Je. Zimmerman et al., IMPROVING INTENSIVE-CARE UNIT DISCHARGE DECISIONS - SUPPLEMENTING PHYSICIAN JUDGMENT WITH PREDICTIONS OF NEXT DAY RISK FOR LIFE-SUPPORT, Critical care medicine, 22(9), 1994, pp. 1373-1384
Objective: To develop predictive equations, estimating the probability
that an individual intensive care unit (ICU) patient will receive lif
e support within the next 24 hrs. Design: Prospective, multicenter, in
ception cohort study. Setting: Forty-two ICUs in 40 U.S. hospitals, in
cluding 26 that were randomly selected and 14 volunteer hospitals, pri
marily university or large tertiary care centers. Patients: A consecut
ive sample of 17,440 ICU admissions. Interventions: None. Measurements
and Main Results: A series of multivariate equations were developed t
o create daily estimates of probability of life support in the next 24
hrs. These equations used demographic, physiologic, and treatment inf
ormation obtained at the time of ICU admission and during the first 7
ICU days. The most important determinants of next day risk for life su
pport were the current day's therapy and Acute Physiology Score of the
Acute Physiology and Chronic Health Evaluation (APACHE) III score. Ot
her predictor variables included diagnosis, age, chronic health status
, emergency surgery, previous day Acute Physiology Score, and hospital
stay and location before ICU admission. The cross-validated ICU day 1
, 2, and 3 predictive equations had receiver operating characteristic
areas of 0.90. Survival, ICU readmission rate, and the number and type
of therapies received by patients predicted at <10% risk. for active
treatment suggest that discharge of patients meeting these criteria to
an intermediate care unit or hospital ward could reduce ICU bed deman
d without compromising patient safety. Conclusions: Accurate, objectiv
e predictions of next day risk for life support can be developed, usin
g readily available patient information. Supplementing physician judgm
ent with these objective risk assessments deserves evaluation for the
role of these assessments in enhancing patient safety and improving IC
U resource utilization.