Key result
A risk prediction model using routinely collected electronic medical record data demonstrated modest accuracy in predicting 5-year mortality or heart failure hospitalization, achieving a maximum C-statistic of 0.71.
Population
n=4,696 patients with a heart failure diagnosis who had an echocardiogram from 1999 to 2004 at a large…
Design
Cohort
Follow-up
5 years
Authors
Loading...
Supports EHR-based HF risk stratification; leaves open need for prospective validation before practice adoption.
Cohort (n=4,696)
No
A simple risk-prediction model using routine electronic health record data can stratify heart failure patients by their absolute risk of poor outcomes to help prioritize disease management efforts, despite modest predictive accuracy.
Smith et al. (2011) conducted a cohort in Heart failure (n=4,696). Risk prediction models was evaluated on Composite of all-cause mortality or hospitalization with a primary discharge diagnosis of heart failure (95% CI 54% to 58%). A risk prediction model using routinely collected electronic medical record data demonstrated modest accuracy in predicting 5-year mortality or heart failure hospitalization, achieving a maximum C-statistic of 0.71.
Synapse has enriched 3 closely related papers on similar clinical questions. Consider them for comparative context: