Huang et al reported a model for predicting facial computed tomography (CT) in a blunt trauma patient. Facial CT can identify facial fractures that might be missed on brain CT. The authors are from National Yang-Ming University and Chang Gung Memorial Hospital in Taiwan.
Patient selection: blunt trauma
Parameters:
(1) age in years
(2) sex
(3) type of injury
(4) loss of consciousness
(5) epistaxis
(6) tooth rupture
(7) facial traumatic lesion
(8) intracranial hemorrhage
(9) skull fracture
Parameter
Finding
Points
age in years
-0.01 * (age)
sex
female
0
male
0.43
type of injury
fall from elevation
0.834
motorcycle collision
0.545
other
0
loss of consciousness
no
0
yes
1.048
epistaxis
no
0
yes
2.13
tooth rupture
no
0
yes
1.148
facial lesion
no
0
yes
3.412
intracranial hemorrhage
no
0
yes
0.527
skull fracture
no
0
yes
1.295
value of X =
= SUM(points for all of the parameters) - 4.721
probability of facial CT =
= 1 / (1 + EXP((-1) * X))
Performance:
• The area under the ROC curve is 0.90 in the derivation and 0.91 in the validation cohorts.
To read more or access our algorithms and calculators, please log in or register.