Performance of electronic medical record tool in predicting 6-month mortality in hospitalized patients with cancer

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.