Unveiling the secrets of gastrointestinal mucous adenocarcinoma survival after surgery with artificial intelligence: A population-based study

Table 1 Data filtering condition

Option in SEER	Value
Database	SEER Research Plus Data, 18 registries. Nov 2020 Sub (2000-2018)
ICD-O-3 Hist/behav	8480/3: Mucinous adenocarcinoma
Primary site-labeled	C16.0-Cardia, NOS
	C16.1-Fundus of stomach
	C16.2-Body of stomach
	C16.3-Gastric antrum
	C16.4-Pylorus
	C16.5-Lesser curvature of stomach NOS
	C16.6-Greater curvature of stomach NOS
	C16.8-Overlapping lesion of stomach
	C16.9-Stomach, NOS
	C17.0-Duodenum
	C17.1-Jejunum
	C17.2-Ileum
	C17.8-Overlapping lesion of small intestine
	C17.9-Small intestine, NOS
	C18.0-Cecum
	C18.1-Appendix
	C18.2-Ascending colon
	C18.3-Hepatic flexure of colon
	C18.4-Transverse colon
	C18.5-Splenic flexure of colon
	C18.6-Descending colon
	C18.7-Sigmoid colon
	C18.8-Overlapping lesion of colon
	C18.9-Colon, NOS
	C19.9-Rectosigmoid junction
	C20.9-Rectum, NOS
Other	Receive surgery and records without missing value

SEER: The Surveillance, Epidemiology, and End Results; ICD-O-3: The International Classification of Diseases for Oncology, Third Edition; NOS: Not otherwise specified.

Table 2 Clinical features of patients, n (%)

	Discovery cohort (n = 7972)	Validation cohort (n = 2392)	Test cohort (n = 1026)	Statistical test method	P value
Age				Kruskal-Wallis	0.5211
Median (IQR)	69 (58, 79)	70 (59, 79)	69 (58, 80)
Sex				Chi-square	0.4781
Female	4029 (50.54)	1219 (50.96)	539 (52.53)
Male	3943 (49.46)	1173 (49.04)	487 (47.47)
Malignant tumor history				Chi-square	0.2368
No	6217 (77.99)	1830 (76.51)	807 (78.65)
Yes	1755 (22.01)	562 (23.49)	219 (21.35)
Site				Chi-square	0.6989
Stomach	180 (2.26)	46 (1.92)	18 (1.75)
Small intestine	105 (1.32)	37 (1.55)	11 (1.07)
Cecum and appendix	2312 (29.00)	729 (30.48)	293 (28.56)
Rectum and rectosigmoid junction	1003 (12.58)	295 (12.33)	129 (12.57)
Other colon	4372 (54.84)	1285 (53.72)	575 (56.04)
T				Chi-square	0.3557
T1	265 (3.32)	75 (3.14)	27 (2.63)
T1a	2 (0.03)	2 (0.08)	0 (0.00)
T1b	16 (0.20)	4 (0.17)	1 (0.10)
T2	883 (11.08)	301 (12.58)	107 (10.43)
T3	4505 (56.51)	1331 (55.64)	591 (57.60)
T4	54 (0.68)	20 (0.84)	8 (0.78)
T4a	1323 (16.60)	356 (14.88)	173 (16.86)
T4b	924 (11.59)	303 (12.67)	119 (11.60)
N				Chi-square	0.6443
N0	4123 (51.72)	1284 (53.68)	543 (52.92)
N1	260 (3.26)	74 (3.09)	22 (2.14)
N1a	832 (10.44)	235 (9.82)	96 (9.36)
N1b	920 (11.54)	267 (11.16)	126 (12.28)
N1c	137 (1.72)	29 (1.21)	16 (1.56)
N2	104 (1.30)	31 (1.30)	13 (1.27)
N2a	654 (8.20)	208 (8.70)	99 (9.65)
N2b	898 (11.26)	255 (10.66)	107 (10.43)
N3	11 (0.14)	4 (0.17)	2 (0.19)
N3a	20 (0.25)	3 (0.13)	1 (0.10)
N3b	13 (0.16)	2 (0.08)	1 (0.10)
M				Chi-square	0.4620
M0	6689 (83.91)	2022 (84.53)	873 (85.09)
M1	96 (1.20)	22 (0.92)	10 (0.97)
M1a	563 (7.06)	162 (6.77)	79 (7.70)
M1b	624 (7.83)	186 (7.78)	64 (6.24)
Stage				Chi-square	0.8700
I	883 (11.08)	292 (12.21)	102 (9.94)
IA	10 (0.13)	3 (0.13)	0 (0.00)
IB	21 (0.26)	3 (0.13)	2 (0.19)
II	3 (0.04)	1 (0.04)	0 (0.00)
IIA	2236 (28.05)	675 (28.22)	305 (29.73)
IIB	405 (5.08)	112 (4.68)	52 (5.07)
IIC	303 (3.80)	111 (4.64)	46 (4.48)
III	2 (0.03)	1 (0.04)	0 (0.00)
IIIA	222 (2.78)	67 (2.80)	28 (2.73)
IIIB	1742 (21.85)	506 (21.15)	227 (22.12)
IIIC	862 (10.81)	251 (10.49)	111 (10.82)
IV	96 (1.20)	22 (0.92)	10 (0.97)
IVA	523 (6.56)	145 (6.06)	73 (7.12)
IVB	603 (7.56)	188 (7.86)	63 (6.14)
IVC	61 (0.77)	15 (0.63)	7 (0.68)
Tumor size (mm)				Kruskal-Wallis	0.4812
Median (IQR)	53.5 (38.0, 72.0)	53.0 (38.0, 75.0)	51.0 (40.0, 70.0)	Median (IQR)
Regional nodes positive				Kruskal-Wallis	0.4721
Median (IQR)	0 (0, 3)	0 (0, 3)	0 (0, 3)
Regional nodes examined				Kruskal-Wallis	0.4691
Median (IQR)	18 (13, 24)	18 (13, 24)	17 (13, 23)
Radiotherapy				Chi-square	0.4074
No	7231 (90.70)	2180 (91.14)	943 (91.91)
Yes	741 (9.30)	212 (8.86)	83 (8.09)
Chemotherapy				Chi-square	0.6545
No	4615 (57.89)	1378 (57.61)	608 (59.26)
Yes	3357 (42.11)	1014 (42.39)	418 (40.74)
Survival time				Kruskal-Wallis	0.2472
Median (IQR)	45 (20.00, 69.00)	45 (20.75, 69.00)	48 (21.00, 71.75)
Status				Chi-square	0.8302
Alive	4034 (50.60)	1195 (49.96)	522 (50.88)
Dead	3938 (49.40)	1197 (50.04)	504 (49.12)

IQR: Interquartile range.

Table 3 Overall performance of the model

	AUC	AUC, 95%CI
	Mean	Low	High
Discovery cohort	0.7433	0.7424	0.7442
Validation cohort	0.7244	0.7234	0.7254
Test cohort	0.7388	0.7378	0.7398

AUC: Area under receiver operating characteristic curve; CI: Confidence interval.

Table 4 Model’s performance at 1-, 3- and 5-years’ overall survival prediction

	Discovery cohort			Validation cohort			Test cohort
	1 yr	3 yr	5 yr	1 yr	3 yr	5 yr	1 yr	3 yr	5 yr
AUC	0.7953	0.8034	0.7971	0.7757	0.7843	0.7772	0.7938	0.7888	0.7871
AUC, 95%CI	0.7817-0.8090	0.7933-0.8136	0.7873-0.8069	0.7501-0.8012	0.7650-0.8036	0.7587-0.7958	0.7566-0.8310	0.7603-0.8173	0.7597-0.8146
Specificity	0.7688	0.7675	0.7985	0.6493	0.7260	0.7586	0.7182	0.6869	0.7296
Sensitivity	0.6742	0.6963	0.6595	0.7775	0.7242	0.6746	0.7386	0.7507	0.7127
Accuracy	0.7536	0.7421	0.7365	0.6697	0.7253	0.7203	0.7212	0.7086	0.7222
NPV	0.9250	0.8200	0.7441	0.9388	0.8234	0.7355	0.9400	0.8424	0.7655
PPV	0.3581	0.6243	0.7253	0.2964	0.5987	0.7010	0.3148	0.5527	0.6723

AUC: Area under receiver operating characteristic curve; CI: Confidence interval; NPV: Negative predictive value; PPV: Positive predictive value.