View in EDS

Improved accuracy and efficiency of primary care fall risk screening of older adults using a machine learning approach.

Saved in:
Bibliographic Details
Title: Improved accuracy and efficiency of primary care fall risk screening of older adults using a machine learning approach.
Authors: Song, Wenyu, Latham, Nancy K., Liu, Luwei, Rice, Hannah E., Sainlaire, Michael, Min, Lillian, Zhang, Linying, Thai, Tien, Kang, Min‐Jeoung, Li, Siyun, Tejeda, Christian, Lipsitz, Stuart, Samal, Lipika, Carroll, Diane L., Adkison, Lesley, Herlihy, Lisa, Ryan, Virginia, Bates, David W., Dykes, Patricia C.
Source: Journal of the American Geriatrics Society. Apr2024, Vol. 72 Issue 4, p1145-1154. 10p.
Subjects: Wounds & injuries, Risk assessment, Receiver operating characteristic curves, Independent living, Research funding, Questionnaires, Clinical decision support systems, Causes of death, Descriptive statistics, Case-control method, Electronic health records, Medical screening, Machine learning, Accidental falls, Old age
Abstract: Background: While many falls are preventable, they remain a leading cause of injury and death in older adults. Primary care clinics largely rely on screening questionnaires to identify people at risk of falls. Limitations of standard fall risk screening questionnaires include suboptimal accuracy, missing data, and non‐standard formats, which hinder early identification of risk and prevention of fall injury. We used machine learning methods to develop and evaluate electronic health record (EHR)‐based tools to identify older adults at risk of fall‐related injuries in a primary care population and compared this approach to standard fall screening questionnaires. Methods: Using patient‐level clinical data from an integrated healthcare system consisting of 16‐member institutions, we conducted a case–control study to develop and evaluate prediction models for fall‐related injuries in older adults. Questionnaire‐derived prediction with three questions from a commonly used fall risk screening tool was evaluated. We then developed four temporal machine learning models using routinely available longitudinal EHR data to predict the future risk of fall injury. We also developed a fall injury‐prevention clinical decision support (CDS) implementation prototype to link preventative interventions to patient‐specific fall injury risk factors. Results: Questionnaire‐based risk screening achieved area under the receiver operating characteristic curve (AUC) up to 0.59 with 23% to 33% similarity for each pair of three fall injury screening questions. EHR‐based machine learning risk screening showed significantly improved performance (best AUROC = 0.76), with similar prediction performance between 6‐month and one‐year prediction models. Conclusions: The current method of questionnaire‐based fall risk screening of older adults is suboptimal with redundant items, inadequate precision, and no linkage to prevention. A machine learning fall injury prediction method can accurately predict risk with superior sensitivity while freeing up clinical time for initiating personalized fall prevention interventions. The developed algorithm and data science pipeline can impact routine primary care fall prevention practice. [ABSTRACT FROM AUTHOR]
Copyright of Journal of the American Geriatrics Society is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Psychology and Behavioral Sciences Collection
FullText Text:
  Availability: 0
Header DbId: pbh
DbLabel: Psychology and Behavioral Sciences Collection
An: 176608235
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Improved accuracy and efficiency of primary care fall risk screening of older adults using a machine learning approach.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Song%2C+Wenyu%22">Song, Wenyu</searchLink><br /><searchLink fieldCode="AR" term="%22Latham%2C+Nancy+K%2E%22">Latham, Nancy K.</searchLink><br /><searchLink fieldCode="AR" term="%22Liu%2C+Luwei%22">Liu, Luwei</searchLink><br /><searchLink fieldCode="AR" term="%22Rice%2C+Hannah+E%2E%22">Rice, Hannah E.</searchLink><br /><searchLink fieldCode="AR" term="%22Sainlaire%2C+Michael%22">Sainlaire, Michael</searchLink><br /><searchLink fieldCode="AR" term="%22Min%2C+Lillian%22">Min, Lillian</searchLink><br /><searchLink fieldCode="AR" term="%22Zhang%2C+Linying%22">Zhang, Linying</searchLink><br /><searchLink fieldCode="AR" term="%22Thai%2C+Tien%22">Thai, Tien</searchLink><br /><searchLink fieldCode="AR" term="%22Kang%2C+Min‐Jeoung%22">Kang, Min‐Jeoung</searchLink><br /><searchLink fieldCode="AR" term="%22Li%2C+Siyun%22">Li, Siyun</searchLink><br /><searchLink fieldCode="AR" term="%22Tejeda%2C+Christian%22">Tejeda, Christian</searchLink><br /><searchLink fieldCode="AR" term="%22Lipsitz%2C+Stuart%22">Lipsitz, Stuart</searchLink><br /><searchLink fieldCode="AR" term="%22Samal%2C+Lipika%22">Samal, Lipika</searchLink><br /><searchLink fieldCode="AR" term="%22Carroll%2C+Diane+L%2E%22">Carroll, Diane L.</searchLink><br /><searchLink fieldCode="AR" term="%22Adkison%2C+Lesley%22">Adkison, Lesley</searchLink><br /><searchLink fieldCode="AR" term="%22Herlihy%2C+Lisa%22">Herlihy, Lisa</searchLink><br /><searchLink fieldCode="AR" term="%22Ryan%2C+Virginia%22">Ryan, Virginia</searchLink><br /><searchLink fieldCode="AR" term="%22Bates%2C+David+W%2E%22">Bates, David W.</searchLink><br /><searchLink fieldCode="AR" term="%22Dykes%2C+Patricia+C%2E%22">Dykes, Patricia C.</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Journal+of+the+American+Geriatrics+Society%22">Journal of the American Geriatrics Society</searchLink>. Apr2024, Vol. 72 Issue 4, p1145-1154. 10p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Wounds+%26+injuries%22">Wounds & injuries</searchLink><br /><searchLink fieldCode="DE" term="%22Risk+assessment%22">Risk assessment</searchLink><br /><searchLink fieldCode="DE" term="%22Receiver+operating+characteristic+curves%22">Receiver operating characteristic curves</searchLink><br /><searchLink fieldCode="DE" term="%22Independent+living%22">Independent living</searchLink><br /><searchLink fieldCode="DE" term="%22Research+funding%22">Research funding</searchLink><br /><searchLink fieldCode="DE" term="%22Questionnaires%22">Questionnaires</searchLink><br /><searchLink fieldCode="DE" term="%22Clinical+decision+support+systems%22">Clinical decision support systems</searchLink><br /><searchLink fieldCode="DE" term="%22Causes+of+death%22">Causes of death</searchLink><br /><searchLink fieldCode="DE" term="%22Descriptive+statistics%22">Descriptive statistics</searchLink><br /><searchLink fieldCode="DE" term="%22Case-control+method%22">Case-control method</searchLink><br /><searchLink fieldCode="DE" term="%22Electronic+health+records%22">Electronic health records</searchLink><br /><searchLink fieldCode="DE" term="%22Medical+screening%22">Medical screening</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Accidental+falls%22">Accidental falls</searchLink><br /><searchLink fieldCode="DE" term="%22Old+age%22">Old age</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Background: While many falls are preventable, they remain a leading cause of injury and death in older adults. Primary care clinics largely rely on screening questionnaires to identify people at risk of falls. Limitations of standard fall risk screening questionnaires include suboptimal accuracy, missing data, and non‐standard formats, which hinder early identification of risk and prevention of fall injury. We used machine learning methods to develop and evaluate electronic health record (EHR)‐based tools to identify older adults at risk of fall‐related injuries in a primary care population and compared this approach to standard fall screening questionnaires. Methods: Using patient‐level clinical data from an integrated healthcare system consisting of 16‐member institutions, we conducted a case–control study to develop and evaluate prediction models for fall‐related injuries in older adults. Questionnaire‐derived prediction with three questions from a commonly used fall risk screening tool was evaluated. We then developed four temporal machine learning models using routinely available longitudinal EHR data to predict the future risk of fall injury. We also developed a fall injury‐prevention clinical decision support (CDS) implementation prototype to link preventative interventions to patient‐specific fall injury risk factors. Results: Questionnaire‐based risk screening achieved area under the receiver operating characteristic curve (AUC) up to 0.59 with 23% to 33% similarity for each pair of three fall injury screening questions. EHR‐based machine learning risk screening showed significantly improved performance (best AUROC = 0.76), with similar prediction performance between 6‐month and one‐year prediction models. Conclusions: The current method of questionnaire‐based fall risk screening of older adults is suboptimal with redundant items, inadequate precision, and no linkage to prevention. A machine learning fall injury prediction method can accurately predict risk with superior sensitivity while freeing up clinical time for initiating personalized fall prevention interventions. The developed algorithm and data science pipeline can impact routine primary care fall prevention practice. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Journal of the American Geriatrics Society is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=pbh&AN=176608235
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1111/jgs.18776
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 10
        StartPage: 1145
    Subjects:
      – SubjectFull: Wounds & injuries
        Type: general
      – SubjectFull: Risk assessment
        Type: general
      – SubjectFull: Receiver operating characteristic curves
        Type: general
      – SubjectFull: Independent living
        Type: general
      – SubjectFull: Research funding
        Type: general
      – SubjectFull: Questionnaires
        Type: general
      – SubjectFull: Clinical decision support systems
        Type: general
      – SubjectFull: Causes of death
        Type: general
      – SubjectFull: Descriptive statistics
        Type: general
      – SubjectFull: Case-control method
        Type: general
      – SubjectFull: Electronic health records
        Type: general
      – SubjectFull: Medical screening
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Accidental falls
        Type: general
      – SubjectFull: Old age
        Type: general
    Titles:
      – TitleFull: Improved accuracy and efficiency of primary care fall risk screening of older adults using a machine learning approach.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Song, Wenyu
      – PersonEntity:
          Name:
            NameFull: Latham, Nancy K.
      – PersonEntity:
          Name:
            NameFull: Liu, Luwei
      – PersonEntity:
          Name:
            NameFull: Rice, Hannah E.
      – PersonEntity:
          Name:
            NameFull: Sainlaire, Michael
      – PersonEntity:
          Name:
            NameFull: Min, Lillian
      – PersonEntity:
          Name:
            NameFull: Zhang, Linying
      – PersonEntity:
          Name:
            NameFull: Thai, Tien
      – PersonEntity:
          Name:
            NameFull: Kang, Min‐Jeoung
      – PersonEntity:
          Name:
            NameFull: Li, Siyun
      – PersonEntity:
          Name:
            NameFull: Tejeda, Christian
      – PersonEntity:
          Name:
            NameFull: Lipsitz, Stuart
      – PersonEntity:
          Name:
            NameFull: Samal, Lipika
      – PersonEntity:
          Name:
            NameFull: Carroll, Diane L.
      – PersonEntity:
          Name:
            NameFull: Adkison, Lesley
      – PersonEntity:
          Name:
            NameFull: Herlihy, Lisa
      – PersonEntity:
          Name:
            NameFull: Ryan, Virginia
      – PersonEntity:
          Name:
            NameFull: Bates, David W.
      – PersonEntity:
          Name:
            NameFull: Dykes, Patricia C.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 04
              Text: Apr2024
              Type: published
              Y: 2024
          Identifiers:
            – Type: issn-print
              Value: 00028614
          Numbering:
            – Type: volume
              Value: 72
            – Type: issue
              Value: 4
          Titles:
            – TitleFull: Journal of the American Geriatrics Society
              Type: main
ResultId 1