EUVIMEDOpdag EUVIMED
ValidierungsstudieOpen access · CC BY-NC-ND 4.0

Development and Internal Validation of a Machine Learning Model for Predicting Long‐Term Opioid Therapy After Hip Fracture Surgery in Older, Opioid‐Naïve Adults

Yasmina Maria Tudorache iD, Simon Storgaard Jensen iD, Katie Jane Sheehan iD, Jan-Erik Gjertsen, Alma Becic Pedersen iD

European Journal of Pain · 2026

DOI: 10.1002/ejp.70280 ↗

At a glance

Validierungsstudie in European Journal of Pain, 2026. Written by Yasmina Maria Tudorache and 4 co-authors. Institution: Department of Clinical Epidemiology, Aarhus University, Aarhus, Denmark. Major MEDLINE topics: Analgesics, Opioid, Hip Fractures, Postoperative Pain, Machine Learning. Cited 1 times so far (Crossref); 44 references. The full text is freely available (open access, CC BY-NC-ND 4.0).

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Background

Long‐term opioid therapy (LTOT) after hip fracture surgery is a common postoperative complication associated with adverse outcomes, yet tools to identify at‐risk patients among opioid‐naïve older adults are lacking. This study aimed to develop and internally validate a parsimonious model to predict LTOT following hip fracture surgery.

Methods

Using Danish nationwide registries, we identified 26,057 opioid‐naïve patients (≥ 65 years) undergoing hip fracture surgery (2010–2020) and analysed 29 predictors, covering demographics, comorbidities, medication, lifestyle, socioeconomics and surgical factors. LTOT was defined as redeeming ≥ 2 prescriptions between 31 and 365 days of surgery. Models were developed using four machine learning methods: logistic regression, backwards elimination, elastic net penalised logistic regression and random forest. Model performance was assessed using area under the receiver operating characteristic curve (AUC), calibration slope, intercept, Brier score and decision curve analysis.

Results

LTOT was identified in 8095 (31.1%) patients. The backward elimination algorithm identified the best performing model, selecting 8 of 29 predictors and achieving an AUC of 0.68, calibration slope of 0.99, intercept of 0.02 and Brier score of 0.20. Predictors included age, marital status, preoperative non‐opioid pain medication, preoperative novel oral anticoagulants, fracture type, surgery delay, length of hospital stay and postoperative cumulated ambulation score at discharge.

Conclusions

A prediction model was developed and validated for use at discharge to identify patients at risk of LTOT 1 year after hip fracture. The model may support risk stratification at discharge, but requires external validation and evaluation of clinical implementation before routine use. Significance Statement This study presents the first internally validated prediction model for long‐term opioid use in opioid‐naïve older adults after hip fracture surgery. The model functions as a simple and interpretable risk stratification tool at discharge and has been incorporated in a freely available risk calculator. It addresses the lack of clinically applicable risk stratification tools in this frail population and highlights opportunities for more targeted postoperative pain management, although feasibility testing is required before clinical implementation.

Subjects

MeSH terms (MEDLINE)

Analgesics, OpioidHip FracturesPostoperative PainMachine LearningHumansFemaleAgedMalePredictive Learning ModelsAged, 80 and overDenmarkPrediction AlgorithmsRegistries

Author keywords

hip fracturelong‐term opioid usageopioid‐naïvepain managementprediction model

Substances

Analgesics, Opioid

Authors and institutions

  • Department of Clinical Epidemiology, Aarhus University, Aarhus, Denmark.
  • Department of Clinical Medicine, Aarhus University Hospital, Aarhus, Denmark.
  • Center of Bone and Joint Health, Blizard Institute, Queen Mary, University of London, London, UK.
  • Department of Orthopaedic Surgery, Haukeland University Hospital, Bergen, Norway.
  • Department of Clinical Medicine, University of Bergen, Bergen, Norway.

ORCID profiles: Yasmina Maria Tudorache, Simon Storgaard Jensen, Katie Jane Sheehan, Alma Becic Pedersen

Cite

APA

Tudorache, Y. M., Jensen, S. S., Sheehan, K. J., Gjertsen, J. E., & Pedersen, A. B. (2026). Development and Internal Validation of a Machine Learning Model for Predicting Long‐Term Opioid Therapy After Hip Fracture Surgery in Older, Opioid‐Naïve Adults. European Journal of Pain. https://doi.org/10.1002/ejp.70280

Vancouver

Tudorache YM, Jensen SS, Sheehan KJ, Gjertsen JE, Pedersen AB. Development and Internal Validation of a Machine Learning Model for Predicting Long‐Term Opioid Therapy After Hip Fracture Surgery in Older, Opioid‐Naïve Adults. European Journal of Pain. 2026. doi:10.1002/ejp.70280

BibTeX
@article{Tudorache2026,
  author = {Tudorache, Yasmina Maria and Jensen, Simon Storgaard and Sheehan, Katie Jane and Gjertsen, Jan-Erik and Pedersen, Alma Becic},
  title = {Development and Internal Validation of a Machine Learning Model for Predicting Long‐Term Opioid Therapy After Hip Fracture Surgery in Older, Opioid‐Naïve Adults},
  journal = {European Journal of Pain},
  year = {2026},
  doi = {10.1002/ejp.70280}
}
Start for free →