Clinical InvestigationCongestive Heart FailurePredicting the risk of unplanned readmission or death within 30 days of discharge after a heart failure hospitalization
Section snippets
Study setting
The province of Alberta has a single-payer, government-funded health care system that provides universal access to over 3.7 million people for hospital, emergency department (ED), and physician services. This study received ethics approval from the Health Ethics Research Board at the University of Alberta.
Data sources
This study used de-identified data from 4 administrative databases maintained by Alberta Health to create our study cohort including (1) the Discharge Abstract Database, which records the
Results
During our study, 59 652 adults in Alberta were discharged after being hospitalized with a diagnosis of HF listed as either the most responsible or a secondary diagnosis. Death or unplanned readmission occurred in about one fifth of patients in the first 30 days after discharge (Table I, Table II), with most of these events being readmissions (and 18.6% of the readmissions were for HF as most responsible diagnosis). Patients who were subsequently readmitted or had died within 30 days of
Discussion
This is the first study to examine the discriminative ability of the CMS-endorsed prediction models and the LACE/LaCE indices in a broad heart failure population and for the composite outcome of “death or unplanned readmission within 30 days of discharge.” Although LACE and LaCE demonstrated only moderate discrimination for predicting 30 day unplanned readmission or death, thereby limiting their use for patient-level prediction, both indices were significantly better able to predict the
Disclosures
Drs McAlister, Kaul, and Ezekowitz receive salary support from Alberta Innovates-Health Solutions and this project was funded by the Canadian Institutes of Health Research and Pfizer Canada through a peer-reviewed operating grant. The funding agencies did not have input into study design, data collection, interpretation of results, or write up/approval for submission.
Acknowledgements
This study is based in part on data provided by Alberta Health. The interpretation and conclusions contained herein are those of the researchers and do not necessarily represent the views of the Government of Alberta. Neither the Government of Alberta nor Alberta Health express any opinion in relation to this study.
References (28)
- et al.
Noncardiac comorbidity increases preventable hospitalizations and mortality among Medicare beneficiaries with chronic heart failure
J Am Coll Cardiol
(2003) - et al.
Prediction of hospital readmission for heart failure: development of a simple risk score based on administrative data
J Am Coll Cardiol
(1999) - et al.
Prediction of rehospitalization and death in severe heart failure by physicians and nurses of the ESCAPE trial
J Card Fail
(2007) - et al.
Risk stratification after hospitalization for decompensated heart failure
J Card Fail
(2004) - et al.
Correlates of early hospital readmission or death in patients with congestive heart failure
Am J Cardiol
(1997) - et al.
A new method of classifying prognostic comorbidity in longitudinal studies: Development and validation
J Chronic Dis
(1987) - et al.
Recent national trends in readmission rates after heart failure hospitalization
Circ Heart Fail
(2010) - et al.
An administrative claims measure suitable for profiling hospital performance on the basis of 30-day all-cause readmission rates among patients with heart failure
Circ Cardiovasc Qual Outcomes
(2008) - et al.
Rehospitalizations among patients in the Medicare fee-for-service program
N Engl J Med
(2009) - et al.
Statistical models and patient predictors of readmission for heart failure: a systematic review
Arch Intern Med
(2008)
Predicting mortality among patients hospitalized for heart failure: derivation and validation of a clinical model
JAMA
An automated model to identify heart failure patients at risk for 30-day readmission or death using electronic medical record data
Med Care
Incremental value of clinical data beyond claims data in predicting 30-day outcomes after heart failure hospitalization
Circ Cardiovasc Qual Outcomes
An administrative claims model suitable for profiling hospital performance based on 30-day mortality rates among patients with heart failure
Circulation
Cited by (137)
Predicting 30-Day Readmissions in Patients With Heart Failure Using Administrative Data: A Machine Learning Approach
2022, Journal of Cardiac FailureInterpretable prediction of 3-year all-cause mortality in patients with heart failure caused by coronary heart disease based on machine learning and SHAP
2021, Computers in Biology and MedicinePatient stratification for risk of readmission due to heart failure by using nationwide administrative data
2021, Journal of Cardiac FailurePredicting morbidity and mortality after radical cystectomy using risk calculators: A comprehensive review of the literature
2021, Urologic Oncology: Seminars and Original Investigations