Validation and comparison of seven mortality prediction models for hospitalized patients with acute decompensated heart failure

Background - Heart failure (HF) inpatient mortality prediction models can help clinicians make treatment decisions and researchers conduct observational studies; however, published models have not been validated in external populations. Methods and Results - We compared the performance of 7 models that predict inpatient mortality in patients hospitalized with acute decompensated heart failure: 4 HF-specific mortality prediction models developed from 3 clinical databases (ADHERE [Acute Decompensated Heart Failure National Registry], EFFECT study [Enhanced Feedback for Effective Cardiac Treatment], and GWTG-HF registry [Get With the Guidelines-Heart Failure]); 2 administrative HF mortality prediction models (Premier, Premier+); and a model that uses clinical data but is not specific for HF (Laboratory-Based Acute Physiology Score [LAPS2]). Using a multihospital, electronic health record-derived data set (HealthFacts [Cerner Corp], 2010-2012), we identified patients ≥18 years admitted with HF. Of 13 163 eligible patients, median age was 74 years; half were women; and 27% were black. In-hospital mortality was 4.3%. Model-predicted mortality ranges varied: Premier+ (0.8%-23.1%), LAPS2 (0.7%-19.0%), ADHERE (1.2%-17.4%), EFFECT (1.0%-12.8%), GWTG-Eapen (1.2%-13.8%), and GWTG-Peterson (1.1%-12.8%). The LAPS2 and Premier models outperformed the clinical models (C statistics: LAPS2 0.80 [95% confidence interval 0.78-0.82], Premier models 0.81 [95% confidence interval 0.79-0.83] and 0.76 [95% confidence interval 0.74-0.78], and clinical models 0.68 to 0.70). Conclusions - Four clinically derived, inpatient, HF mortality models exhibited similar performance, with C statistics near 0.70. Three other models, 1 developed in electronic health record data and 2 developed in administrative data, also were predictive, with C statistics from 0.76 to 0.80. Because every model performed acceptably, the decision to use a given model should depend on practical concerns and intended use.