Performance of electronic medical record tool in predicting 6-month mortality in hospitalized patients with cancer
- PMID: 39961789
- PMCID: PMC12318460
- DOI: 10.1002/jhm.70012
Performance of electronic medical record tool in predicting 6-month mortality in hospitalized patients with cancer
Abstract
Background: A systematic tool to identify hospitalized patients with high mortality risk may be beneficial for targeting palliative care to those in greatest need.
Objective: Evaluate the performance of the End-of-life Index (EOLI; Epic Systems Corporation) in identifying patients at the highest 6-month mortality risk among hospitalized patients with cancer.
Methods: We conducted a retrospective study of adults with cancer admitted to oncology services in a 959-bed hospital between July 1 and December 31, 2023. We evaluated EOLI score performance in determining mortality risk using the area under the receiver operating characteristic curve (AUC). The primary outcome was 6-month mortality for patients with an EOLI score above and below the optimal threshold value. Secondary outcomes included in-hospital mortality, 30-day mortality, length of stay, intensive care unit (ICU) utilization, palliative care consultation, do-not-resuscitate status on discharge, and discharge disposition.
Results: The EOLI score had moderate accuracy in identifying patients at higher risk of 6-month mortality (AUC: 0.71) with an optimal threshold value of 40. For patients with EOLI > 40 and < 40, the 6-month mortality was 45.9% and 16.3%, respectively (p < .001). Patients with EOLI > 40 had higher ICU utilization (12.4% vs. 6.5%, p = .002) and were more likely to be discharged to a location other than home (13.5% vs. 5.3%; p < .001).
Conclusions: For hospitalized patients with cancer, the EOLI shows moderate accuracy in identifying patients with a high risk of 6-month mortality. As a screening tool, the EOLI can be used to identify patients who may benefit from timely palliative care.
© 2025 The Author(s). Journal of Hospital Medicine published by Wiley Periodicals LLC on behalf of Society of Hospital Medicine.
Conflict of interest statement
The authors declare no conflict of interest.
Figures


Similar articles
-
Comparison of Two Modern Survival Prediction Tools, SORG-MLA and METSSS, in Patients With Symptomatic Long-bone Metastases Who Underwent Local Treatment With Surgery Followed by Radiotherapy and With Radiotherapy Alone.Clin Orthop Relat Res. 2024 Dec 1;482(12):2193-2208. doi: 10.1097/CORR.0000000000003185. Epub 2024 Jul 23. Clin Orthop Relat Res. 2024. PMID: 39051924
-
[Volume and health outcomes: evidence from systematic reviews and from evaluation of Italian hospital data].Epidemiol Prev. 2013 Mar-Jun;37(2-3 Suppl 2):1-100. Epidemiol Prev. 2013. PMID: 23851286 Italian.
-
Falls prevention interventions for community-dwelling older adults: systematic review and meta-analysis of benefits, harms, and patient values and preferences.Syst Rev. 2024 Nov 26;13(1):289. doi: 10.1186/s13643-024-02681-3. Syst Rev. 2024. PMID: 39593159 Free PMC article.
-
The Real-World Effect of Early Screening for Palliative Care Criteria in a Medical Intensive Care Unit: An Instrumental Variable Analysis.Ann Am Thorac Soc. 2025 Feb;22(2):247-254. doi: 10.1513/AnnalsATS.202407-702OC. Ann Am Thorac Soc. 2025. PMID: 39441096
-
Glutamine supplementation for critically ill adults.Cochrane Database Syst Rev. 2014 Sep 9;2014(9):CD010050. doi: 10.1002/14651858.CD010050.pub2. Cochrane Database Syst Rev. 2014. PMID: 25199493 Free PMC article.
References
-
- Chow E, Harth T, Hruby G, Finkelstein J, Wu J, Danjoux C. How accurate are physicians’ clinical predictions of survival and the available prognostic tools in estimating survival times in terminally ill cancer patients? A systematic review. Clin Oncol. 2001;13:209‐218. - PubMed
MeSH terms
LinkOut - more resources
Full Text Sources
Medical
Research Materials