Hospitalised adults whose condition deteriorates while they are on hospital wards have considerable morbidity and mortality. Early identification of patients at risk of clinical deterioration has traditionally relied on manually calculated scores, and outcomes after an automated detection of clinical deterioration have not been widely reported.
The authors of this article published in The New England Journal of Medicine developed an intervention program involving remote monitoring by nurses who reviewed records of patients who had been identified as being at high risk. Results of this monitoring were then communicated to rapid-response teams at hospitals. They compared outcomes among hospitalised patients whose condition reached the alert threshold at hospitals where the system was operational, with outcomes among patients at hospitals where the system had not yet been implemented.
The authors found that using an automated predictive model to identify high-risk patients, for whom interventions could then be implemented by rapid-response teams, was associated with decreased mortality.