Model of Srivastava et al for Predicting Perinatal Arterial Ischemic Stroke (PAIS) in a Term Neonate

Description

Srivastava et al reported a model for predicting perinatal arterial ischemic stroke (PAIS) in a term neonate. This can help to identify a high-risk neaonate who may require more aggressive management. The authors are from multiple institutions in Canada, England, the Netherlands and the United States.

Patient selection: term neonate

Parameters:

(1) maternal age in years

(2) tobacco exposure (not specifically defined, presumably smoking)

(3) substance use

(4) preeclampsia

(5) chorioamnionitis

(6) maternal fever intrapartum

(7) emergency cesarean delivery

(8) 5-minute Apgar score, from 0 to 10

(9) sex of neonate

Parameter	Finding	Points
maternal age		-0.1 * (age)
tobacco exposure	no	0
	yes	0.21
substance use	no	0
	yes	1.73
preeclampsia	no	0
	yes	0.86
chorioamnionitis	no	0
	yes	1.29
maternal fever intrapartum	no	0
	yes	0.52
emergency cesarean	no	0
	yes	0.50
5-minute Apgar	high (>= 7)	0
	low (< 7)	1.69
sex of neonate	female	0
	male	0.28

value of X =

= SUM(points for all of the parameters) + 1.26

probability of PAIS =

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

NOTE: The equation as written gives a higher-than-expected probability (30% risk with low risk pregnancy). The constant for a logistic regression model is typically a negative value. A modified equation using -1.26 is included in the implementation.

Performance:

• The area under the ROC curve is 0.73.

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