Zubin J Eapen1, Li Liang2, Gregg C Fonarow3, Paul A Heidenreich4, Lesley H Curtis2, Eric D Peterson2, Adrian F Hernandez2. 1. Duke Clinical Research Institute, Duke University Medical Center, Durham, North Carolina. Electronic address: zubin.eapen@duke.edu. 2. Duke Clinical Research Institute, Duke University Medical Center, Durham, North Carolina. 3. University of California Los Angeles, Los Angeles, California. 4. Palo Alto VA Medical Center, Palo Alto, California.
Abstract
OBJECTIVES: The study sought to derive and validate risk-prediction tools from a large nationwide registry linked with Medicare claims data. BACKGROUND: Few clinical models have been developed utilizing data elements readily available in electronic health records (EHRs) to facilitate "real-time" risk estimation. METHODS: Heart failure (HF) patients ≥ 65 years of age hospitalized in the GWTG-HF (Get With The Guidelines-Heart Failure) program were linked with Medicare claims from January 2005 to December 2009. Multivariable models were developed for 30-day mortality after admission, 30-day rehospitalization after discharge, and 30-day mortality/rehospitalization after discharge. Candidate variables were selected based on availability in EHRs and prognostic value. The models were validated in a 30% random sample and separately in patients with reduced and preserved ejection fraction (EF). RESULTS: Among 33,349 patients at 160 hospitals, 3,002 (9.1%) died within 30 days of admission, 7,020 (22.8%) were rehospitalized within 30 days of discharge, and 8,374 (27.2%) died or were rehospitalized within 30 days of discharge. Compared with patients classified as low risk, high-risk patients had significantly higher odds of death (odds ratio [OR]: 8.82, 95% confidence interval [CI]: 7.58 to 10.26), rehospitalization (OR: 1.99, 95% CI: 1.86 to 2.13), and death/rehospitalization (OR: 2.65, 95% CI: 2.44 to 2.89). The 30-day mortality model demonstrated good discrimination (c-index 0.75) while the rehospitalization and death/rehospitalization models demonstrated more modest discrimination (c-indices of 0.59 and 0.62), with similar performance in the validation cohort and for patients with preserved and reduced EF. CONCLUSIONS: These predictive models allow for risk stratification of 30-day outcomes for patients hospitalized with HF and may provide a validated, point-of-care tool for clinical decision making.
OBJECTIVES: The study sought to derive and validate risk-prediction tools from a large nationwide registry linked with Medicare claims data. BACKGROUND: Few clinical models have been developed utilizing data elements readily available in electronic health records (EHRs) to facilitate "real-time" risk estimation. METHODS:Heart failure (HF) patients ≥ 65 years of age hospitalized in the GWTG-HF (Get With The Guidelines-Heart Failure) program were linked with Medicare claims from January 2005 to December 2009. Multivariable models were developed for 30-day mortality after admission, 30-day rehospitalization after discharge, and 30-day mortality/rehospitalization after discharge. Candidate variables were selected based on availability in EHRs and prognostic value. The models were validated in a 30% random sample and separately in patients with reduced and preserved ejection fraction (EF). RESULTS: Among 33,349 patients at 160 hospitals, 3,002 (9.1%) died within 30 days of admission, 7,020 (22.8%) were rehospitalized within 30 days of discharge, and 8,374 (27.2%) died or were rehospitalized within 30 days of discharge. Compared with patients classified as low risk, high-risk patients had significantly higher odds of death (odds ratio [OR]: 8.82, 95% confidence interval [CI]: 7.58 to 10.26), rehospitalization (OR: 1.99, 95% CI: 1.86 to 2.13), and death/rehospitalization (OR: 2.65, 95% CI: 2.44 to 2.89). The 30-day mortality model demonstrated good discrimination (c-index 0.75) while the rehospitalization and death/rehospitalization models demonstrated more modest discrimination (c-indices of 0.59 and 0.62), with similar performance in the validation cohort and for patients with preserved and reduced EF. CONCLUSIONS: These predictive models allow for risk stratification of 30-day outcomes for patients hospitalized with HF and may provide a validated, point-of-care tool for clinical decision making.
Authors: Scott L Hummel; Prashanth Katrapati; Brenda W Gillespie; Anthony C Defranco; Todd M Koelling Journal: Mayo Clin Proc Date: 2014-03-29 Impact factor: 7.616
Authors: Pamela N Peterson; Larry A Allen; Paul A Heidenreich; Nancy M Albert; Ileana L Piña Journal: Circ Heart Fail Date: 2018-10 Impact factor: 8.790
Authors: Benjamin A Goldstein; Michael J Pencina; Maria E Montez-Rath; Wolfgang C Winkelmayer Journal: J Am Med Inform Assoc Date: 2016-06-29 Impact factor: 4.497
Authors: Benjamin A Goldstein; Ann Marie Navar; Michael J Pencina; John P A Ioannidis Journal: J Am Med Inform Assoc Date: 2016-05-17 Impact factor: 4.497
Authors: Kristin E Bergethon; Christine Ju; Adam D DeVore; N Chantelle Hardy; Gregg C Fonarow; Clyde W Yancy; Paul A Heidenreich; Deepak L Bhatt; Eric D Peterson; Adrian F Hernandez Journal: Circ Heart Fail Date: 2016-06 Impact factor: 8.790
Authors: Jonathan D Davis; Margaret A Olsen; Kerry Bommarito; Shane J LaRue; Mohammed Saeed; Michael W Rich; Justin M Vader Journal: Am J Med Date: 2016-08-31 Impact factor: 4.965
Authors: Frances M Russell; Robert R Ehrman; Robinson Ferre; Luna Gargani; Vicki Noble; Jordan Rupp; Sean P Collins; Benton Hunter; Kathleen A Lane; Phillip Levy; Xiaochun Li; Christopher O'Connor; Peter S Pang Journal: Heart Lung Date: 2018-11-15 Impact factor: 2.210