Derivation of Data-Driven Triggers for Palliative Care Consultation in Critically Ill Patients
Purpose: To examine the ability of existing triggers for intensive care unit (ICU) palliative care consultation to predict 6-month mortality, and derive new triggers for consultation based on risk factors for 6-month mortality.
Materials and Methods: Retrospective cohort study of NY state residents who received intensive care, 2008-2013. We examined sensitivity and specificity of existing triggers for predicting 6-month mortality and used logistic regression to generate patient subgroups at high-risk for 6-month mortality as potential novel triggers for ICU palliative care consultation.
Results: Of 1,019,849 patients, 195,847 (19.2%) died within 6 months of admission. Existing triggers were specific but not sensitive for predicting 6-month mortality, (sensitivity 0.3%-11.1%, specificity 96.5-99.9% for individual triggers). Using logistic regression, patient subgroups with the highest predicted probability of 6-month mortality were older patients admitted with sepsis (age 70-79 probability 49.7%, [49.5-50.0]) or cancer (non-metastatic cancer, age 70-79 probability 51.5%, [51.1-51.9]; metastatic cancer, age 70-79 probability 60.3%, [59.9-60.6]). Sensitivity and specificity of novel triggers ranged from 0.05% to 9.2% and 98.6% to 99.9%, respectively.
Conclusions: Existing triggers for palliative care consultation are specific, but insensitive for 6-month mortality. Using a data-driven approach to derive novel triggers may identify subgroups of patients at high-risk of 6-month mortality.
- SPARCS triggers JCC R1 clean.docx application/vnd.openxmlformats-officedocument.wordprocessingml.document 329 KB Download File
Also Published In
- Journal of Critical Care
This is a pre-print of an article published in Journal of Critical Care, August 2018.