Artificial intelligence assists surgeons' decision-making of temporary ileostomy in patients with rectal cancer who have received anterior resection. Issue 2 (February 2023)

• Record Type: Journal Article
• Authors: Shao, Shengli; Zhao, Yufeng; Lu, Qiyi; Liu, Lu; Mu, Lei; Qin, Jichao
• Is Part Of: European journal of surgical oncology. Volume 49:Issue 2(2023)
• Page Start: 433
• Page End: 439
• Publication Date: 2023-02
• Subjects: Artificial intelligence -- Temporary ileostomy -- Rectal cancer -- Anastomotic leakage; Oncology -- Periodicals; Cancer -- Surgery -- Periodicals; Medical Oncology -- Periodicals; Neoplasms -- surgery -- Periodicals; Cancer -- Chirurgie -- Périodiques; Cancérologie -- Périodiques; Oncologie; Chirurgie (geneeskunde); Electronic journals; Electronic journals -- Sciences; Electronic journals -- Medicine; Electronic journals; 616.994059005
• DOI: 10.1016/j.ejso.2022.09.020
• Languages: English
• ISSNs: 0748-7983

Abstract

Abstract: Background: Due to the difficult evaluation of the risk of anastomotic leakage (AL) after rectal cancer resection, the decision to perform a temporary ileostomy is not easily distinguishable. The aim of the present study was to develop an artificial intelligence (AI) model for identifying the risk of AL to assist surgeons in the selective implementation of a temporary ileostomy. Materials and methods: The data from 2240 patients with rectal cancer who received anterior resection were collected, and these patients were divided into one training and two test cohorts. Five AI algorithms, such as support vector machine (SVM), logistic regression (LR), Naive Bayes (NB), stochastic gradient descent (SGD) and random forest (RF) were employed to develop predictive models using clinical variables and were assessed using the two test cohorts. Results: The SVM model indicated good discernment of AL, and might have increased the implementation of temporary ileostomy in patients with AL in the training cohort (p < 0.001). Following the assessment of the two test cohorts, the SVM model could identify AL in a favorable manner, which performed with positive predictive values of 0.150 (0.091–0.234) and 0.151 (0.091–0.237), and negative predictive values of 0.977 (0.958–0.988) and 0.986 (0.969–0.994), respectively. It is important to note that the implementation of temporary ileostomy in patients without AL would have been significantly reduced (p < 0.001) and which would have been significantly increased in patients with AL (p < 0.05). Conclusion: The model ( https://alrisk.21cloudbox.com/ ) indicated good discernment of AL, which may be used to assist the surgeon's decision-making of performing temporary ileostomy.