Predicting lymph node metastasis in colorectal cancer: An analysis of influencing factors to develop a risk model

Postcholecystectomy bile duct injury (BDI) remains a devastating iatrogenic complication that adversely impacts the quality of life with high healthcare costs. Despite a decrease in the incidence of laparoscopic cholecystectomy-related BDI, the absolute number remains high as cholecystectomy is a co...

Full description

Saved in:
Bibliographic Details
Published inWorld journal of gastrointestinal surgery Vol. 15; no. 10; pp. 2234 - 2246
Main Authors Lei, Yun-Peng, Song, Qing-Zhi, Liu, Shuang, Xie, Ji-Yan, Lv, Guo-Qing
Format Journal Article
LanguageEnglish
Published United States Baishideng Publishing Group Inc 27.10.2023
Subjects
Online AccessGet full text
ISSN1948-9366
1948-9366
DOI10.4240/wjgs.v15.i10.2234

Cover

Abstract Postcholecystectomy bile duct injury (BDI) remains a devastating iatrogenic complication that adversely impacts the quality of life with high healthcare costs. Despite a decrease in the incidence of laparoscopic cholecystectomy-related BDI, the absolute number remains high as cholecystectomy is a commonly performed surgical procedure. Open Roux-en-Y hepaticojejunostomy with meticulous surgical technique remains the gold standard surgical procedure with excellent long-term results in most patients. As with many hepatobiliary disorders, a minimally invasive approach has been recently explored to minimize access-related complications and improve postoperative recovery. Since patients with gallstone disease are often admitted for a minimally invasive cholecystectomy, laparoscopic and robotic approaches for repairing postcholecystectomy biliary stricture are attractive. While recent series have shown the feasibility and safety of minimally invasive post-cholecystectomy biliary stricture management, most are retrospective analyses with small sample sizes. Also, long-term follow-up is available only in a limited number of studies. The principles and technique of minimally invasive repair resemble open repair except for the extent of adhesiolysis and the suturing technique with continuous sutures commonly used in minimally invasive approaches. The robotic approach overcomes key limitations of laparoscopic surgery and has the potential to become the preferred minimally invasive approach for the repair of postcholecystectomy biliary stricture. Despite increasing use, lack of prospective studies and selection bias with available evidence precludes definitive conclusions regarding minimally invasive surgery for managing postcholecystectomy biliary stricture. High-volume prospective studies are required to confirm the initial promising outcomes with minimally invasive surgery.
AbstractList Postcholecystectomy bile duct injury (BDI) remains a devastating iatrogenic complication that adversely impacts the quality of life with high healthcare costs. Despite a decrease in the incidence of laparoscopic cholecystectomy-related BDI, the absolute number remains high as cholecystectomy is a commonly performed surgical procedure. Open Roux-en-Y hepaticojejunostomy with meticulous surgical technique remains the gold standard surgical procedure with excellent long-term results in most patients. As with many hepatobiliary disorders, a minimally invasive approach has been recently explored to minimize access-related complications and improve postoperative recovery. Since patients with gallstone disease are often admitted for a minimally invasive cholecystectomy, laparoscopic and robotic approaches for repairing postcholecystectomy biliary stricture are attractive. While recent series have shown the feasibility and safety of minimally invasive post-cholecystectomy biliary stricture management, most are retrospective analyses with small sample sizes. Also, long-term follow-up is available only in a limited number of studies. The principles and technique of minimally invasive repair resemble open repair except for the extent of adhesiolysis and the suturing technique with continuous sutures commonly used in minimally invasive approaches. The robotic approach overcomes key limitations of laparoscopic surgery and has the potential to become the preferred minimally invasive approach for the repair of postcholecystectomy biliary stricture. Despite increasing use, lack of prospective studies and selection bias with available evidence precludes definitive conclusions regarding minimally invasive surgery for managing postcholecystectomy biliary stricture. High-volume prospective studies are required to confirm the initial promising outcomes with minimally invasive surgery.
Colorectal cancer (CRC) is a significant global health issue, and lymph node metastasis (LNM) is a crucial prognostic factor. Accurate prediction of LNM is essential for developing individualized treatment strategies for patients with CRC. However, the prediction of LNM is challenging and depends on various factors such as tumor histology, clinicopathological features, and molecular characteristics. The most reliable method to detect LNM is the histopathological examination of surgically resected specimens; however, this method is invasive, time-consuming, and subject to sampling errors and interobserver variability. To analyze influencing factors and develop and validate a risk prediction model for LNM in CRC based on a large patient queue. This study retrospectively analyzed 300 patients who underwent CRC surgery at two Peking University Shenzhen hospitals between January and December 2021. A deep learning approach was used to extract features potentially associated with LNM from primary tumor histological images while a logistic regression model was employed to predict LNM in CRC using machine-learning-derived features and clinicopathological variables as predictors. The prediction model constructed for LNM in CRC was based on a logistic regression framework that incorporated machine learning-extracted features and clinicopathological variables. The model achieved high accuracy (0.86), sensitivity (0.81), specificity (0.87), positive predictive value (0.66), negative predictive value (0.94), area under the curve for the receiver operating characteristic (0.91), and a low Brier score (0.10). The model showed good agreement between the observed and predicted probabilities of LNM across a range of risk thresholds, indicating good calibration and clinical utility. The present study successfully developed and validated a potent and effective risk-prediction model for LNM in patients with CRC. This model utilizes machine-learning-derived features extracted from primary tumor histology and clinicopathological variables, demonstrating superior performance and clinical applicability compared to existing models. The study provides new insights into the potential of deep learning to extract valuable information from tumor histology, in turn, improving the prediction of LNM in CRC and facilitate risk stratification and decision-making in clinical practice.
Colorectal cancer (CRC) is a significant global health issue, and lymph node metastasis (LNM) is a crucial prognostic factor. Accurate prediction of LNM is essential for developing individualized treatment strategies for patients with CRC. However, the prediction of LNM is challenging and depends on various factors such as tumor histology, clinicopathological features, and molecular characteristics. The most reliable method to detect LNM is the histopathological examination of surgically resected specimens; however, this method is invasive, time-consuming, and subject to sampling errors and interobserver variability.BACKGROUNDColorectal cancer (CRC) is a significant global health issue, and lymph node metastasis (LNM) is a crucial prognostic factor. Accurate prediction of LNM is essential for developing individualized treatment strategies for patients with CRC. However, the prediction of LNM is challenging and depends on various factors such as tumor histology, clinicopathological features, and molecular characteristics. The most reliable method to detect LNM is the histopathological examination of surgically resected specimens; however, this method is invasive, time-consuming, and subject to sampling errors and interobserver variability.To analyze influencing factors and develop and validate a risk prediction model for LNM in CRC based on a large patient queue.AIMTo analyze influencing factors and develop and validate a risk prediction model for LNM in CRC based on a large patient queue.This study retrospectively analyzed 300 patients who underwent CRC surgery at two Peking University Shenzhen hospitals between January and December 2021. A deep learning approach was used to extract features potentially associated with LNM from primary tumor histological images while a logistic regression model was employed to predict LNM in CRC using machine-learning-derived features and clinicopathological variables as predictors.METHODSThis study retrospectively analyzed 300 patients who underwent CRC surgery at two Peking University Shenzhen hospitals between January and December 2021. A deep learning approach was used to extract features potentially associated with LNM from primary tumor histological images while a logistic regression model was employed to predict LNM in CRC using machine-learning-derived features and clinicopathological variables as predictors.The prediction model constructed for LNM in CRC was based on a logistic regression framework that incorporated machine learning-extracted features and clinicopathological variables. The model achieved high accuracy (0.86), sensitivity (0.81), specificity (0.87), positive predictive value (0.66), negative predictive value (0.94), area under the curve for the receiver operating characteristic (0.91), and a low Brier score (0.10). The model showed good agreement between the observed and predicted probabilities of LNM across a range of risk thresholds, indicating good calibration and clinical utility.RESULTSThe prediction model constructed for LNM in CRC was based on a logistic regression framework that incorporated machine learning-extracted features and clinicopathological variables. The model achieved high accuracy (0.86), sensitivity (0.81), specificity (0.87), positive predictive value (0.66), negative predictive value (0.94), area under the curve for the receiver operating characteristic (0.91), and a low Brier score (0.10). The model showed good agreement between the observed and predicted probabilities of LNM across a range of risk thresholds, indicating good calibration and clinical utility.The present study successfully developed and validated a potent and effective risk-prediction model for LNM in patients with CRC. This model utilizes machine-learning-derived features extracted from primary tumor histology and clinicopathological variables, demonstrating superior performance and clinical applicability compared to existing models. The study provides new insights into the potential of deep learning to extract valuable information from tumor histology, in turn, improving the prediction of LNM in CRC and facilitate risk stratification and decision-making in clinical practice.CONCLUSIONThe present study successfully developed and validated a potent and effective risk-prediction model for LNM in patients with CRC. This model utilizes machine-learning-derived features extracted from primary tumor histology and clinicopathological variables, demonstrating superior performance and clinical applicability compared to existing models. The study provides new insights into the potential of deep learning to extract valuable information from tumor histology, in turn, improving the prediction of LNM in CRC and facilitate risk stratification and decision-making in clinical practice.
Author Lei, Yun-Peng
Lv, Guo-Qing
Song, Qing-Zhi
Xie, Ji-Yan
Liu, Shuang
Author_xml – sequence: 1
  givenname: Yun-Peng
  surname: Lei
  fullname: Lei, Yun-Peng
– sequence: 2
  givenname: Qing-Zhi
  surname: Song
  fullname: Song, Qing-Zhi
– sequence: 3
  givenname: Shuang
  surname: Liu
  fullname: Liu, Shuang
– sequence: 4
  givenname: Ji-Yan
  surname: Xie
  fullname: Xie, Ji-Yan
– sequence: 5
  givenname: Guo-Qing
  surname: Lv
  fullname: Lv, Guo-Qing
BackLink https://www.ncbi.nlm.nih.gov/pubmed/37969707$$D View this record in MEDLINE/PubMed
BookMark eNp9kUtv3CAUhVGVqnk0P6CbiGU2M8UGG5NNFEVtUylSu2jWCMNlQoJhAsxE8--LlYeSLoqQQJfvnIvuOUR7IQZA6EtDlqxl5Ovj3Sovt023dLXStpR9QAeNYMNC0L7fe3PfR8c535G6GOuFIJ_QPuWiF5zwA_TwO4Fxuriwwn43rW9xiAbwBEXlul3GLmAdfUygi_JYq6AhneGLgFVQfjcT0VbI-g0EPdtYpUtMGZeIDWzBxzVWOLl8j6dq7T-jj1b5DMfP5xG6-f7tz-XV4vrXj5-XF9cLTSkpCyDQU9ORjmgz0tYqIoQVtWjBjg3pWiY6oMoC56NhfAAzsNHYtqOjHchI6RE6f_Jdb8YJjIZQkvJyndyk0k5G5eT7l-Bu5SpuZUP6OmA-VIfTZ4cUHzaQi5xc1uC9ChA3WbaDILzjgrGKnrxt9trlZdAVaJ4AnWLOCewr0hA55ynnPGXNU9Y85Zxn1fB_NNoVVVyc_-v8f5R_AZuLqn4
CitedBy_id crossref_primary_10_7759_cureus_61832
crossref_primary_10_1016_j_surg_2024_109030
crossref_primary_10_1007_s00261_024_04668_z
crossref_primary_10_3390_ijms25020874
crossref_primary_10_1016_j_aca_2024_343360
Cites_doi 10.1097/EDE.0b013e3181c30fb2
10.1007/s11605-015-3026-6
10.1186/s12885-015-1632-z
10.3322/caac.21492
10.1097/SLA.0000000000000229
10.1245/s10434-013-3426-3
10.3748/wjg.v20.i22.6786
10.1080/07357900802098165
10.1001/jama.2017.14585
10.1002/ijc.28384
10.6004/jnccn.2018.0021
10.1038/s41598-018-21758-3
10.1245/s10434-010-0985-4
10.1007/s10147-017-1101-6
10.1200/JCO.2015.65.9128
10.1053/j.gastro.2004.04.022
10.1038/s43856-023-00282-0
10.1200/JCO.2012.46.2457
10.1136/gutjnl-2015-310961
10.1016/S1470-2045(13)70016-0
10.1016/j.csbj.2014.11.005
10.1038/s41591-019-0462-y
10.1136/bmj.g7594
10.1186/1479-5876-11-58
10.1200/JCO.2009.24.0952
10.1053/j.gastro.2018.01.023
10.1016/j.jamcollsurg.2013.04.018
10.1002/cncr.24396
10.1007/BF02049154
ContentType Journal Article
Copyright The Author(s) 2023. Published by Baishideng Publishing Group Inc. All rights reserved.
The Author(s) 2023. Published by Baishideng Publishing Group Inc. All rights reserved. 2023
Copyright_xml – notice: The Author(s) 2023. Published by Baishideng Publishing Group Inc. All rights reserved.
– notice: The Author(s) 2023. Published by Baishideng Publishing Group Inc. All rights reserved. 2023
DBID AAYXX
CITATION
NPM
7X8
5PM
DOI 10.4240/wjgs.v15.i10.2234
DatabaseName CrossRef
PubMed
MEDLINE - Academic
PubMed Central (Full Participant titles)
DatabaseTitle CrossRef
PubMed
MEDLINE - Academic
DatabaseTitleList CrossRef
PubMed
MEDLINE - Academic
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
DocumentTitleAlternate Lei YP et al. LNM in CRC
EISSN 1948-9366
EndPage 2246
ExternalDocumentID PMC10642478
37969707
10_4240_wjgs_v15_i10_2234
Genre Journal Article
GroupedDBID 53G
5VR
8WL
AAKDD
AAYXX
ADBBV
ALMA_UNASSIGNED_HOLDINGS
AOIJS
BAWUL
CCEZO
CHBEP
CIEJG
CITATION
CW9
DIK
E3Z
F5P
FA0
GX1
HYE
OK1
RNS
RPM
NPM
7X8
5PM
ID FETCH-LOGICAL-c330t-e0e63d5050cdb32fa099f90e6fefb1052495e3afe77bd478ed84bdf253bf80b33
ISSN 1948-9366
IngestDate Thu Aug 21 18:36:25 EDT 2025
Fri Jul 11 08:16:00 EDT 2025
Mon Jul 21 05:15:50 EDT 2025
Tue Jul 01 01:58:54 EDT 2025
Thu Apr 24 23:13:12 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed false
IsScholarly true
Issue 10
Keywords Lymph node metastasis
Risk prediction model
Clinicopathological factors
Individualized treatment strategies
Colorectal cancer
Machine learning
Language English
License The Author(s) 2023. Published by Baishideng Publishing Group Inc. All rights reserved.
This article is an open-access article that was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution NonCommercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial.
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c330t-e0e63d5050cdb32fa099f90e6fefb1052495e3afe77bd478ed84bdf253bf80b33
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
Corresponding author: Guo-Qing Lv, MD, MS, Attending Doctor, Department of Gastrointestinal Surgery, Shenzhen Peking University-The Hong Kong University of Science and Technology Medical Center, Peking University Shenzhen Hospital, No. 120 Lianhua Road, Futian District, Shenzhen 518036, Guangdong Province, China. 365973269@qq.com
Author contributions: Lei YP, Lv GQ proposed the concept of this study; Song QZ collected the data; Liu S and Lv GQ contributed to formal analysis; Xie JY and Lei YP conducted the survey; Song QZ and Liu S contributed to these methods; Lei YP and Song QZ guided the research; Lei YP, Lv GQ validated the results of the study; Song QZ contributed to the visualization of the study; Lei YP Song QZ and Lv GQ reviewed and edited the final manuscript.
Supported by “San Ming” Project of Shenzhen, No. SZSM201612051.
OpenAccessLink https://pubmed.ncbi.nlm.nih.gov/PMC10642478
PMID 37969707
PQID 2890757944
PQPubID 23479
PageCount 13
ParticipantIDs pubmedcentral_primary_oai_pubmedcentral_nih_gov_10642478
proquest_miscellaneous_2890757944
pubmed_primary_37969707
crossref_primary_10_4240_wjgs_v15_i10_2234
crossref_citationtrail_10_4240_wjgs_v15_i10_2234
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate 2023-10-27
2023-Oct-27
20231027
PublicationDateYYYYMMDD 2023-10-27
PublicationDate_xml – month: 10
  year: 2023
  text: 2023-10-27
  day: 27
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle World journal of gastrointestinal surgery
PublicationTitleAlternate World J Gastrointest Surg
PublicationYear 2023
Publisher Baishideng Publishing Group Inc
Publisher_xml – name: Baishideng Publishing Group Inc
References B20
B21
B22
B23
B24
B25
B26
B27
B28
B29
B30
B10
B11
B12
B13
B14
B15
B16
B17
B18
B19
B1
B2
B3
B4
B5
B6
B7
B8
B9
References_xml – ident: B25
  doi: 10.1097/EDE.0b013e3181c30fb2
– ident: B4
  doi: 10.1007/s11605-015-3026-6
– ident: B13
  doi: 10.1186/s12885-015-1632-z
– ident: B1
  doi: 10.3322/caac.21492
– ident: B27
  doi: 10.1097/SLA.0000000000000229
– ident: B28
  doi: 10.1245/s10434-013-3426-3
– ident: B30
  doi: 10.3748/wjg.v20.i22.6786
– ident: B6
  doi: 10.1080/07357900802098165
– ident: B23
  doi: 10.1001/jama.2017.14585
– ident: B9
  doi: 10.1002/ijc.28384
– ident: B2
  doi: 10.6004/jnccn.2018.0021
– ident: B12
  doi: 10.1038/s41598-018-21758-3
– ident: B8
  doi: 10.1245/s10434-010-0985-4
– ident: B16
  doi: 10.1007/s10147-017-1101-6
– ident: B21
  doi: 10.1200/JCO.2015.65.9128
– ident: B11
– ident: B19
  doi: 10.1053/j.gastro.2004.04.022
– ident: B20
  doi: 10.1038/s43856-023-00282-0
– ident: B29
  doi: 10.1200/JCO.2012.46.2457
– ident: B22
  doi: 10.1136/gutjnl-2015-310961
– ident: B7
  doi: 10.1016/S1470-2045(13)70016-0
– ident: B10
  doi: 10.1016/j.csbj.2014.11.005
– ident: B24
  doi: 10.1038/s41591-019-0462-y
– ident: B26
  doi: 10.1136/bmj.g7594
– ident: B3
  doi: 10.1186/1479-5876-11-58
– ident: B17
  doi: 10.1200/JCO.2009.24.0952
– ident: B15
  doi: 10.1053/j.gastro.2018.01.023
– ident: B5
  doi: 10.1016/j.jamcollsurg.2013.04.018
– ident: B14
  doi: 10.1002/cncr.24396
– ident: B18
  doi: 10.1007/BF02049154
SSID ssj0000446990
Score 2.2804122
Snippet Postcholecystectomy bile duct injury (BDI) remains a devastating iatrogenic complication that adversely impacts the quality of life with high healthcare costs....
Colorectal cancer (CRC) is a significant global health issue, and lymph node metastasis (LNM) is a crucial prognostic factor. Accurate prediction of LNM is...
SourceID pubmedcentral
proquest
pubmed
crossref
SourceType Open Access Repository
Aggregation Database
Index Database
Enrichment Source
StartPage 2234
SubjectTerms Retrospective Study
Title Predicting lymph node metastasis in colorectal cancer: An analysis of influencing factors to develop a risk model
URI https://www.ncbi.nlm.nih.gov/pubmed/37969707
https://www.proquest.com/docview/2890757944
https://pubmed.ncbi.nlm.nih.gov/PMC10642478
Volume 15
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1db9MwFLXKkBAviG86PmQknphckjipE96mCTRNKirSJnW8RE7itJmmBNpkCP4Of5R7bTd1V4RgL1HrOo6Uc2rfe318LyFvZKkKLIrDBBjLLFTjhMUyzpj0fSGFiKPcx8PJk0_j47PwZBbNBoNfjmqpa7NR_vOP50pugiq0Aa54SvY_kO0HhQb4DPjCFRCG6z9hPF3iNosWLl_-AFgO6gYFqaqVYPNhphEtMgePHGY1zAOCCC9tKFA62UgqW6lEqyptAR6wSe2BqgNpBOi6aI5rzBohjpN7Yg7PXTaYgQImDmxbOYeutepHawfOu5pNlV0yMbpjZcGf4fnsy6Lqu1edDs4uOrnpPDMbKicVO7fEtjGLQKvfTAoAE5jDytJYM3W-E2zr5Z_KzMdJCPMxN4VZ-gk7conpudNvYCOjyn414c3ry0QIZgxg-_1ivhpd-dGoQkF8f-tW9u3p5MhHHy0U8S1yOxBgoDkhIb3cg0MNS7rZMceR3-2Mu23z7Dgy1_W4joFzep_cs54JPTQ0e0AGqn5I7kys9uIR-bZhG9Vso8g2umEbrWq6YRs1bHtPD2u65hptSupwjVqu0bahlmtUUuQa1Vx7TM4-fjg9Oma2YAfLOfdapjw15gXY1F5eZDwoJbgfZQKNpSozMOSxzrniMD0IkRXwRlURh1lRBhHPytjLOH9C9uqmVs8IBbNWJbjrq3yOIYgs98G1Db1ShRxeVD4k3vqVprnNZo9FVS5T8GoRhRRRSAGFFFBIEYUhedvf8tWkcvlb59drnFKYcHEXTdaq6VYp7syLCJYx6PPU4NYPx0UyToQnhiTeQrTvgMnct3-pq4VO6r5m2f7Nb31O7m7-bC_IXrvs1EswmdvslabsbzsTzvg
linkProvider National Library of Medicine
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Predicting+lymph+node+metastasis+in+colorectal+cancer%3A+An+analysis+of+influencing+factors+to+develop+a+risk+model&rft.jtitle=World+journal+of+gastrointestinal+surgery&rft.au=Lei%2C+Yun-Peng&rft.au=Song%2C+Qing-Zhi&rft.au=Liu%2C+Shuang&rft.au=Xie%2C+Ji-Yan&rft.date=2023-10-27&rft.pub=Baishideng+Publishing+Group+Inc&rft.eissn=1948-9366&rft.volume=15&rft.issue=10&rft.spage=2234&rft.epage=2246&rft_id=info:doi/10.4240%2Fwjgs.v15.i10.2234&rft.externalDocID=PMC10642478
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1948-9366&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1948-9366&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1948-9366&client=summon