Machine learning to predict pregnancy outcomes: a systematic review, synthesizing framework and future research agenda

Table 2 Objectives of the reviewed articles

Scope	Study Objective	Ref	Frequency
Predicting pregnancy risks/complications	Predicting risk level during pregnancy	[33]
	Explore risks related to voluntary termination of pregnancy	[47]
	Prediction of preterm/extreme preterm birth	[10, 48,49,50,51]	9 (35%)
	Prediction of risk of uterine rupture	[37]
	Prediction of risk of perinatal death	[52]
Exploring pregnancy factors	Determining factors related to successful vaginal delivery	[35]
	To explore factors responsible for emergency cesarean section	[39]
	To Determine influential factors in child mortality prediction	[44]	7 (27%)
	To explore factors responsible for preterm birth	[9, 53]
	Prediction of low birth weight and factors responsible for it	[46, 54]
Predicting mode of delivery	To predict delivery method	[8]	4 (15%)
	To predict success of vaginal birth after cesarean delivery	[36, 38, 41]
Predicting outcome of IVF treatment	Predicting early pregnancy loss	[45]
	Predicting successful pregnancy after IVF	[42]	3 (11%)
	Predicting the live birth chance	[55]
Predicting labor outcome	To determine the suitability of induction of labor	[34]	2 (8%)
	To determine potential value of cervical length in predicting progress of labor	[40]
Comparison between two birth weight groups	To compare outcome of vaginal intended breech deliveries between low weight group and high weight group	[43]	1 (4%)

ISSN: 1471-2393