Tara Lagu1, Penelope S Pekow2, Meng-Shiou Shieh2, Mihaela Stefan2, Quinn R Pack2, Mohammad Amin Kashef2, Auras R Atreya2, Gregory Valania2, Mara T Slawsky2, Peter K Lindenauer2. 1. From the Center for Quality of Care Research (T.L., P.S.P., M.-S.S., M.S., Q.R.P., G.V., M.T.S., P.K.L.), Division of Hospital Medicine, Department of Medicine (T.L., M.S., P.K.L.), and Division of Cardiology (Q.R.P., M.A.K., A.R.A., G.V., M.T.S.), Baystate Medical Center, Springfield, MA; Department of Medicine, Tufts University School of Medicine, Boston, MA (T.L., M.S., Q.R.P., M.A.K., A.R.A., G.V., M.T.S., P.K.L.); and School of Public Health and Health Sciences, University of Massachusetts-Amherst (P.S.P.). lagutc@gmail.com. 2. From the Center for Quality of Care Research (T.L., P.S.P., M.-S.S., M.S., Q.R.P., G.V., M.T.S., P.K.L.), Division of Hospital Medicine, Department of Medicine (T.L., M.S., P.K.L.), and Division of Cardiology (Q.R.P., M.A.K., A.R.A., G.V., M.T.S.), Baystate Medical Center, Springfield, MA; Department of Medicine, Tufts University School of Medicine, Boston, MA (T.L., M.S., Q.R.P., M.A.K., A.R.A., G.V., M.T.S., P.K.L.); and School of Public Health and Health Sciences, University of Massachusetts-Amherst (P.S.P.).
Abstract
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.
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.
Authors: Christopher W Seymour; Vincent X Liu; Theodore J Iwashyna; Frank M Brunkhorst; Thomas D Rea; André Scherag; Gordon Rubenfeld; Jeremy M Kahn; Manu Shankar-Hari; Mervyn Singer; Clifford S Deutschman; Gabriel J Escobar; Derek C Angus Journal: JAMA Date: 2016-02-23 Impact factor: 56.272
Authors: Gabriel J Escobar; John D Greene; Peter Scheirer; Marla N Gardner; David Draper; Patricia Kipnis Journal: Med Care Date: 2008-03 Impact factor: 2.983
Authors: Wayne C Levy; Dariush Mozaffarian; David T Linker; Santosh C Sutradhar; Stefan D Anker; Anne B Cropp; Inder Anand; Aldo Maggioni; Paul Burton; Mark D Sullivan; Bertram Pitt; Philip A Poole-Wilson; Douglas L Mann; Milton Packer Journal: Circulation Date: 2006-03-13 Impact factor: 29.690
Authors: Mikhail Kosiborod; Silvio E Inzucchi; Harlan M Krumholz; Frederick A Masoudi; Abhinav Goyal; Lan Xiao; Philip G Jones; Suzanne Fiske; John A Spertus Journal: Arch Intern Med Date: 2009-03-09
Authors: Chanu Rhee; Zilu Zhang; Sameer S Kadri; David J Murphy; Greg S Martin; Elizabeth Overton; Christopher W Seymour; Derek C Angus; Raymund Dantes; Lauren Epstein; David Fram; Richard Schaaf; Rui Wang; Michael Klompas Journal: Crit Care Med Date: 2019-03 Impact factor: 7.598
Authors: Kevin F O'Sullivan; Mohammad Amin Kashef; Alexander B Knee; Alexander S Roseman; Penelope S Pekow; Mihaela S Stefan; Meng-Shiou Shieh; Quinn R Pack; Peter K Lindenauer; Tara Lagu Journal: J Hosp Med Date: 2019-07-24 Impact factor: 2.960
Authors: Vishal N Rao; Michelle D Kelsey; Anita M Kelsey; Stuart D Russell; Robert J Mentz; Manesh R Patel; Marat Fudim Journal: Clin Cardiol Date: 2021-03-07 Impact factor: 2.882
Authors: Deepshikha Charan Ashana; George L Anesi; Vincent X Liu; Gabriel J Escobar; Christopher Chesley; Nwamaka D Eneanya; Gary E Weissman; William Dwight Miller; Michael O Harhay; Scott D Halpern Journal: Am J Respir Crit Care Med Date: 2021-07-15 Impact factor: 30.528