View in EDS HTML Full Text PDF Full Text

Development of Attention-based Prediction Models for All-cause Mortality, Home Care Need, and Nursing Home Admission in Ageing Adults in Spain Using Longitudinal Electronic Health Record Data.

Saved in:
Bibliographic Details
Title: Development of Attention-based Prediction Models for All-cause Mortality, Home Care Need, and Nursing Home Admission in Ageing Adults in Spain Using Longitudinal Electronic Health Record Data.
Authors: Carrasco-Ribelles, Lucía A.1,2,3, Cabrera-Bean, Margarita2, Khalid, Sara4, Roso-Llorach, Albert1, Violán, Concepción3,5,6,7 cviolanf.mn.ics@gencat.cat
Source: Journal of Medical Systems. 1/25/2025, Vol. 49 Issue 1, p1-12. 12p.
Subjects: Home care services, Prediction models, Death, Patients, Research funding, Receiver operating characteristic curves, Hospital admission & discharge, Primary health care, Probability theory, Nursing care facilities, Attention, Longitudinal method, Electronic health records, Deep learning, Needs assessment, Honesty, Calibration, Sensitivity & specificity (Statistics)
Geographic Terms: Spain
Abstract: Predicting health-related outcomes can help with proactive healthcare planning and resource management. This is especially important on the older population, an age group growing in the coming decades. Considering longitudinal rather than cross-sectional information from primary care electronic health records (EHRs) can contribute to more informed predictions. In this work, we developed prediction models using longitudinal EHRs to inform resource allocation. In this study, we developed deep-learning-based prognostic models to predict 1-year and 5-year all-cause mortality, nursing home admission, and home care need in people over 65 years old using all the longitudinal information from EHRs. The models included attention mechanisms to increase their transparency. EHRs were drawn from SIDIAP (primary care, Catalonia (Spain)) from 2010-2019. Performance on the test set was compared to that from baseline models using cross-sectional one-year history only. Data from 1,456,052 individuals over 65 years old were considered. Cohen's kappa obtained using longitudinal data was 3.4-fold (1-year all-cause mortality), 10.3-fold (5-year all-cause mortality), 1.1-fold (5-year nursing home admission), and 1.2-fold (5-year home care need) higher than that obtained by the one-year history baseline models. Our models performed better than those not considering longitudinal data, especially when predicting further into the future. However, nursing home admission and home care need in the long term were harder to predict, suggesting their dependence on more abrupt changes. The attention maps helped to understand the predictions, enhancing model transparency. These prediction models can contribute to improve resource allocation in the general population of aging adults. [ABSTRACT FROM AUTHOR]
Copyright of Journal of Medical Systems is the property of Springer Nature 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
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 183076976
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Development of Attention-based Prediction Models for All-cause Mortality, Home Care Need, and Nursing Home Admission in Ageing Adults in Spain Using Longitudinal Electronic Health Record Data.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Carrasco-Ribelles%2C+Lucía+A%2E%22">Carrasco-Ribelles, Lucía A.</searchLink><relatesTo>1,2,3</relatesTo><br /><searchLink fieldCode="AR" term="%22Cabrera-Bean%2C+Margarita%22">Cabrera-Bean, Margarita</searchLink><relatesTo>2</relatesTo><br /><searchLink fieldCode="AR" term="%22Khalid%2C+Sara%22">Khalid, Sara</searchLink><relatesTo>4</relatesTo><br /><searchLink fieldCode="AR" term="%22Roso-Llorach%2C+Albert%22">Roso-Llorach, Albert</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Violán%2C+Concepción%22">Violán, Concepción</searchLink><relatesTo>3,5,6,7</relatesTo><i> cviolanf.mn.ics@gencat.cat</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Journal+of+Medical+Systems%22">Journal of Medical Systems</searchLink>. 1/25/2025, Vol. 49 Issue 1, p1-12. 12p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Home+care+services%22">Home care services</searchLink><br /><searchLink fieldCode="DE" term="%22Prediction+models%22">Prediction models</searchLink><br /><searchLink fieldCode="DE" term="%22Death%22">Death</searchLink><br /><searchLink fieldCode="DE" term="%22Patients%22">Patients</searchLink><br /><searchLink fieldCode="DE" term="%22Research+funding%22">Research funding</searchLink><br /><searchLink fieldCode="DE" term="%22Receiver+operating+characteristic+curves%22">Receiver operating characteristic curves</searchLink><br /><searchLink fieldCode="DE" term="%22Hospital+admission+%26+discharge%22">Hospital admission & discharge</searchLink><br /><searchLink fieldCode="DE" term="%22Primary+health+care%22">Primary health care</searchLink><br /><searchLink fieldCode="DE" term="%22Probability+theory%22">Probability theory</searchLink><br /><searchLink fieldCode="DE" term="%22Nursing+care+facilities%22">Nursing care facilities</searchLink><br /><searchLink fieldCode="DE" term="%22Attention%22">Attention</searchLink><br /><searchLink fieldCode="DE" term="%22Longitudinal+method%22">Longitudinal method</searchLink><br /><searchLink fieldCode="DE" term="%22Electronic+health+records%22">Electronic health records</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Needs+assessment%22">Needs assessment</searchLink><br /><searchLink fieldCode="DE" term="%22Honesty%22">Honesty</searchLink><br /><searchLink fieldCode="DE" term="%22Calibration%22">Calibration</searchLink><br /><searchLink fieldCode="DE" term="%22Sensitivity+%26+specificity+%28Statistics%29%22">Sensitivity & specificity (Statistics)</searchLink>
– Name: SubjectGeographic
  Label: Geographic Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Spain%22">Spain</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Predicting health-related outcomes can help with proactive healthcare planning and resource management. This is especially important on the older population, an age group growing in the coming decades. Considering longitudinal rather than cross-sectional information from primary care electronic health records (EHRs) can contribute to more informed predictions. In this work, we developed prediction models using longitudinal EHRs to inform resource allocation. In this study, we developed deep-learning-based prognostic models to predict 1-year and 5-year all-cause mortality, nursing home admission, and home care need in people over 65 years old using all the longitudinal information from EHRs. The models included attention mechanisms to increase their transparency. EHRs were drawn from SIDIAP (primary care, Catalonia (Spain)) from 2010-2019. Performance on the test set was compared to that from baseline models using cross-sectional one-year history only. Data from 1,456,052 individuals over 65 years old were considered. Cohen's kappa obtained using longitudinal data was 3.4-fold (1-year all-cause mortality), 10.3-fold (5-year all-cause mortality), 1.1-fold (5-year nursing home admission), and 1.2-fold (5-year home care need) higher than that obtained by the one-year history baseline models. Our models performed better than those not considering longitudinal data, especially when predicting further into the future. However, nursing home admission and home care need in the long term were harder to predict, suggesting their dependence on more abrupt changes. The attention maps helped to understand the predictions, enhancing model transparency. These prediction models can contribute to improve resource allocation in the general population of aging adults. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Journal of Medical Systems is the property of Springer Nature 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=183076976
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s10916-024-02138-z
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 12
        StartPage: 1
    Subjects:
      – SubjectFull: Home care services
        Type: general
      – SubjectFull: Prediction models
        Type: general
      – SubjectFull: Death
        Type: general
      – SubjectFull: Patients
        Type: general
      – SubjectFull: Research funding
        Type: general
      – SubjectFull: Receiver operating characteristic curves
        Type: general
      – SubjectFull: Hospital admission & discharge
        Type: general
      – SubjectFull: Primary health care
        Type: general
      – SubjectFull: Probability theory
        Type: general
      – SubjectFull: Nursing care facilities
        Type: general
      – SubjectFull: Attention
        Type: general
      – SubjectFull: Longitudinal method
        Type: general
      – SubjectFull: Electronic health records
        Type: general
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Needs assessment
        Type: general
      – SubjectFull: Honesty
        Type: general
      – SubjectFull: Calibration
        Type: general
      – SubjectFull: Sensitivity & specificity (Statistics)
        Type: general
      – SubjectFull: Spain
        Type: general
    Titles:
      – TitleFull: Development of Attention-based Prediction Models for All-cause Mortality, Home Care Need, and Nursing Home Admission in Ageing Adults in Spain Using Longitudinal Electronic Health Record Data.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Carrasco-Ribelles, Lucía A.
      – PersonEntity:
          Name:
            NameFull: Cabrera-Bean, Margarita
      – PersonEntity:
          Name:
            NameFull: Khalid, Sara
      – PersonEntity:
          Name:
            NameFull: Roso-Llorach, Albert
      – PersonEntity:
          Name:
            NameFull: Violán, Concepción
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 25
              M: 01
              Text: 1/25/2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 01485598
          Numbering:
            – Type: volume
              Value: 49
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: Journal of Medical Systems
              Type: main
ResultId 1