A prediction model of elderly hip fracture mortality including preoperative red cell distribution width constructed based on the random survival forest (RSF) and Cox risk ratio regression
Authors' conclusion
An independent correlation between pre-RDW and 1-year mortality after surgery in elderly hip fracture can be used to predict mortality in elderly hip fracture patients and has predictive significance in anemia patients.
Study context
- Population
- Elderly patients who underwent hip fracture surgery
- Participants
- 2,106 patients
- Exposure
- Non-anemia vs Anemia
- Outcome
- Mortality within 1 year after hip fracture surgery
- Follow-up
- 1 year
Methodological detailsprediction model, random survival forest, Cox regression, internal and external validation, nomogram
- Prediction model
- Random survival forest
- Cox regression
- Internal and external validation
- Nomogram
Main finding
As reported in the abstract
Independent risk factors for 1-year mortality
RSF selected important influencing factors
12
Independent risk factors for death within 1 year on Cox regression, including preoperative RDW (pre-RDW)
8
Observational data: associations, not effects.
Further findings
Pre-RDW and 1-year mortality by anemia status (stratified analysis)
- Pre-RDW still independently associated with 1-year mortality in the non-anemia group, not in the anemia group
- Model from total cohort validated in anemia patients with good clinical benefits
Original publication
A prediction model of elderly hip fracture mortality including preoperative red cell distribution width constructed based on the random survival forest (RSF) and Cox risk ratio regression. Osteoporos Int. Published 7 December 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →