THURSDAY, Nov. 12, 2020 (HealthDay News) — The use of automated detection of impending in-hospital clinical deterioration for which interventions could be implemented is associated with reduced mortality, according to a study published in the Nov. 12 issue of the New England Journal of Medicine.
Gabriel J. Escobar, M.D., from the Kaiser Permanente Medical Center in Santa Clara, California, and colleagues developed an intervention program involving remote monitoring by nurses who reviewed records of hospitalized patients identified as being at high risk for clinical deterioration; results from monitoring were communicated to rapid-response teams at hospitals. Outcomes were compared for hospitalized patients whose condition reached the alert threshold at hospitals where the system was operational versus those where the system had not yet been deployed.
A total of 43,949 hospitalizations (for 35,669 patients) involved a patient whose condition reached the alert threshold; 15,487 hospitalizations were included in the intervention cohort and 28,462 were included in the comparison cohort. The researchers found that versus the comparison cohort, mortality within 30 days after an alert was lower in the intervention cohort (adjusted relative risk, 0.84).
“We found that in conjunction with careful implementation, the use of automated predictive models was associated with lower hospital mortality, a lower incidence of intensive care unit admission, and a shorter length of stay in the hospital,” the authors write.