Table 1.

Previously published machine learning-based Gestational risk prediction models.

Authors	Subject/Data	Algorithms	AUC-ROC	Prediction	Clinical Support
Qiu et al. [12]	4378 pregnancies	Hybrid model of logistic regression, support vector machine	0.847	No	No
Ye et al. [13]	22,242 pregnancies	Gradient boosting, decision tree	0.74	No	No
Zheng et al. [14]	4771 pregnancies	Multivariate Bayesian logistic regression	0.766	No	No
Artzi et al. [15]	588,622 pregnancies	Gradient boosting	0.854	No	No
Xiong et al. [16]	490 pregnancies	Light gradient boosting machine	0.942	No	No
Yan et al. [17]	3988 pregnancies	Logistic regression	0.779	No	No
Hou et al. [18]	1000 pregnancies	Light gradient boosting machine	0.852	No	No
Wu et al. [19]	32,190 pregnancies	Deep neural network	0.80	No	No
Wu et al. [20]	17,005 pregnancies	Random forest	0.746	No	No
Wang, F. [21]	4260 pregnancies	Random Forest, logistic regression	0.953	Yes	No
Our paper	699 Pregnancies	Logistic Regression, Random Forest, SVM	0.91	Yes	Yes