Perioperative medicine & outcomes
Machine Learning–Based Identification and Ranking of Mortality Predictors After Hip Fracture Surgery: An Analysis of the Australian and New Zealand Hip Fracture Registry
Authors' conclusion
Machine learning identified ASA grade, dementia, age, and mobility as the top predictors of mortality after hip fracture surgery.
Study context
- Population
- Patients undergoing hip fracture surgery, Australian and New Zealand Hip Fracture Registryover 11,000 analysed
- Outcome
- Mortality after hip fracture surgery; ranking of predictors by permutation-based feature importance
Methodological detailsRandom Survival Forest, permutation-based feature importance, Australian and New Zealand Hip Fracture Registry
- Random Survival Forest
- Permutation-based feature importance
- Australian and New Zealand Hip Fracture Registry
Performance
As reported in the abstract
Predictor importance for mortality (RSF permutation importance score)
- American Society of Anesthesiologists (ASA) grade
- 0.051
- Pre-existing dementia
- 0.036
- Age
- 0.019
- Preadmission walking ability
- 0.016
- Male sex (weaker association)
- 0.009
- Acute hospital stay (weaker association)
- 0.006
Further findings
Mortality during follow-up · median 630 days follow-up
- Patients who died
- 31%
Random Survival Forest (RSF) model performance
- Test C index
- 0.7305
Original publication
Machine Learning–Based Identification and Ranking of Mortality Predictors After Hip Fracture Surgery: An Analysis of the Australian and New Zealand Hip Fracture Registry. Anesth Analg. Published 30 June 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →