Derivation and Validation of an In‐Hospital Mortality Prediction Model Suitable for Profiling Hospital Performance in Heart Failure

Abstract

BackgroundComparing heart failure (HF) outcomes across hospitals requires adequate risk adjustment. We aimed to develop and validate a model that can be used to compare quality of HF care across hospitals.Methods and ResultsWe included patients with HF aged ≥18 years admitted to one of 433 hospitals that participated in the Premier Inc Data Warehouse. This model (Premier) contained patient demographics, comorbidities, and acute conditions present on admission, derived from administrative and billing records. In a separate data set derived from electronic health records, we validated the Premier model by comparing hospital risk‐standardized mortality rates calculated with the Premier model to those calculated with a validated clinical model containing laboratory data (LAPS [Laboratory‐Based Acute Physiology Score]). Among the 200 832 admissions in the Premier Inc Data Warehouse, inpatient mortality was 4.0%. The model showed acceptable discrimination in the warehouse data (C statistic 0.75; 95% confidence interval, 0.74–0.76). In the validation data set, both the Premier model and the LAPS models showed acceptable discrimination (C statistic: Premier: 0.76 [95% confidence interval, 0.74–0.77]; LAPS: 0.78 [95% confidence interval, 0.76–0.80]). Risk‐standardized mortality rates for both models ranged from 2% to 7%. A linear regression equation describing the association between Premier‐ and LAPS‐specific mortality rates revealed a regression line with a slope of 0.71 (SE: 0.07). The correlation coefficient of the standardized mortality rates from the 2 models was 0.82.ConclusionsCompared with a validated model derived from clinical data, an HF mortality model derived from administrative data showed highly correlated risk‐standardized mortality rate estimates, suggesting it could be used to identify high‐ and low‐performing hospitals for HF care.

In‐hospital care in acute heart failure during the COVID‐19 pandemic: insights from the German‐wide Helios hospital network

“…9 In-hospital mortality rates in previously published studies investigating non-electively hospitalized HF populations range from 4.0-8.0% with a decrease during the last years. 24,[36][37][38][39][40] When comparing the baseline characteristics, our cohort showed a remarkably high prevalence of comorbidities such as diabetes mellitus and chronic kidney disease, which explains the relatively high event rate. 38,40 In line with our findings, higher age and NYHA class were found as predictors of fatal outcome.…”

“…24,[36][37][38][39][40] When comparing the baseline characteristics, our cohort showed a remarkably high prevalence of comorbidities such as diabetes mellitus and chronic kidney disease, which explains the relatively high event rate. 38,40 In line with our findings, higher age and NYHA class were found as predictors of fatal outcome. 24, 39 Akintoye and colleagues also reported a significant association of CCI with in-hospital mortality, but there has been no distinction between elective and non-elective hospital admission in their study.…”

Validation and Comparison of Seven Mortality Prediction Models for Hospitalized Patients With Acute Decompensated Heart Failure

“…Using administrative billing data, we previously developed a model 16,17 that is similar to the heart failure model developed by Krumholz et al for the Centers for Medicare and Medicaid Services (CMS). 18 We developed this model using data from the cost-accounting systems of 433 hospitals that participated in the Premier, Inc. Data Warehouse (PDW, a voluntary, fee-supported database) between January 1, 2009, and June 30, 2011.…”

Expected and observed in‐hospital mortality in heart failure patients before and during the COVID‐19 pandemic: Introduction of the machine learning‐based standardized mortality ratio at Helios hospitals

“…There were only two comparable prediction models focusing on administrative data only, which reported lower AUC values (0.72-0.78). 22,23 A direct juxtaposition with our model is, however, hindered due to a different set of included variables. Our data set does not contain information on ethnicity, insurance data, used medication, and other variables being implemented into the mentioned models.…”