Multi–task deep survival analysis links acute exacerbation frequency to hip fracture risk in advanced COPD.

• Developed first multitask deep learning model integrating hip fracture risk and acute exacerbation prediction in advanced COPD patients. • Multitask deep learning model predicts COPD hip fracture risk (C-index 0.725) and acute exacerbation frequency (MSE 0.522). • Each acute COPD exacerbation link...

Descripción completa

Detalles Bibliográficos
Publicado en:Heart & Lung Vol. 76; pp. 164 - 174
Autores principales: Xu, Pengyu, Wang, Xiaoyu, Li, Zhuying
Formato: research Journal Article
Publicado: Elsevier B.V. Mar2026
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=192300677&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 192300677
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        01479563
        04L
      jtl: Heart & Lung
      issn: 01479563
      maglogo: N
    pubinfo:
      dt: Mar2026
      vid: 76
      pid: 467
      pub: Elsevier B.V.
      place: New York, New York
    artinfo:
      ui:
        192300677
        192300677
        192300677
        10.1016/j.hrtlng.2025.10.008
        192300677
      ppf: 164
      ppct: 10
      formats:
      tig:
        atl: Multi–task deep survival analysis links acute exacerbation frequency to hip fracture risk in advanced COPD.
      aug:
        au:
          Xu, Pengyu
          Wang, Xiaoyu
          Li, Zhuying
        affil: Heilongjiang University of Chinese Medicine, Harbin, Heilongjiang 150040, China
      sug:
        subj:
          Deep Learning
          Survival Analysis
          Disease Exacerbation
          Prediction Models
          Hip Fractures Risk Factors
          Pulmonary Disease, Chronic Obstructive Physiopathology
          Severity of Illness
          Human
          Multitasking Behavior
          Inflammation
          Osteoporotic Fractures
          Muscle, Skeletal
          China
          Prospective Studies
          Cox Proportional Hazards Model
          Biological Markers
          Confidence Intervals
          Risk Assessment
      ab: • Developed first multitask deep learning model integrating hip fracture risk and acute exacerbation prediction in advanced COPD patients. • Multitask deep learning model predicts COPD hip fracture risk (C-index 0.725) and acute exacerbation frequency (MSE 0.522). • Each acute COPD exacerbation linked to 28 % higher fracture hazard, revealing inflammation-bone fragility interplay. • Lung function decline drive skeletal vulnerability in COPD patients. Chronic obstructive pulmonary disease (COPD) is linked to elevated hip fracture risk, but validated prediction tools integrating disease–specific pathophysiology are lacking. To develop a multitask deep learning model predicting hip fracture risk and acute exacerbation frequency in COPD patients, and identify key predictors of skeletal vulnerability. This retrospective cohort study analyzed 4995 COPD patients (245 incident hip fractures) from the China Health and Retirement Longitudinal Study (CHARLS). A multitask deep survival model combined Cox proportional hazards (fracture prediction) and regression (exacerbation frequency) tasks, integrating demographic, clinical, and biomarker data. Performance was evaluated via concordance index (C–index) and mean squared error (MSE). The model achieved a C–index of 0.725 for fracture prediction and MSE of 0.522 for exacerbation frequency, outperforming conventional methods. Key predictors included acute exacerbation frequency (fracture group: 2.5 ± 4.4 vs. non–fracture: 1.1 ± 2.2 events/year; adjusted HR = 1.28 per additional event, 95 % CI: 1.19–1.38) and baseline lung function (fracture group: 262.7 ± 96.7 mL vs. non–fracture: 277.4 ± 85.7 mL). Frequent hospitalizations (≥2/year) increased fracture risk by 47 %. Systemic inflammation (elevated CRP/IL–6) and age further contributed to skeletal vulnerability. This study establishes the first multitask deep learning framework for COPD–related fracture risk, demonstrating superior performance through multidimensional feature synthesis. The model enables personalized prevention by highlighting exacerbation burden, lung function decline, and inflammation as critical risk factors.
      pubtype: Academic Journal
      doctype:
        research
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N