In Journal of the American Medical Directors Association
OBJECTIVE : A web-based application was developed for medical staff to easily access and use a comprehensive delirium prevention management program-comprising risk prediction, assessment, and intervention-even in long-term care facilities with insufficient systems.
DESIGN : A randomized control trial.
SETTING AND PARTICIPANTS : A long-term care facility with 250 beds in Korea. Participants were 130 facility residents aged 18 or older who understood the purpose of this study and for whom a legal representative provided participation consent. Participants were randomly assigned to the intervention and control groups (n = 65 per group).
METHODS : The participants' risk of delirium episodes was predicted using the web-based application Web_DeliPREVENT_4LCF. Delirium was assessed using the built-in Short Confusion Assessment Method (S-CAM). Among the intervention group, nonpharmacological, multicomponent delirium prevention interventions guided by the application were applied to participants who were predicted to be at risk for delirium or tested positive for delirium. The intervention was provided for 30 days.
RESULTS : The intervention group had a 0.30 times lower incidence of delirium (95% confidence interval [CI] 0.12-0.79; P = .015) and 0.08 times lower 1-month hospitalization mortality (95% CI 0.01-0.79; P = .031) than the control group. There were no differences between the 2 groups in delirium severity, mortality, and 3-month hospitalization mortality, long-term care facility discharge, and length of stay.
CONCLUSIONS AND IMPLICATIONS : The Web_DeliPREVENT_4LCF was effective in reducing delirium episodes and 1-month in-hospital mortality. Therefore, even in Korean long-term care facilities, which lack manpower and electronic medical record systems compared with general hospitals, the health care professional can easily access and use them for early detection and preventive intervention for residents' delirium.
REGISTRATION : KCT0005804.
Park Mina, Moon Kyoung Ja
2023-Feb-01
Delirium, long-term care, machine learning, predictive model, prevention
