Rouabhi et al reported a prediction model for cerebral palsy in a term neonate. The authors are from multiple institutions in Canada.
Patient selection: term neonate
Parameters:
(1) number of pregnancies
(2) number of miscarriages
(3) tobacco use
(4) drug use (substance abuse)
(5) diabetes
(6) pre-eclampsia
(7) chorioamnionitis
(8) prolonged rupture of the membranes (PROM)
(9) 5-minute Apgar score
(10) gestational age in weeks at birth
(11) sex
(12) birthweight in kilograms
|
Parameters
|
Finding
|
Points
|
|
number of pregnancies
|
|
0.31 * (number)
|
|
number of miscarriages
|
|
-0.29 * (number)
|
|
tobacco use
|
no
|
0
|
|
|
yes
|
0.82
|
|
drug use
|
no
|
0
|
|
|
yes
|
2.34
|
|
diabetes
|
no
|
0
|
|
|
yes
|
0.75
|
|
pre-eclampsia
|
no
|
0
|
|
|
yes
|
1.39
|
|
chorioamnionitis
|
no
|
0
|
|
|
yes
|
2.7
|
|
PROM
|
no
|
0
|
|
|
yes
|
-0.69
|
|
5-minute Apgar
|
|
-0.44 * (score)
|
|
gestational age
|
|
-0.11 * (age)
|
|
sex
|
male
|
0.21
|
|
|
female
|
0
|
|
birthweight in kg
|
|
(0.27 * ((weight)^2)) - (2.2 * (weight))
|
value of X =
= SUM(points for all of the parameters) + 10.9
probability of cerebral palsy =
= 1 / (1 + EXP((-1) * X))
Performance:
• The area under the ROC curve is 0.74.
