A novel electronic-health-record based, machine-learning model to predict 1-year risk of fall hospitalisation in older adults: a Hong Kong territory-wide cohort and modelling study.

Objective Older adults face high risk of falls. We developed an electronic-health-record (EHR) based machine-learning (ML) model to predict 1-year risk of fall in older adults for pre-emptive intervention. Methods We included 4 902 161 records from 1 142 000 adults aged ≥65 years who attended the Ho...

Full description

Bibliographic Details
Published in:Age & Ageing Vol. 54; no. 10; pp. 1 - 13
Main Authors: Yang, Aimin, Shi, Mai, Lau, Eric S H, Yu, Jiazhou, Luk, Andrea O Y, Ma, Ronald C W, Kong, Alice P S, Wong, Raymond, Chan, Jones C M, Chan, Juliana C N, Chow, Elaine
Format: Article
Published: Oxford University Press / USA Oct2025
Subjects:
Online Access:View this record in EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ssf&AN=189289160&site=ehost-live
header:
  @attributes:
    shortDbName: ssf
    uiTerm: 189289160
    longDbName: Social Sciences Full Text (H.W. Wilson)
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        00020729
        AGA
      jtl: Age & Ageing
      issn: 00020729
      maglogo: N
    pubinfo:
      dt: Oct2025
      vid: 54
      iid: 10
      pid: 622
      pub: Oxford University Press / USA
    artinfo:
      ui:
        189289160
        10.1093/ageing/afaf285
      ppf: 1
      ppct: 12
      formats:
      tig:
        atl: A novel electronic-health-record based, machine-learning model to predict 1-year risk of fall hospitalisation in older adults: a Hong Kong territory-wide cohort and modelling study.
      aug:
        au:
          Yang, Aimin
          Shi, Mai
          Lau, Eric S H
          Yu, Jiazhou
          Luk, Andrea O Y
          Ma, Ronald C W
          Kong, Alice P S
          Wong, Raymond
          Chan, Jones C M
          Chan, Juliana C N
          Chow, Elaine
        affil:
          Department of Medicine and Therapeutics, The Chinese University of Hong Kong, Prince of Wales Hospital, Hong Kong Special Administrative Region, China
          Li Ka Shing Institute of Health Sciences, The Chinese University of Hong Kong, Prince of Wales Hospital, Hong Kong Special Administrative Region, China
          Hong Kong Institute of Diabetes and Obesity, The Chinese University of Hong Kong, Prince of Wales Hospital, Hong Kong Special Administrative Region, China
          Phase 1 Clinical Trial Centre, The Chinese University of Hong Kong, Prince of Wales Hospital, Hong Kong Special Administrative Region, China
      su:
        Hong Kong (China)
        Patients
        Hospital admission & discharge
        Residential patterns
        Hospitals
        Retrospective studies
        Age distribution
        Case-control method
        Hospital care of older people
        Fasting
        Old age
        Blood sugar analysis
        Predictive tests
        Random forest algorithms
        Early medical intervention
        Receiver operating characteristic curves
        Outpatient services in hospitals
        Logistic regression analysis
        Probability theory
        Questionnaires
        Diagnostic errors
        Descriptive statistics
        Hospital emergency services
        Electronic health records
        Medical records
        Acquisition of data
        Medical appointments
        Morse Fall Scale
        Machine learning
        Accuracy
        Calibration
        Accidental falls
        Sensitivity & specificity (Statistics)
        Algorithms
        Nosology
        Medical triage
        Drug utilization
        Evaluation
      sug:
        subj:
          Patients
          Hospital admission & discharge
          Residential patterns
          Hospitals
          Retrospective studies
          Age distribution
          Case-control method
          Hospital care of older people
          Fasting
          Old age
          Hong Kong (China)
          General Medical and Surgical Hospitals
          General (except paediatric) hospitals
          All Other Outpatient Care Centers
          Blood sugar analysis
          Predictive tests
          Random forest algorithms
          Early medical intervention
          Receiver operating characteristic curves
          Outpatient services in hospitals
          Logistic regression analysis
          Probability theory
          Questionnaires
          Diagnostic errors
          Descriptive statistics
          Hospital emergency services
          Electronic health records
          Medical records
          Acquisition of data
          Medical appointments
          Morse Fall Scale
          Machine learning
          Accuracy
          Calibration
          Accidental falls
          Sensitivity & specificity (Statistics)
          Algorithms
          Nosology
          Medical triage
          Drug utilization
          Evaluation
      keyword:
        adult
        area under the roc curve
        diabetes mellitus
        electric health records
        electronic medical records
        fall
        fall risks
        hong kong
        machine learning
        mental recall
        older adult
        older adults
        outpatients
        precision
        risk prediction
        type 2
        adult
        area under the roc curve
        diabetes mellitus
        electric health records
        electronic medical records
        fall
        fall risks
        hong kong
        machine learning
        mental recall
        older adult
        older adults
        outpatients
        precision
        risk prediction
        type 2
      ab: Objective Older adults face high risk of falls. We developed an electronic-health-record (EHR) based machine-learning (ML) model to predict 1-year risk of fall in older adults for pre-emptive intervention. Methods We included 4 902 161 records from 1 142 000 adults aged ≥65 years who attended the Hong Kong Hospital Authority (HA) facilities in 2013–2017. We included 260 predictors including demographics, in-patient/out-patient admissions, emergency department (ED) attendance, complications, medications and laboratory tests during 1-year period to predict fall events based on diagnostic codes in the ensuing 12 months. The cohort was randomly split into training, testing and internal validation sets in a 7:2:1 ratio. We evaluated the performance of six ML-algorithms. Results 67 163 fall events were accrued with the XGBoost model having the best performance in the validation set (area-under-the-receiver-operating-characteristic-curve [AUROC] = 0.979, area-under-the-precision-recall-curve [AUPRC] = 0.764; positive-predictive-value [PPV] = 0.614) versus logistic-regression model (AUROC = 0.885, AUPRC = 0.169; PPV = 0.210). The top 30 predictors included number of ED attendance, fasting plasma glucose, number and types of outpatient appointments, ED triage category of 'urgent', number of admissions and stay, age, residential districts, history of fall and medication use with an AUROC of 0.939 in a validation cohort of patients with diabetes. In an age- and sex-matched sub-cohort, compared to the widely-used Morse Fall Score, XGBoost model had higher sensitivity (0.569-versus-0.139) with optimal balance of identifying positive cases whilst simultaneously minimising false positives and false negative (F1 score: 0.626-versus-0.555). Conclusions Our ML-model highlights the utility of EHR in identifying high-risk individuals for falls, supporting integrating into the EHR system for targeted preventive actions.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: N
    holdings:
      @attributes:
        islocal: N