Predicting the magnitude of risk for non-curative endoscopic submucosal dissection in superficial esophageal cancer using explainable artificial intelligence

doi:10.4251/wjgo.v18.i2.114782

Advanced Search

BPG is committed to discovery and dissemination of knowledge

Home / Archive / Volume 18, Issue 2

This Article

Academic Content and Language Evaluation of This Article

CrossCheck and Google Search of This Article

Academic Rules and Norms of This Article

Citation of this article

Corresponding Author of This Article

Research Domain of This Article

Article-Type of This Article

Open-Access Policy of This Article

Times Cited Counts in Google of This Article

Number of Hits and Downloads for This Article

Total Article Views (0)

All Articles published online

The chart showing PDF series, HTML series, Figures (1-7) series, Tables (1-2) series.

Item

Count

PDF

HTML

Figures (1-7)

Tables (1-2)

Sum=3

Publishing Process of This Article

The chart showing Browse series, Download series.

Item

Count

Browse

Download

Sum=2

Feb 15, 2026 (publication date) through Feb 3, 2026

Times Cited of This Article

Times Cited (0)

Journal Information of This Article

Publication Name

World Journal of Gastrointestinal Oncology

ISSN

1948-5204

Publisher of This Article

Baishideng Publishing Group Inc, 7041 Koll Center Parkway, Suite 160, Pleasanton, CA 94566, USA

Retrospective Study

World J Gastrointest Oncol. Feb 15, 2026; 18(2): 114782
Published online Feb 15, 2026. doi: 10.4251/wjgo.v18.i2.114782

Table 1 Baseline demographic profile and clinical parameters of the study cohort, n (%)

Variable	Classification term	Total (n = 495)	Training set (n = 366)	Testing set (n = 129)	P value
Age	< 67	225 (45.455)	181 (49.454)	44 (34.109)	0.003
	≥ 67	270 (54.545)	185 (50.546)	85 (65.891)
Gender	Female	157 (31.717)	126 (34.426)	31 (24.031)	0.029
	Male	338 (68.283)	240 (65.574)	98 (75.969)
BMI	< 22.21 kg/m²	250 (50.505)	196 (53.552)	54 (41.860)	0.022
	≥ 22.21 kg/m²	245 (49.495)	170 (46.448)	75 (58.140)
Hypertension	No	379 (76.566)	279 (76.230)	100 (77.519)	0.766
	Yes	116 (23.434)	87 (23.770)	29 (22.481)
Diabetic condition	No	425 (85.859)	321 (87.705)	104 (80.620)	0.047
	Yes	70 (14.141)	45 (12.295)	25 (19.380)
Cardiovascular disorder	No	467 (94.343)	346 (94.536)	121 (93.798)	0.755
	Yes	28 (5.657)	20 (5.464)	8 (6.202)
Renal impairment	No	484 (97.778)	358 (97.814)	126 (97.674)	0.926
	Yes	11 (2.222)	8 (2.186)	3 (2.326)
COPD	No	456 (92.121)	351 (95.902)	105 (81.395)	< 0.001
	Yes	39 (7.879)	15 (4.098)	24 (18.605)
Smoking history	No	284 (57.374)	226 (61.749)	58 (44.961)	< 0.001
	Yes	211 (42.626)	140 (38.251)	71 (55.039)
Alcohol intake	No	341 (68.889)	247 (67.486)	94 (72.868)	0.256
	Yes	154 (31.111)	119 (32.514)	35 (27.132)
Familial predisposition	No	447 (90.303)	341 (93.169)	106 (82.171)	< 0.001
	Yes	48 (9.697)	25 (6.831)	23 (17.829)
PLR	< 146.207	345 (69.697)	250 (68.306)	95 (73.643)	0.257
	≥ 146.207	150 (30.303)	116 (31.694)	34 (26.357)
PNR	< 48.367	181 (36.566)	138 (37.705)	43 (33.333)	0.375
	≥ 48.367	314 (63.434)	228 (62.295)	86 (66.667)
NLR	< 2.092	251 (50.707)	191 (52.186)	60 (46.512)	0.268
	≥ 2.092	244 (49.293)	175 (47.814)	69 (53.488)
SII	< 566.753	313 (63.232)	239 (65.301)	74 (57.364)	0.108
	≥ 566.753	182 (36.768)	127 (34.699)	55 (42.636)
EOM	< SM1	145 (29.293)	108 (29.508)	37 (28.682)	0.240
	SM1	238 (48.081)	169 (46.175)	69 (53.488)
	> SM1	112 (22.626)	89 (24.317)	23 (17.829)
Brownish discoloration	No	210 (42.424)	162 (44.262)	48 (37.209)	0.163
	Yes	285 (57.576)	204 (55.738)	81 (62.791)
Esophageal stricture	No	446 (90.101)	332 (90.710)	114 (88.372)	0.444
	Yes	49 (9.899)	34 (9.290)	15 (11.628)
CR	< 1/2	139 (28.081)	105 (28.689)	34 (26.357)	0.610
	1/2-3/4	208 (42.020)	149 (40.710)	59 (45.736)
	> 3/4	148 (29.899)	112 (30.601)	36 (27.907)
Chronic esophagitis	No	469 (94.747)	342 (93.443)	127 (98.450)	0.028
	Yes	26 (5.253)	24 (6.557)	2 (1.550)
Multiple lesions	No	434 (87.677)	317 (86.612)	117 (90.698)	0.225
	Yes	61 (12.323)	49 (13.388)	12 (9.302)
Tumor enhancement	No	261 (52.727)	189 (51.639)	72 (55.814)	0.414
	Yes	234 (47.273)	177 (48.361)	57 (44.186)
Thickness	< 5 mm	223 (45.051)	168 (45.902)	55 (42.636)	0.395
	5-7 mm	177 (35.758)	133 (36.339)	44 (34.109)
	> 7 mm	95 (19.192)	65 (17.760)	30 (23.256)
LVI	No	461 (93.131)	343 (93.716)	118 (91.473)	0.386
	Yes	34 (6.869)	23 (6.284)	11 (8.527)
Differentiation grade	Well-differentiated	99 (20.000)	78 (21.311)	21 (16.279)	0.295
	Moderately-differentiated	370 (74.747)	267 (72.951)	103 (79.845)
	Poorly-differentiated	26 (5.253)	21 (5.738)	5 (3.876)
Invasion depth	< SM1	241 (48.687)	182 (49.727)	59 (45.736)	0.321
	SM1	185 (37.374)	130 (35.519)	55 (42.636)
	> SM1	69 (13.939)	54 (14.754)	15 (11.628)
Positive vertical margin	No	474 (95.758)	350 (95.628)	124 (96.124)	0.810
	Yes	21 (4.242)	16 (4.372)	5 (3.876)
PPT	HGIN/LGIN	197 (39.798)	149 (40.710)	48 (37.209)	0.485
	ESCC	298 (60.202)	217 (59.290)	81 (62.791)
NCR	No	390 (78.788)	282 (77.049)	108 (83.721)	0.111
	Yes	105 (21.212)	84 (22.951)	21 (16.279)
Paris classification	II-a	151 (30.505)	111 (30.328)	40 (31.008)	0.998
	II-b	220 (44.444)	163 (44.536)	57 (44.186)
	II-c	84 (16.970)	62 (16.940)	22 (17.054)
	Others	40 (8.081)	30 (8.197)	10 (7.752)
Tumor location	Cervical/upper thoracic	66 (13.333)	50 (13.661)	16 (12.403)	0.096
	Middle thoracic	296 (59.798)	227 (62.022)	69 (53.488)
	Lower thoracic	133 (26.869)	89 (24.317)	44 (34.109)
Hot beverage/food consumption	< 3 times weekly	365 (73.737)	276 (75.410)	89 (68.992)	0.154
	≥ 3 times weekly	130 (26.263)	90 (24.590)	40 (31.008)
Fried food consumption	< 3 times weekly	434 (87.677)	322 (87.978)	112 (86.822)	0.731
	≥ 3 times weekly	61 (12.323)	44 (12.022)	17 (13.178)
Fruit/vegetable consumption	< 3 times weekly	48 (9.697)	33 (9.016)	15 (11.628)	0.389
	≥ 3 times weekly	447 (90.303)	333 (90.984)	114 (88.372)
Preserved food consumption	< 3 times weekly	250 (50.505)	210 (57.377)	40 (31.008)	< 0.001
	≥ 3 times weekly	245 (49.495)	156 (42.623)	89 (68.992)
Oral health status	< 4 times weekly	44 (8.889)	32 (8.743)	12 (9.302)	0.954
	4-7 times weekly	438 (88.485)	324 (88.525)	114 (88.372)
	> 7 times weekly	13 (2.626)	10 (2.732)	3 (2.326)

BMI: Body mass index; COPD: Chronic obstructive pulmonary disease; PLR: Platelet-to-lymphocyte ratio; NLR: Neutrophil-to-lymphocyte ratio; PNR: Platelet-to-neutrophil ratio; SII: Systemic immune-inflammation index; EOM: Endoscopic ultrasound or magnifying endoscopy with narrow-band imaging; CR: Circumferential ratio; LVI: Lymphovascular invasion; PPT: Preoperative pathological type; NCR: Non-curative resection; SM1: Superficial layer; HGIN/LGIN: High-grade intraepithelial neoplasia/Low-grade intraepithelial neoplasia; ESCC: Esophageal squamous cell carcinoma.

Full Size Table

Table 2 Multivariable logistic regression analysis of non-curative resection after endoscopic submucosal dissection for superficial esophageal cancer

Predictor	Estimate	SE	OR (95%CI)	Z	P value
SII	0.55	0.295	1.733 (0.968-3.091)	1.863	0.063
Thickness = 5-7 mm	0.321	0.355	1.379 (0.688-2.790)	0.904	0.366
Thickness > 7 mm	1.12	0.379	3.065 (1.463-6.498)	2.956	0.003
EOM = SM1	0.894	0.459	2.445 (1.043-6.469)	1.947	0.052
EOM > SM1	2.327	0.479	10.252 (4.211-28.176)	4.854	0.0
Esophageal stricture	1.227	0.416	3.411 (1.512-7.760)	2.952	0.003
Multiple lesions	0.98	0.401	2.666 (1.210-5.865)	2.444	0.015
CR = 1/2-3/4	0.513	0.411	1.671 (0.763-3.872)	1.248	0.212
CR > 3/4	1.315	0.421	3.724 (1.669-8.799)	3.121	0.002
PPT	1.062	0.341	2.892 (1.513-5.791)	3.117	0.002

SII: Systemic immune-inflammation index; EOM: Endoscopic ultrasound or magnifying endoscopy with narrow-band imaging; SM1: Superficial layer; CR: Circumferential ratio; PPT: Preoperative pathological type.

Full Size Table

Citation: Luo ZC, Guo HY, Tang X, Chen XR, Zhang CY, Cui YT, Zuo J, Li HR, Hou XM, Chen H, Song SB, Wang XF. Predicting the magnitude of risk for non-curative endoscopic submucosal dissection in superficial esophageal cancer using explainable artificial intelligence. World J Gastrointest Oncol 2026; 18(2): 114782
URL: https://www.wjgnet.com/1948-5204/full/v18/i2/114782.htm
DOI: https://dx.doi.org/10.4251/wjgo.v18.i2.114782