Machine learning-driven pathogen cluster analysis identifies high-risk subtypes of infected pancreatic necrosis in a multi-center cohort

doi:10.3748/wjg.118717

Advanced Search

BPG is committed to discovery and dissemination of knowledge

Home / Archive / Volume 32, Issue 27

This Article

(3)

(4)

(0)

(1)

(63)

Peer-Review Report of This Article

CrossCheck and Google Search of This Article

Academic Rules and Norms of This Article

Supplementary Materials 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

Journal Information of This Article

Publication Name

World Journal of Gastroenterology

ISSN

1007-9327

Publisher of This Article

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

Retrospective Study

Copyright: ©Author(s) 2026. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial (CC BY-NC 4.0) license. No commercial re-use. See permissions. Published by Baishideng Publishing Group Inc.

World J Gastroenterol. Jul 21, 2026; 32(27): 118717
Published online Jul 21, 2026. doi: 10.3748/wjg.118717

Table 1 Baseline of clusters in the derivation cohort, n (%)

Characteristics	Levels	Cluster α (n = 112)	Cluster β (n = 78)	Cluster γ (n = 152)	Cluster δ (n = 54)	P value
Age	mean ± SD	46.5 ± 13.8	45.9 ± 12.8	47.0 ± 12.2	49.2 ± 12.3	0.498
Gender	Female	30 (26.8)	21 (26.9)	37 (24.3)	14 (25.9)	0.964
Gender	Male	82 (73.2)	57 (73.1)	115 (75.7)	40 (74.1)
Complications	No	73 (65.2)	56 (71.8)	111 (73)	35 (64.8)	0.453
Complications	Yes	39 (34.8)	22 (28.2)	41 (27)	19 (35.2)
Smoking or drinking	No	68 (60.7)	43 (55.1)	87 (57.2)	31 (57.4)	0.887
Smoking or drinking	Yes	44 (39.3)	35 (44.9)	65 (42.8)	23 (42.6)
Etiology	Biliary	56 (50)	37 (47.4)	76 (50)	28 (51.9)	0.820
	Hypertriglyceridemia	36 (32.1)	27 (34.6)	46 (30.3)	12 (22.2)
	Alcoholic	4 (3.6)	4 (5.1)	6 (3.9)	5 (9.3)
	Other	16 (14.3)	10 (12.8)	24 (15.8)	9 (16.7)
Severity classification	Critical acute pancreatitis	49 (43.8)	33 (42.3)	94 (61.8)	36 (66.7)	0.001
APACHE II score	Median (IQR)	8.0 (5.0-12.0)	8.0 (5.0-14.0)	9.0 (5.0-15.0)	11.5 (6.0-20.0)	0.051
BISAP score	Median (IQR)	2.0 (1.0-3.0)	2.0 (1.0-2.0)	2.0 (2.0-3.0)	2.0 (2.0-3.0)	0.007
Number of organ failures	No	64 (57.1)	42 (53.8)	55 (36.2)	17 (31.5)	0.002
	Single organ failure	19 (17)	18 (23.1)	33 (21.7)	13 (24.1)
	Multiple organ failure	29 (25.9)	18 (23.1)	64 (42.1)	24 (44.4)
Respiratory failure	No	73 (65.2)	48 (61.5)	65 (42.8)	20 (37)	< 0.001
Respiratory failure	Yes	39 (34.8)	30 (38.5)	87 (57.2)	34 (63)
Renal failure	No	78 (69.6)	57 (73.1)	92 (60.5)	29 (53.7)	0.055
Renal failure	Yes	34 (30.4)	21 (26.9)	60 (39.5)	25 (46.3)
Circulation failure	No	90 (80.4)	68 (87.2)	104 (68.4)	42 (77.8)	0.009
Circulation failure	Yes	22 (19.6)	10 (12.8)	48 (31.6)	12 (22.2)
ICU stay	No	39 (34.8)	35 (44.9)	29 (19.1)	17 (31.5)	< 0.001
ICU stay	Yes	73 (65.2)	43 (55.1)	123 (80.9)	37 (68.5)
Duration of ICU stay	Median (IQR)	5.0 (0.0-17.0)	2.5 (0.0-13.0)	10.0 (3.0-21.5)	9.0 (0.0-18.0)	< 0.001
Surgery approach	Step-up approach	95 (84.8)	66 (84.6)	128 (84.2)	47 (87)	0.969
Surgery approach	Step-down approach	17 (15.2)	12 (15.4)	24 (15.8)	7 (13)
The number of surgery intervention	Median (IQR)	3.0 (2.0-4.0)	3.0 (2.0-5.0)	4.0 (3.0-6.0)	3.5 (2.0-6.0)	0.024
Invasive ventilation	No	64 (57.1)	53 (67.9)	91 (59.9)	23 (42.6)	0.034
Invasive ventilation	Yes	48 (42.9)	25 (32.1)	61 (40.1)	31 (57.4)
CRRT	No	91 (81.2)	71 (91)	109 (71.7)	32 (59.3)	< 0.001
CRRT	Yes	21 (18.8)	7 (9)	43 (28.3)	22 (40.7)
CVC indwelling	No	73 (65.2)	53 (67.9)	84 (55.3)	19 (35.2)	< 0.001
CVC indwelling	Yes	39 (34.8)	25 (32.1)	68 (44.7)	35 (64.8)
Vasopressor administration	No	82 (73.2)	66 (84.6)	86 (56.6)	31 (57.4)	< 0.001
Vasopressor administration	Yes	30 (26.8)	12 (15.4)	66 (43.4)	23 (42.6)
Hemorrhage	No	89 (80.9)	64 (82.1)	111 (73)	43 (79.6)	0.314
Hemorrhage	Yes	21 (19.1)	14 (17.9)	41 (27)	11 (20.4)
Pancreatic fistula	No	58 (52.7)	54 (69.2)	87 (58)	38 (70.4)	0.049
Pancreatic fistula	Yes	52 (47.3)	24 (30.8)	63 (42)	16 (29.6)
Gastrointestinal fistula	No	99 (90)	66 (84.6)	119 (78.3)	48 (88.9)	0.053
Gastrointestinal fistula	Yes	11 (10)	12 (15.4)	33 (21.7)	6 (11.1)
Bloodstream infection	No	88 (78.6)	65 (83.3)	89 (58.6)	44 (81.5)	< 0.001
Bloodstream infection	Yes	24 (21.4)	13 (16.7)	63 (41.4)	10 (18.5)
Peripancreatic polymicrobial infection	No	46 (41.1)	32 (41)	44 (28.9)	33 (61.1)	< 0.001
Peripancreatic polymicrobial infection	Yes	66 (58.9)	46 (59)	108 (71.1)	21 (38.9)
Pancreatic fungal infection	No	83 (74.1)	66 (84.6)	111 (73)	37 (68.5)	0.144
Pancreatic fungal infection	Yes	29 (25.9)	12 (15.4)	41 (27)	17 (31.5)
Pancreatic MDRO infection	No	79 (70.5)	44 (56.4)	40 (26.3)	21 (38.9)	< 0.001
Pancreatic MDRO infection	Yes	33 (29.5)	34 (43.6)	112 (73.7)	33 (61.1)
Death	No	89 (79.5)	70 (89.7)	112 (73.7)	37 (68.5)	0.013
Death	Yes	23 (20.5)	8 (10.3)	40 (26.3)	17 (31.5)

α: Enterococcus faecium/Enterobacter cloacae–predominant; β: Escherichia coli–dominant; γ: Multidrug-resistant organism-enriched; δ: Acinetobacter baumannii–Candida glabrata; APACHE II score: Acute Physiology and Chronic Health Examination II score; BISAP score: Bedside Index of Severity in Acute Pancreatitis score; CRRT: Continuous renal replacement therapy; CVC: Central venous catheter; MDRO: Multidrug-resistant organisms; ICU: Intensive care unit; IQR: Interquartile range.

Full Size Table

Table 2 Statistical test results of in-hospital mortality among the clusters in the derivation cohort

Outcome	Statistical test P value
	General	Pairwise¹
	General	α vs β	α vs γ	α vs δ	β vs γ	β vs δ	γ vs δ
90-day mortality	0.008	0.300	1.000	0.480	0.024	0.006	1.000

¹P values for pairwise comparisons were adjusted using Bonferroni correction.

α: Enterococcus faecium/Enterobacter cloacae–predominant; β: Escherichia coli–dominant; γ: Multidrug-resistant organism-enriched; δ: Acinetobacter baumannii–Candida glabrata.

Full Size Table

Table 3 Adjusted associations between pathogen-defined clusters and 90-day mortality (Cox models)

Characteristics	Hazard ratio	Lower 95%CI	Upper 95%CI	P value
Age	0.997	0.979	1.016	0.785
APACHE II score	0.992	0.954	1.031	0.68
BISAP score	1.295	0.991	1.693	0.059
Cluster
Cluster α
Cluster β	0.337	0.118	0.965	0.043
Cluster γ	1.397	0.782	2.498	0.259
Cluster δ	2.35	1.136	4.863	0.021
Complications
No
Yes	0.793	0.476	1.323	0.375
Critical acute pancreatitis
No
Yes	0.857	0.451	1.631	0.639
Gender
Female
Male	0.809	0.414	1.582	0.536
Smoking or drinking
No
Yes	1.36	0.785	2.356	0.273
Type of pancreatitis
Biliary
Hypertriglyceridemia	1.101	0.613	1.977	0.747
Alcoholic	1.013	0.222	4.63	0.986
Other	0.875	0.405	1.893	0.735

Models adjusted for age, gender, Acute Physiology and Chronic Health Evaluation II score, etiology of pancreatitis (biliary, hypertriglyceridaemia, alcohol, other), complications, smoking or drinking and critical acute pancreatitis. Proportional-hazards assumptions were checked using Schoenfeld residuals and no material violations were observed. CI: Confidence interval; APACHE II score: Acute Physiology and Chronic Health Examination II score; BISAP score: Bedside Index of Severity in Acute Pancreatitis score; α: Enterococcus faecium/Enterobacter cloacae–predominant; β: Escherichia coli–dominant; γ: Multidrug-resistant organism-enriched; δ: Acinetobacter baumannii–Candida glabrata.

Full Size Table

Citation: Liu BQ, Sun ZF, Ning CH, Xiao J, Wu D, Lin CY, Hong XY, Guo R, Chen L, Cao XT, Shen DC, Huang GW. Machine learning-driven pathogen cluster analysis identifies high-risk subtypes of infected pancreatic necrosis in a multi-center cohort. World J Gastroenterol 2026; 32(27): 118717
URL: https://www.wjgnet.com/1007-9327/full/v32/i27/118717.htm
DOI: https://dx.doi.org/10.3748/wjg.118717

Liu BQ, Sun ZF, Ning CH, Xiao J, Wu D, Lin CY, Hong XY, Guo R, Chen L, Cao XT, Shen DC, Huang GW. Machine learning-driven pathogen cluster analysis identifies high-risk subtypes of infected pancreatic necrosis in a multi-center cohort. World J Gastroenterol 2026; 32(27): 118717 [DOI: 10.3748/wjg.118717]

All content on this site: Copyright © 1993-2026 Baishideng Publishing Group Inc, its licensors, and contributors. All rights are reserved, including those for text and data mining, AI training, and similar technologies. For all open access content, the relevant licensing terms apply.