Development and Internal Validation of an Electronic Medical Record-Based Machine Learning Model for Frailty Prediction in Hospitalized Patients: Retrospective Cohort Study.
4 affiliations
- 1SA Health, Commission on Excellence and Innovation in Health, Adelaide, South Australia, Australia.
- 2Central Adelaide Local Health Network, Royal Adelaide Hospital, 1 Port Road, Adelaide, South Australia, 5000, Australia, 61 0432831520.
- 3School of Public Health, Adelaide University, Adelaide, South Australia, Australia.
- 4Adelaide EpiCentre, Central Adelaide Local Health Network, Adelaide, South Australia, Australia.
Abstract
Background
Frailty is prevalent among hospitalized patients and is associated with increased risk of complications, prolonged hospitalization, higher mortality, and health care costs. Existing frailty screening tools, including the Clinical Frailty Scale (CFS) and Hospital Frailty Risk Score (HFRS), have limitations related to subjectivity, resource intensity, or reliance on retrospective data, limiting their use in routine acute care. Early identification of frailty is critical to support targeted interventions and resource allocation, yet scalable approaches for predicting frailty early during hospital admission remain limited.Objective
This paper evaluates whether routinely collected electronic medical record (EMR) data available within the first 72 hours of admission can be used to predict frailty in hospitalized patients.Methods
A retrospective cohort study was conducted using routinely collected EMR data from the Royal Adelaide Hospital (RAH), including overnight admissions with a length of stay of at least 72 hours between July 2023 and December 2024. Frailty was defined using the HFRS (score >4). Predictors were derived from EMR data available within 72 hours of admission, including demographics, medications, laboratory results, nursing assessments, and medical and allied health consult orders. Data were split into training (21,436/26,824, 80%) and test (5388/26,824, 20%) sets. Multiple machine learning models were trained, with the F₂-score as the primary optimization metric. Model performance was evaluated using the F₂-score, recall, area under the receiver operating characteristic curve (AUROC), calibration, and clinical utility analyses.Results
This study included 26,824 admissions, of whom 9427 (35%) were classified as frail. The final XGBoost (XGB) model achieved an F₂-score of 0.755 (95% CI 0.741-0.768), an AUROC of 0.777 (95% CI 0.764-0.790), and a recall of 0.873 (95% CI 0.857-0.887) on the test dataset, with good calibration and an expected-to-observed ratio close to 1 (0.996, 95% CI 0.963-1.028). Key predictors included polypharmacy, laboratory results (including creatinine, albumin, and sodium), allied health consult orders, and nursing assessment data. Model performance was lower at 24 hours postadmission and improved by discharge.Conclusions
An EMR-based frailty prediction model using data available at 72 hours postadmission can identify patients with frailty early in their hospital stay, supporting targeted interventions and operational planning. Reduced performance in Indigenous patients highlights the need for culturally validated frailty indices and ongoing evaluation of equity in predictive modeling.
Related
- Machine Learning–Based Prediction of Major Postoperative Complications After Noncardiac Surgery Under General Anesthesia Using Routinely Available Electronic Health Record Data: Retrospective Multicenter Development and Validation Study
- Development and internal validation of an exploratory clinical prediction model for MRI-defined white matter injury in moderate-to-late preterm infants: a single-center retrospective study
- Development and Internal Validation of a Preintubation Prediction Model for Postintubation Hypotension in Trauma Patients Undergoing Emergency Endotracheal Intubation: A Retrospective Cohort Study
- Development and validation of a clinical prediction model for diagnosing nephrotic syndrome in adults: a retrospective diagnostic prediction study
- Prediction of incident inflammatory bowel disease from routine electronic health records: development and external validation of a longitudinal machine learning model
BibTeX
@article{szabo2026development,
title = {{Development and Internal Validation of an Electronic Medical Record-Based Machine Learning Model for Frailty Prediction in Hospitalized Patients: Retrospective Cohort Study.}},
author = {Georgina Christine Laurea Szabo and Madison Bills and Matthew Williams and Annie Conway and Leesa Van Bochove and Gerry O'Callaghan},
journal = {JMIR medical informatics},
year = {2026},
month = oct,
doi = {10.2196/95478},
url = {https://europepmc.org/article/MED/42950281},
note = {CC BY},
}
RIS
TY - JOUR
TI - Development and Internal Validation of an Electronic Medical Record-Based Machine Learning Model for Frailty Prediction in Hospitalized Patients: Retrospective Cohort Study.
AU - Georgina Christine Laurea Szabo
AU - Madison Bills
AU - Matthew Williams
AU - Annie Conway
AU - Leesa Van Bochove
AU - Gerry O'Callaghan
PY - 2026
DA - 2026/10/01
JO - JMIR medical informatics
DO - 10.2196/95478
UR - https://europepmc.org/article/MED/42950281
AB - Background Frailty is prevalent among hospitalized patients and is associated with increased risk of complications, prolonged hospitalization, higher mortality, and health care costs. Existing frailty screening tools, including the Clinical Frailty Scale (CFS) and Hospital Frailty Risk Score (HFRS), have limitations related to subjectivity, resource intensity, or reliance on retrospective data, limiting their use in routine acute care. Early identification of frailty is critical to support targeted interventions and resource allocation, yet scalable approaches for predicting frailty early during hospital admission remain limited.Objective This paper evaluates whether routinely collected electronic medical record (EMR) data available within the first 72 hours of admission can be used to predict frailty in hospitalized patients.Methods A retrospective cohort study was conducted using routinely collected EMR data from the Royal Adelaide Hospital (RAH), including overnight admissions with a length of stay of at least 72 hours between July 2023 and December 2024. Frailty was defined using the HFRS (score >4). Predictors were derived from EMR data available within 72 hours of admission, including demographics, medications, laboratory results, nursing assessments, and medical and allied health consult orders. Data were split into training (21,436/26,824, 80%) and test (5388/26,824, 20%) sets. Multiple machine learning models were trained, with the F₂-score as the primary optimization metric. Model performance was evaluated using the F₂-score, recall, area under the receiver operating characteristic curve (AUROC), calibration, and clinical utility analyses.Results This study included 26,824 admissions, of whom 9427 (35%) were classified as frail. The final XGBoost (XGB) model achieved an F₂-score of 0.755 (95% CI 0.741-0.768), an AUROC of 0.777 (95% CI 0.764-0.790), and a recall of 0.873 (95% CI 0.857-0.887) on the test dataset, with good calibration and an expected-to-observed ratio close to 1 (0.996, 95% CI 0.963-1.028). Key predictors included polypharmacy, laboratory results (including creatinine, albumin, and sodium), allied health consult orders, and nursing assessment data. Model performance was lower at 24 hours postadmission and improved by discharge.Conclusions An EMR-based frailty prediction model using data available at 72 hours postadmission can identify patients with frailty early in their hospital stay, supporting targeted interventions and operational planning. Reduced performance in Indigenous patients highlights the need for culturally validated frailty indices and ongoing evaluation of equity in predictive modeling.
SN - 2291-9694
ER -