Table 7.

Comparison with previously published machine learning-based GDM prediction models.

Model	Population	No. of features	Clinical test needed	Specificity	Sensitivity	AUC-ROC	AUC-PR
Model 1	Overweight & obese	5	Fasting blood test (fasting glucose, insulin, white cell count)	0.768	0.733	0.792	0.485
Model 2	Overweight& obese	5	Routine blood test (white cell count)	0.6	0.6	0.659	0.208
Model 3	Overweight & obese	4	No	0.674	0.533	0.656	0.199
Qiu et al.17	General	49	Fasting blood test (fasting plasma glucose, complete blood count, liver function test...)	0.998	0.622	0.847	–
Zheng et al.18	General	4	Fasting blood test (fasting plasma glucose, triglycerides)	0.75	0.66	0.766	–
Ye et al.19	General	17	Fasting blood test (fasting glucose, HbA1c, triglycerides...)	0.99	0.15	0.74	–
				0.26	0.90
Artzi et al.20	General	2,355	Laboratory tests including fasting blood test (glucose, white cell count...), blood pressure measurement, urine test, and blood test in previous pregnancy (glucose tolerance test...).	–	–	0.854	0.318
		9	Blood test in previous pregnancy (HbA1c% test, glucose challenge test/oral glucose tolerance test)	–	–	0.799	0.241
Xiong et al.21	General	43	Routine blood test, hepatic and renal function examination, coagulation function examination	0.995	0.883	0.942	–
Yan et al.22	General	61	Blood test (complete blood test, liver function test...), urine test (urine glucose, urinary gallbladder, nitrite...)	–	0.706	0.779	–
Hou et al.23	General	83	Single nucleotide polymorphism genes, blood test (cholesterol, white blood cell...)	–	–	0.852	–
Wu et al.24	General	73	Fasting blood test (fasting plasma glucose, complete blood count, liver function test)	0.82	0.63	0.80	–
		7	Fasting blood test (fasting plasma glucose, HbA1c, triglycerides)	0.82	0.59	0.77	–
Wu et al.25	General	15	Blood test (complete blood count, liver function test, ferritin...)	0.269	0.91	0.746	–
				0.524	0.75
				0.777	0.487