hospital systems.
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: article
– Name: Format
  Label: File Description
  Group: SrcInfo
  Data: electronic resource
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: ISSN
  Label: ISSN
  Group: ISSN
  Data: 2731-4251
– Name: NoteTitleSource
  Label: Relation
  Group: SrcInfo
  Data: https://doaj.org/toc/2731-4251
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1038/s44184-024-00105-7
– Name: URL
  Label: Access URL
  Group: URL
  Data: <link linkTarget="URL" linkTerm="https://doaj.org/article/f4f839b28d394e4b9bbd7e3473d55876" linkWindow="_blank">https://doaj.org/article/f4f839b28d394e4b9bbd7e3473d55876</link>
– Name: AN
  Label: Accession Number
  Group: ID
  Data: edsdoj.f4f839b28d394e4b9bbd7e3473d55876
PLink https://login.libproxy.scu.edu/login?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsdoj&AN=edsdoj.f4f839b28d394e4b9bbd7e3473d55876
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1038/s44184-024-00105-7
    Languages:
      – Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 8
        StartPage: 1
    Subjects:
      – SubjectFull: Therapeutics. Psychotherapy
        Type: general
      – SubjectFull: RC475-489
        Type: general
    Titles:
      – TitleFull: Deep learning models can predict violence and threats against healthcare providers using clinical notes
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Nicholas J. Dobbins
      – PersonEntity:
          Name:
            NameFull: Jacqueline Chipkin
      – PersonEntity:
          Name:
            NameFull: Tim Byrne
      – PersonEntity:
          Name:
            NameFull: Omar Ghabra
      – PersonEntity:
          Name:
            NameFull: Julia Siar
      – PersonEntity:
          Name:
            NameFull: Mitchell Sauder
      – PersonEntity:
          Name:
            NameFull: R. Michael Huijon
      – PersonEntity:
          Name:
            NameFull: Taylor M. Black
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 12
              Type: published
              Y: 2024
          Identifiers:
            – Type: issn-print
              Value: 27314251
          Numbering:
            – Type: volume
              Value: 3
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: npj Mental Health Research
              Type: main
ResultId 1