Fan et al reported a model for predicting the risk of acute kidney injury (AKI) in a patient with diabetic ketoacidosis. This can help to identify a patient who may require more aggressive management. The authors are from the Second Affiliated Hospital of Jilin University in China.
Patient selection: diabetic ketoacidosis
Parameters:
(1) Glasgow coma scale (GCS)
(2) diabetic microangiopathy
(3) diabetes type
(4) history of congestive heart failure
(5) history of hypertension
(6) diastolic blood pressure in mm Hg, from 10 to 90
(7) urine output in mL, from 0 to 11,000, presumably daily
(8) respiratory rate in breaths per minute, from 10 to 70
points for GCS =
= 96.25 - (6.42 * (GCS))
points for diastolic blood pressure =
= 58.8 - (0.63 * (DBP))
points for respiratory rate =
= (1.667 * (rate)) - 16.667
points for urine output =
= 97.4 - (0.00885 * (output))
|
Parameter
|
Finding
|
Points
|
|
microangiopathy
|
no
|
0
|
|
|
yes
|
27.8
|
|
DM type
|
type 1
|
0
|
|
|
type 2
|
32.6
|
|
CHF
|
no
|
0
|
|
|
yes
|
35.2
|
|
hypertension
|
no
|
0
|
|
|
yes
|
30.8
|
total score =
= SUM(points for all of the parameters)
Interpretation:
• minimum score: 0
• maximum score: 451.4
value of X =
= (0.02906 * (score)) - 5.085
probability of AKI =
= 1 / (1 + EXP((-1) * X))
Performance:
• The area under the ROC curve is 0.75.
