Optimizing the Prognostic Model of Cervical Cancer Based on Artificial Intelligence Algorithm and Data Mining Technology

Table 1

Clinicopathological characteristics of cervical cancer patients.

Characteristics	Groups	Patients
		Total (9)	Training dataset ()	Validation dataset ()
Age at initial diagnosis	Median	46.5	47	46
	Range	20-88	24-81	20-88
	<50	177	102 (57.63)	75 (42.37)
	≥50	122	78 (63.93)	44 (36.07)
FIGO stage	I	158	96 (60.76)	62 (39.24)
	II	5	3 (60.00)	2 (40.00)
	IIA	21	13 (61.90)	8 (38.10)
	IIB	43	24 (55.81)	19 (44.19)
	III	44	23 (52.27)	21 (47.73)
	IV	21	15 (71.43)	6 (28.57)
	Unknown	7	6 (85.71)	1 (14.29)
Histological type	SCC	247	142 (57.49)	105 (42.51)
	Adenocarcinoma	46	33 (71.74)	13 (28.26)
	Adenosquamous	6	5 (83.33)	1 (16.67)
Histologic grade	G1	16	8 (50.00)	8 (50.00)
	G2	131	78 (59.54)	53 (40.46)
	G3	120	71 (59.17)	49 (40.83)
	Others	32	23 (71.88)	9 (28.12)
Neoplasm statue	Tumor free	186	112 (60.22)	74 (39.78)
	With tumor	71	45 (63.38)	26 (36.62)
	Unknown	42	23 (54.76)	19 (45.24)

G: grade; SCC: squamous cell carcinoma. Values are shown as (%) unless otherwise specified.