Machine learning-based prediction of short- and long-term mortality for shared decision-making in older hip fracture patients: the Dutch Hip Fracture Audit algorithms in 74,396 cases.

Background and purpose — Treatment-related shared decision-making (SDM) in older adults with hip fractures is complex due to the need to balance patient-specific factors such as life goals, frailty, and surgical risks. It includes considerations such as prognosis and decisions concerning whether to...

Descripción completa

Detalles Bibliográficos
Publicado en:Acta Orthopaedica Vol. 96; pp. 521 - 529
Autores principales: DIJKSTRA, Hidde, PARSONS, Cathleen S., VAN BREMEN 4-, Hanne-Eva, WILLEMS, Hanna C., DE HOND, Anne A. H., VAN MUNSTER, Barbara C., DOORNBERG, Job N., OOSTERHOFF, Jacobien H. F.
Formato: research tables/charts Journal Article
Publicado: Medical Journals Sweden AB 2025
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=191461400&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 191461400
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        17453674
        1BVL
      jtl: Acta Orthopaedica
      issn: 17453674
      maglogo: N
    pubinfo:
      dt: 2025
      vid: 96
      pid: 59195
      pub: Medical Journals Sweden AB
    artinfo:
      ui:
        191461400
        191461400
        191461400
        10.2340/17453674.2025.44248
        191461400
      ppf: 521
      ppct: 8
      formats:
        fmt:
          @attributes:
            type: P
      tig:
        atl: Machine learning-based prediction of short- and long-term mortality for shared decision-making in older hip fracture patients: the Dutch Hip Fracture Audit algorithms in 74,396 cases.
      aug:
        au:
          DIJKSTRA, Hidde
          PARSONS, Cathleen S.
          VAN BREMEN 4-, Hanne-Eva
          WILLEMS, Hanna C.
          DE HOND, Anne A. H.
          VAN MUNSTER, Barbara C.
          DOORNBERG, Job N.
          OOSTERHOFF, Jacobien H. F.
        affil: Department of Orthopaedic Surgery, University Medical Centre Groningen, University of Groningen.
      sug:
        subj:
          Machine Learning Algorithms
          Prediction Algorithms
          Prediction Models
          Mortality Risk Factors
          Decision Making, Shared
          Hip Fractures Mortality
          Risk Assessment
          Decision Making, Computer Assisted
          Hip Fractures Surgery
          Fracture Fixation
          Frail Elderly
          Human
          Male
          Female
          Aged
          Aged, 80 and Over
          Audit
          Retrospective Design
          Hip Fractures Prognosis
          Netherlands
          Sensitivity and Specificity
          Calibration
          Malnutrition
          Dementia Patients
          Logistic Regression
          Prospective Studies
          Functional Status
          Boosting Machine Learning Algorithms
          Random Forest
          Support Vector Machine
          Clinical Assessment Tools
          Geriatric Functional Assessment
          Physical Mobility
          Data Analysis Software
          Descriptive Statistics
          Confidence Intervals
          Correlation Coefficient
          Funding Source
          Aged: 65+ years
          Aged, 80 & over
          Male
          Female
      ab: Background and purpose — Treatment-related shared decision-making (SDM) in older adults with hip fractures is complex due to the need to balance patient-specific factors such as life goals, frailty, and surgical risks. It includes considerations such as prognosis and decisions concerning whether to operate or not on frail, life-limited patients. We aimed to develop machine learning (ML)-driven prediction models for short- and long-term mortality in a large cohort of patients with hip fractures. Methods — In this national registry-based retrospective cohort study, patients aged ≥ 70 years registered in the nationwide Dutch Hip Fracture Audit from 2018–2023 were included. Predictive variables were selected based on the literature and/or clinical relevance. 6 ML algorithms, including logistic regression, were trained with internal cross-validation and evaluated on discrimination (c-statistic), sensitivity, specificity, calibration, and interpretability. Results — 74,396 patients (median age 84, IQR 78–89; 68% female) were analyzed. Most patients lived at home (69%) and high malnutrition risk was seen in 10%. 18% had dementia. Mortality rates were 9.1% (30-day), 15% (90- day), and 26% (1-year). Logistic regression performed comparably to other algorithms, but was chosen as the preferred algorithm due to its superior interpretability (c-statistic: 30-day 0.82, 90-day 0.81, 1-year 0.80). Conclusion — We developed and validated ML algorithms, including logistic regression, for mortality prediction in older hip fracture patients with adequate performance. This information may inform SDM.
      pubtype: Academic Journal
      doctype:
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N