Key result
Predictive risk models for hospital readmissions yield C statistics between 0.55 and 0.80, outperforming staff physicians whose predictions achieved a C statistic of approximately 0.58.
Design
Editorial
Authors
Loading...
The editorial highlights that while predictive models can identify patients at high risk for readmission, healthcare systems should also consider whether the readmission is actually preventable.
The editorial highlights that while predictive models can identify patients at high risk for readmission, healthcare systems should also consider whether the readmission is actually preventable.
Steventon et al. (2017) conducted an editorial in Hospital readmissions. Predictive risk models vs. Clinical judgment was evaluated on C statistic for readmission prediction. Predictive risk models for hospital readmissions yield C statistics between 0.55 and 0.80, outperforming staff physicians whose predictions achieved a C statistic of approximately 0.58.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: