Evaluating Tele-ICU Implementation Based on Observed and Predicted ICU Mortality: A Systematic Review and Meta-Analysis

Abstract

Objectives: Past studies have examined numerous components of tele-ICU care to decipher which elements increase patient and institutional benefit. These factors include review of the patient chart within 1 hour, frequent collaborative data reviews, mechanisms for rapid laboratory/alert review, and interdisciplinary rounds. Previous meta-analyses have found an overall ICU mortality benefit implementing tele-ICU, however, subgroup analyses found few differences. The purpose of this systematic review and meta-analysis was to explore the effect of tele-ICU implementation with regard to ICU mortality and explore subgroup differences via observed and predicted mortality.

Data sources: We searched PubMed, Cochrane Library, Embase, and European Society of Intensive Care Medicine for articles related to tele-ICU from inception to September 18, 2018.

Study selection: We included all trials meeting inclusion criteria which looked at the effect of tele-ICU implementation on ICU mortality.

Data extraction: We abstracted study characteristics, patient characteristics, severity of illness scores, and ICU mortality rates.

Data synthesis: We included 13 studies from 2,766 abstracts identified from our search strategy. The before-after tele-ICU implementation pooled odds ratio for overall ICU mortality was 0.75 (95% CI, 0.65-0.88; p < 0.001). In subgroup analysis, the pooled odds ratio for ICU mortality between the greater than 1 versus less than 1 observed to predicted mortality ratios was 0.64 (95% CI, 0.52-0.77; p < 0.001) and 0.98 (95% CI, 0.81-1.18; p = 0.81), respectively. Test for interaction was significant (p = 0.002).

Conclusions: After evaluating all included studies, tele-ICU implementation was associated with an overall reduction in ICU mortality. Subgroup analysis suggests that publications exhibiting observed to predicted ICU mortality ratios of greater than 1 before tele-ICU implementation was associated with a reduction in ICU mortality after tele-ICU implementation. No significant ICU mortality reduction was noted in the subgroup of observed to predicted ICU mortality ratio less than 1 before tele-ICU implementation. Future studies should confirm this finding using patient-level data.