Combined Application of Inflammation-related Biomarkers to Predict Postoperative Complications of Rectal Cancer Patients: a Retrospective Study by Machine Learning Analysis

Overview

Journal Langenbecks Arch Surg

Specialty General Surgery

Date 2023 Oct 13

PMID 37831218

Authors

Kunyue Wang

Youyuan Tang

Feng Zhang

Xingpo Guo

Ling Gao

Affiliations

Soon will be listed here.

Abstract

Background: Postoperative complications in patients of rectal cancer pose challenges to postoperative recovery. Accurately predicting these complications is crucial for developing effective treatment plans for patients.

Methods: In this retrospective study, 493 patients with rectal cancer who underwent radical resection between January 2020 and December 2021 were examined. We evaluated logistic regression, support vector machines, regression trees, and random forests to predict the incidence of postoperative complications in patients and evaluate the performance of the model. The results will be analyzed to make recommendations for reducing complications.

Results: Among the four machine learning models, random forest demonstrated the highest results. The performance of this model was showed with an AUC of 0.880 (95% CI 0.807-0.949), an accuracy of 88.0% (95% CI 0.815-0.929), a sensitivity of 96.6%, and a specificity of 45.8%. Notably, factors such as inflammation related prognostic index, prognostic nutritional index, tumor location, and T stage were found to significantly increase the probability of postoperative complications.

Conclusion: Our study provided evidence that machine learning models can effectively evaluate early postoperative complications of the patients after surgery.

Citing Articles

Significance of the geriatric nutritional risk index and neutrophil-to-lymphocyte ratio as prognostic indicators in older patients with gastric cancer: a retrospective cohort study.

Miyamoto H, Toyokawa T, Ishidate T, Kuroda K, Miki Y, Yoshii M BMC Cancer. 2024; 24(1):1396.

PMID: 39538153 PMC: 11562485. DOI: 10.1186/s12885-024-13158-w.

References

Sung H, Ferlay J, Siegel R, Laversanne M, Soerjomataram I, Jemal A . Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries. CA Cancer J Clin. 2021; 71(3):209-249. DOI: 10.3322/caac.21660. View

van der Sijp M, Bastiaannet E, Mesker W, van der Geest L, Breugom A, Steup W . Differences between colon and rectal cancer in complications, short-term survival and recurrences. Int J Colorectal Dis. 2016; 31(10):1683-91. PMC: 5031780. DOI: 10.1007/s00384-016-2633-3. View

Degiuli M, Elmore U, De Luca R, De Nardi P, Tomatis M, Biondi A . Risk factors for anastomotic leakage after anterior resection for rectal cancer (RALAR study): A nationwide retrospective study of the Italian Society of Surgical Oncology Colorectal Cancer Network Collaborative Group. Colorectal Dis. 2021; 24(3):264-276. PMC: 9300066. DOI: 10.1111/codi.15997. View

Zhou S, Zhou H, Zheng Z, Liang J, Zhou Z, Wang X . Predictive risk factors for anastomotic leakage after anterior resection of rectal cancer in elderly patients over 80 years old: an analysis of 288 consecutive patients. World J Surg Oncol. 2019; 17(1):112. PMC: 6599342. DOI: 10.1186/s12957-019-1655-z. View

Makuuchi R, Irino T, Tanizawa Y, Bando E, Kawamura T, Terashima M . Esophagojejunal anastomotic leakage following gastrectomy for gastric cancer. Surg Today. 2018; 49(3):187-196. DOI: 10.1007/s00595-018-1726-8. View

McSorley S, Black D, Horgan P, McMillan D . The relationship between tumour stage, systemic inflammation, body composition and survival in patients with colorectal cancer. Clin Nutr. 2017; 37(4):1279-1285. DOI: 10.1016/j.clnu.2017.05.017. View

Larson D, Abd El Aziz M, Perry W, DAngelo A, Behm K, Mathis K . Additional Value of Preoperative Albumin for Surgical Risk Stratification among Colorectal Cancer Patients. Ann Nutr Metab. 2021; 76(6):422-430. DOI: 10.1159/000514058. View

Wang F, He W, Jiang C, Guo G, Ke B, Dai Q . Prognostic value of inflammation-based scores in patients receiving radical resection for colorectal cancer. BMC Cancer. 2018; 18(1):1102. PMC: 6233268. DOI: 10.1186/s12885-018-4842-3. View

Baker S, Monlezun D, Ambroze Jr W, Margolin D . Anastomotic Leak is Increased With Infection After Colectomy: Machine Learning-Augmented Propensity Score Modified Analysis of 46 735 Patients. Am Surg. 2020; 88(1):74-82. DOI: 10.1177/0003134820973720. View

10.

van der Pas M, Haglind E, Cuesta M, Furst A, Lacy A, Hop W . Laparoscopic versus open surgery for rectal cancer (COLOR II): short-term outcomes of a randomised, phase 3 trial. Lancet Oncol. 2013; 14(3):210-8. DOI: 10.1016/S1470-2045(13)70016-0. View

11.

Dindo D, Demartines N, Clavien P . Classification of surgical complications: a new proposal with evaluation in a cohort of 6336 patients and results of a survey. Ann Surg. 2004; 240(2):205-13. PMC: 1360123. DOI: 10.1097/01.sla.0000133083.54934.ae. View

12.

Stoltzfus J . Logistic regression: a brief primer. Acad Emerg Med. 2011; 18(10):1099-104. DOI: 10.1111/j.1553-2712.2011.01185.x. View

13.

de Klaver W, Wisse P, van Wifferen F, Bosch L, Jimenez C, van der Hulst R . Clinical Validation of a Multitarget Fecal Immunochemical Test for Colorectal Cancer Screening : A Diagnostic Test Accuracy Study. Ann Intern Med. 2021; 174(9):1224-1231. DOI: 10.7326/M20-8270. View

14.

Li T, Huang J, Lei P, Yang X, Chen Z, Chen P . A novel nomogram for anastomotic leakage after surgery for rectal cancer: a retrospective study. PeerJ. 2022; 10:e14437. PMC: 9744139. DOI: 10.7717/peerj.14437. View

15.

Chan J, Diakos C, Chan D, Engel A, Pavlakis N, Gill A . A Longitudinal Investigation of Inflammatory Markers in Colorectal Cancer Patients Perioperatively Demonstrates Benefit in Serial Remeasurement. Ann Surg. 2017; 267(6):1119-1125. DOI: 10.1097/SLA.0000000000002251. View

16.

Watanabe J, Otani S, Sakamoto T, Arai Y, Hanaki T, Amisaki M . Prognostic indicators based on inflammatory and nutritional factors after pancreaticoduodenectomy for pancreatic cancer. Surg Today. 2016; 46(11):1258-67. DOI: 10.1007/s00595-016-1308-6. View

17.

Peng L, Peng C, Yang F, Wang J, Zuo W, Cheng C . Machine learning approach for the prediction of 30-day mortality in patients with sepsis-associated encephalopathy. BMC Med Res Methodol. 2022; 22(1):183. PMC: 9252033. DOI: 10.1186/s12874-022-01664-z. View

18.

Asadi S, Roshan S, Kattan M . Random forest swarm optimization-based for heart diseases diagnosis. J Biomed Inform. 2021; 115:103690. DOI: 10.1016/j.jbi.2021.103690. View

19.

Kazi M, Gori J, Sasi S, Srivastava N, Khan A, Mukherjee S . Prognostic Nutritional Index Prior to Rectal Cancer Resection Predicts Overall Survival. Nutr Cancer. 2022; 74(9):3228-3235. DOI: 10.1080/01635581.2022.2072906. View

20.

Xia L, Li W, Zhai J, Yan C, Chen J, Yang H . Significance of neutrophil-to-lymphocyte ratio, platelet-to-lymphocyte ratio, lymphocyte-to-monocyte ratio and prognostic nutritional index for predicting clinical outcomes in T1-2 rectal cancer. BMC Cancer. 2020; 20(1):208. PMC: 7066735. DOI: 10.1186/s12885-020-6698-6. View