Description

Martin et al reported a model for predicting readmission of a surgical ICU patient. This can help to identify a patient who may benefit from more aggressive management. The authors are from University of Utah.


Patient selection: surgical ICU patient being discharged from the ICU

 

Parameters:

(1) respiratory rate in breaths per minute

(2) serum BUN in mg/dL

(3) age in years

(4) serum glucose in mg/dL

(5) serum chloride in mmol/L

(6) history of atrial fibrillation

(7) history of renal insufficiency

 

Parameter

Finding

Points

respiratory rate

 

0.04883 * (rate)

serum BUN

 

0.004967 * (BUN)

age in years

 

0.011588 * (age)

serum glucose

 

0.003519 * (glucose)

serum chloride

 

0.036104 * (chloride)

atrial fibrillation

no

0

 

yes

0.580153

renal insufficiency

no

0

 

yes

0.458202

 

value of X =

= SUM(points for all of the parameters) - 9.284491

 

probability of readmission =

= 1 / (1 + EXP((-1) * X))

 

Performance:

• The area under the ROC curve is 0.71.


To read more or access our algorithms and calculators, please log in or register.