View in EDS

A Resampling Based Grid Search Method to Improve Reliability and Robustness of Mixture-Item Response Theory Models of Multimorbid High-Risk Patients.

Saved in:
Bibliographic Details
Title: A Resampling Based Grid Search Method to Improve Reliability and Robustness of Mixture-Item Response Theory Models of Multimorbid High-Risk Patients.
Authors: Batten, Adam J.1 (AUTHOR) adam.batten@va.gov, Thorpe, Joshua2 (AUTHOR) joshua.thorpe@va.gov, Piegari, Rebecca I.3 (AUTHOR) rebecca.piegari@va.gov, Rosland, Ann-Marie2 (AUTHOR) ann-marie.rosland@va.gov
Source: IEEE Journal of Biomedical & Health Informatics. Jun2020, Vol. 24 Issue 6, p1780-1787. 8p.
Subjects: Comorbidity, Item response theory, Model theory, Akaike information criterion, Chronic diseases, Information measurement, Failure mode & effects analysis
Abstract: There are many statistics available to the applied statistician for assessing model fit and even more methods for assessing internal and external validity. We detail a useful approach using a grid search technique that balances the internal model consistency with generalizability and can be used with models that naturally lend themselves to multiple assessment techniques. Our method relies on resampling and a simple grid search method over 3 commonly used statistics that are simple to calculate. We apply this method in a latent traits framework using a mixture Item Response Theory (MIXIRT) model of common chronic health conditions. Model fit is assessed using Akaike's Information Criteria (AIC), latent class similarity is measured with the Variance of Information (VI), and the consistency of condition complexity and prevalence across latent classes is compared using Kendall's τ rank order statistic. From two patient cohorts at high risk for hospitalization in 2014 and 2018, we generated 19 MIXIRT models (allowing 2–20 latent classes) on 21 common comorbid conditions identified via healthcare encounter diagnosis codes. We ran these models on 100 bootstrap samples of size 10% for each cohort. Among the resulting models, combined AIC and VI statistics identified 5–7 latent classes, but the rank order correlation of condition complexity revealed that only the 5 class solutions had consistent condition complexity. The 5 class solutions were combined to produce a single parsimonious MIXIRT solution that balanced clinical significance with model fit, cluster similarity, and consistency of condition complexity. [ABSTRACT FROM AUTHOR]
Copyright of IEEE Journal of Biomedical & Health Informatics is the property of IEEE 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: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 143721366
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: A Resampling Based Grid Search Method to Improve Reliability and Robustness of Mixture-Item Response Theory Models of Multimorbid High-Risk Patients.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Batten%2C+Adam+J%2E%22">Batten, Adam J.</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> adam.batten@va.gov</i><br /><searchLink fieldCode="AR" term="%22Thorpe%2C+Joshua%22">Thorpe, Joshua</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> joshua.thorpe@va.gov</i><br /><searchLink fieldCode="AR" term="%22Piegari%2C+Rebecca+I%2E%22">Piegari, Rebecca I.</searchLink><relatesTo>3</relatesTo> (AUTHOR)<i> rebecca.piegari@va.gov</i><br /><searchLink fieldCode="AR" term="%22Rosland%2C+Ann-Marie%22">Rosland, Ann-Marie</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> ann-marie.rosland@va.gov</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22IEEE+Journal+of+Biomedical+%26+Health+Informatics%22">IEEE Journal of Biomedical & Health Informatics</searchLink>. Jun2020, Vol. 24 Issue 6, p1780-1787. 8p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Comorbidity%22">Comorbidity</searchLink><br /><searchLink fieldCode="DE" term="%22Item+response+theory%22">Item response theory</searchLink><br /><searchLink fieldCode="DE" term="%22Model+theory%22">Model theory</searchLink><br /><searchLink fieldCode="DE" term="%22Akaike+information+criterion%22">Akaike information criterion</searchLink><br /><searchLink fieldCode="DE" term="%22Chronic+diseases%22">Chronic diseases</searchLink><br /><searchLink fieldCode="DE" term="%22Information+measurement%22">Information measurement</searchLink><br /><searchLink fieldCode="DE" term="%22Failure+mode+%26+effects+analysis%22">Failure mode & effects analysis</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: There are many statistics available to the applied statistician for assessing model fit and even more methods for assessing internal and external validity. We detail a useful approach using a grid search technique that balances the internal model consistency with generalizability and can be used with models that naturally lend themselves to multiple assessment techniques. Our method relies on resampling and a simple grid search method over 3 commonly used statistics that are simple to calculate. We apply this method in a latent traits framework using a mixture Item Response Theory (MIXIRT) model of common chronic health conditions. Model fit is assessed using Akaike's Information Criteria (AIC), latent class similarity is measured with the Variance of Information (VI), and the consistency of condition complexity and prevalence across latent classes is compared using Kendall's τ rank order statistic. From two patient cohorts at high risk for hospitalization in 2014 and 2018, we generated 19 MIXIRT models (allowing 2–20 latent classes) on 21 common comorbid conditions identified via healthcare encounter diagnosis codes. We ran these models on 100 bootstrap samples of size 10% for each cohort. Among the resulting models, combined AIC and VI statistics identified 5–7 latent classes, but the rank order correlation of condition complexity revealed that only the 5 class solutions had consistent condition complexity. The 5 class solutions were combined to produce a single parsimonious MIXIRT solution that balanced clinical significance with model fit, cluster similarity, and consistency of condition complexity. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of IEEE Journal of Biomedical & Health Informatics is the property of IEEE 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=egs&AN=143721366
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1109/JBHI.2019.2948734
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 8
        StartPage: 1780
    Subjects:
      – SubjectFull: Comorbidity
        Type: general
      – SubjectFull: Item response theory
        Type: general
      – SubjectFull: Model theory
        Type: general
      – SubjectFull: Akaike information criterion
        Type: general
      – SubjectFull: Chronic diseases
        Type: general
      – SubjectFull: Information measurement
        Type: general
      – SubjectFull: Failure mode & effects analysis
        Type: general
    Titles:
      – TitleFull: A Resampling Based Grid Search Method to Improve Reliability and Robustness of Mixture-Item Response Theory Models of Multimorbid High-Risk Patients.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Batten, Adam J.
      – PersonEntity:
          Name:
            NameFull: Thorpe, Joshua
      – PersonEntity:
          Name:
            NameFull: Piegari, Rebecca I.
      – PersonEntity:
          Name:
            NameFull: Rosland, Ann-Marie
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 06
              Text: Jun2020
              Type: published
              Y: 2020
          Identifiers:
            – Type: issn-print
              Value: 21682194
          Numbering:
            – Type: volume
              Value: 24
            – Type: issue
              Value: 6
          Titles:
            – TitleFull: IEEE Journal of Biomedical & Health Informatics
              Type: main
ResultId 1