Key result
An improved random survival forest risk model predicted hospital mortality in heart failure patients with an out-of-bag C-statistic of 0.821, demonstrating superiority over conventional models.
Why the study?
Does an improved random survival forest model accurately predict hospital mortality in ICU patients with heart failure?
Population
8,059 patients with heart failure in Intensive care unit cohorts from the public MIMIC II clinical database
Comparison
Improved random survival forest risk model… vs Conventional random survival forest-based model…
Design
Cohort
Authors
Loading...
May enhance ICU HF risk stratification; leaves open external validation before practice adoption.
Observational (n=8,059)
Does an improved random survival forest model accurately predict hospital mortality in ICU patients with heart failure?
Effect estimate: C-statistic 0.821
An improved random survival forest model incorporating 32 risk factors provides high accuracy in predicting hospital mortality for ICU patients with heart failure.
Miao et al. (2018) conducted an observational in Heart failure (n=8,059). Improved random survival forest (iRSF) risk model vs. Conventional random survival forest-based model was evaluated on Heart failure mortality prediction (C-statistic 0.821). An improved random survival forest risk model predicted hospital mortality in heart failure patients with an out-of-bag C-statistic of 0.821, demonstrating superiority over conventional models.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: