Do Predictive Models Integrated at Point of Care Improve Risk Stratification for Older HF Patients?

Integration of risk-prediction models at the point of care may allow "efficient, appropriate risk stratification and may also be used to inform older heart failure patients and families at risk for early morbidity or mortality," according to a new study published in JACC: Heart Failure.

Additional Resources
The study linked data from 33,349 heart failure patients ≥65 years of age at 160 hospitals in the GWTG-HF (Get With The Guidelines-Heart Failure) program to Medicare claims from January 2005 to December 2009. Study investigators developed multivariable models for 30-day mortality after admission, 30-day rehospitalization after discharge, and 30-day mortality/rehospitalization after discharge. From there, candidate variables were selected based on availability in EHRs and prognostic value and the models were validated in a 30 percent random sample and separately in patients with reduced and preserved ejection fraction (EF).

Overall results found that of the more than 33,000 patients, nearly 1 in 10 died within 30 days of admission and nearly 1 in 4 were readmitted within 30 days after discharge. Compared with patients classified as low risk, high-risk patients had significantly higher odds of death, rehospitalization, and death/rehospitalization. The results also found a history of prior hospitalizations within six months of an admission had similar discriminatory power compared with existing 30-day rehospitalization models. "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," the investigators said.

In general, the investigators point out, that the study findings not only reinforce previous studies showing poor outcomes for both mortality and rehospitalization in Medicare beneficiaries, they also demonstrate that prediction models with fair discriminative capacity can be developed from clinical data obtained as part of routine clinical care during an index hospitalization for heart failure. "In contrast to administrative claims, which are typically coded post-discharge, this study provides the key clinical variables that can identify patients at risk for short-term adverse outcomes before they are discharged," the investigators note.

To date, few clinical models have been developed utilizing data elements readily available in electronic health records (EHRs) to facilitate "real-time" risk estimation. Based on these new findings, the study investigators suggest that 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. They note that further studies are needed to test the effectiveness of implementing these models within EHRs to inform clinical decision making.


Keywords: Electronic Health Records, Decision Making, Heart Failure, Medicare, Patient Discharge, Hospitalization, United States


< Back to Listings