Using an automated mortality prediction tool to focus advance care planning efforts for inpatients
About the Project
One important obstacle to improving end-of-life (EOL) care is the failure of clinicians to reliably identify those who are approaching the EOL. Our best predictive models have only modest accuracy, and they only work if clinicians have the time and inclination to use them, which is often not the case. There are promising interventions for improving the care delivered to patients nearing the EOL, but in these studies, the time-consuming tasks of identifying patients and initiating the intervention were performed by research staff who do not exist in the real-world clinical environment. An accurate and automated mortality prediction tool could enhance the real-world effectiveness of any palliative intervention, and facilitate research and quality improvement by reliably identifying people who might benefit and prompting staff to initiate interventions or address unmet palliative needs.
In previous work funded by CFN, we piloted a computerized application that uses a modified version of the Hospital One-Year Mortality Risk score (HOMR) to seamlessly identify inpatients at risk of one-year mortality using administrative data collected at the time of admission. For patients at elevated mortality risk, automated notices were sent to the admitting teams reminding them to assess and address unmet palliative needs. Final results are pending but interim results suggest that this tool is acceptable to stakeholders.
In the present project, we will evaluate the KT potential of the HOMR application in two ways. First, by incorporating the HOMR application instead of a manual, provider-dependent process for identifying eligible patients in two ongoing projects aimed at improving Advance Care Planning (ACP). Second, by assessing unmet palliative needs among patients identified by the HOMR application. We hypothesize that the HOMR tool will improve the efficiency of identifying patients who should be approached for discussions about goals of care, and result in a larger number of patients approached overall. We also hypothesize that patients identified by HOMR have a substantial burden of unmet palliative needs, supporting the idea that the HOMR tool could be used as a seamless prospective clinical surveillance “trigger” for other EOL interventions.
This project builds on previously funded CFN grant – CAT2015-16.
James Downar, MDCM, MHSc — University Health Network
John You — McMaster University
Daniel Kobewka — University of Ottawa
Alan Forster — University of Ottawa
Dev Jayaraman — McGill University
Jessica Simon — University of Calgary
Ayn Sinnarajah — University of Calgary
Peter Wu — University of Toronto
Shahin Ansari — University Health Network