The Role of Artificial Intelligence in Predicting and Preventing Anastomotic Leakage in Colorectal Surgery
DOI:
https://doi.org/10.14748/2z3tjb46Keywords:
colorectal cancer, anastomotic leakage, artificial intelligence, machine learning, deep learning, risk predictionAbstract
Introduction: Anastomotic leakage (AL) remains one of the most severe complications following colorectal surgery, leading to high morbidity, mortality, and impaired oncological outcomes.
Aim: The aim of this article is to evaluate the current role of artificial intelligence (AI) in predicting and preventing AL in patients undergoing colorectal cancer surgery.
Materials and Methods: A review of current literature focusing on the incidence, risk factors, and clinical impact of AL, alongside the application of AI-based models for risk prediction and intraoperative assessment has been conducted.
Results: Several machine learning (ML) and deep learning (DL) models have demonstrated superior accuracy compared to traditional scoring systems (e.g., anastomoticleak.com, ACS NSQIP, REAL Score). Predictive factors identified include nutritional deficits, visceral fat area, sarcopenia, tumor characteristics, and intraoperative parameters. Radiomic and AI-based models have shown promising potential in stratifying risk, guiding protective stoma creation, and supporting intraoperative decision-making through tools such as indocyanine green angiography, hyperspectral imaging, and semantic segmentation.
Conclusion: AI-driven predictive models outperform conventional scoring systems and represent a significant advancement in the management of colorectal cancer surgery. Integration of AI into clinical practice guidelines could enable individualized risk stratification, improve outcomes, and reduce the incidence of AL.
References
1. Sung H, Ferlay J, Siegel RL, et al. Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries. CA Cancer J Clin. 2021 May;71(3):209-49. doi: 10.3322/caac.21660.
2. Global Cancer Observatory. Global Cancer Observatory [Internet]. Iarc.fr. 2020. Available from: https://gco.iarc.fr/
3. McDermott FD, Heeney A, Kelly ME, et al. Systematic review of preoperative, intraoperative and postoperative risk factors for colorectal anastomotic leaks. Br J Surg. 2015 Apr;102(5):462-79. doi: 10.1002/bjs.9697.
4. Kang CY, Halabi WJ, Chaudhry OO, et al. Risk factors for anastomotic leakage after anterior resection for rectal cancer. JAMA Surg. 2013 Jan;148(1):65-71. doi: 10.1001/2013.jamasurg.2.
5. Hyman N, Manchester TL, Osler T, et al. Anastomotic leaks after intestinal anastomosis: it's later than you think. Ann Surg. 2007 Feb;245(2):254-8. doi: 10.1097/01.sla.0000225083.27182.85.
6. Arezzo A, Migliore M, Chiaro P, et al. The REAL (REctal Anastomotic Leak) score for prediction of anastomotic leak after rectal cancer surgery. Tech Coloproctol. 2019 Jul;23(7):649-63. doi: 10.1007/s10151-019-02028-4.
7. Esteva A, Robicquet A, Ramsundar B, et al. A guide to deep learning in healthcare. Nat Med. 2019 Jan;25(1):24-29. doi: 10.1038/s41591-018-0316-z.
8. Sammour T, Cohen L, Karunatillake AI, et al. Validation of an online risk calculator for the prediction of anastomotic leak after colon cancer surgery and preliminary exploration of artificial intelligence-based analytics. Tech Coloproctol. 2017 Nov;21(11):869-877. doi: 10.1007/s10151-017-1701-1.
9. Quero G, Mascagni P, Kolbinger FR, et al. Artificial Intelligence in Colorectal Cancer Surgery: Present and Future Perspectives. Cancers (Basel). 2022 Aug 4;14(15):3803. doi: 10.3390/cancers14153803.
10. Kumar S, Gupta R, Bhalerao A, et al. Artificial Intelligence in Surgical Gastroenterology: From Predictive Models to Intraoperative Guidance. Apollo Med. 2025. doi:10.1177/09760016251369605.
11. Nawrat Z. Introduction to AI-driven surgical robots. Art Int Surg. 2023;3:90-7. doi: 10.20517/ais.2023.14.
12. Elemento O, Leslie C, Lundin J, et al. Artificial intelligence in cancer research, diagnosis and therapy. Nat Rev Cancer. 2021 Dec;21(12):747-52. doi: 10.1038/s41568-021-00399-1.
13. Taher H, Grasso V, Tawfik S, et al. The challenges of deep learning in artificial intelligence and autonomous actions in surgery: a literature review. Art Int Surg. 2022;2:144-58. doi: 10.20517/ais.2022.11.
14. Lieffers JR, Bathe OF, Fassbender K, et al. Sarcopenia is associated with postoperative infection and delayed recovery from colorectal cancer resection surgery. Br J Cancer. 2012 Sep 4;107(6):931-6. doi: 10.1038/bjc.2012.350.
15. Mosquera C, Koutlas NJ, Edwards KC, et al. Impact of malnutrition on gastrointestinal surgical patients. J Surg Res. 2016 Sep;205(1):95-101. doi: 10.1016/j.jss.2016.05.030.
16. Xu H, Kong F. Malnutrition-Related Factors Increased the Risk of Anastomotic Leak for Rectal Cancer Patients Undergoing Surgery. Biomed Res Int. 2020 Apr 30;2020:5059670. doi: 10.1155/2020/5059670.
17. Zhao H, Liu G, Li Y, et al. Body fat ratio as a novel predictor of complications and survival after rectal cancer surgery. Front Nutr. 2024 Aug 9;11:1398807. doi: 10.3389/fnut.2024.1398807.
18. Henrique JR, Pereira RG, Ferreira RS, et al. Pilot study GLIM criteria for categorization of a malnutrition diagnosis of patients undergoing elective gastrointestinal operations: A pilot study of applicability and validation. Nutrition. 2020 Nov-Dec;79-80:110961. doi: 10.1016/j.nut.2020.110961.
19. Weimann A, Braga M, Carli F, et al. ESPEN practical guideline: Clinical nutrition in surgery. Clin Nutr. 2021 Jul;40(7):4745-4761. doi: 10.1016/j.clnu.2021.03.031.
20. Yamano T, Yoshimura M, Kobayashi M, et al. Malnutrition in rectal cancer patients receiving preoperative chemoradiotherapy is common and associated with treatment tolerability and anastomotic leakage. Int J Colorectal Dis. 2016 Apr;31(4):877-84. doi: 10.1007/s00384-016-2507-8.
21. Ishizawa T. “Bon mariage” of artificial intelligence and intraoperative fluorescence imaging for safer surgery. Art Int Surg. 2023;3:163-5. doi: 10.20517/ais.2023.25.
22. Park SH, Park HM, Baek KR, et al. Artificial intelligence based real-time microcirculation analysis system for laparoscopic colorectal surgery. World J Gastroenterol. 2020 Nov 28;26(44):6945-62. doi: 10.3748/wjg.v26.i44.6945.
23. Fabbri N, Pesce A, Raimondi E, et al. Quantitative fluorescence angiography versus hyperspectral imaging to assess bowel ischemia: What is the best choice? Surgery. 2024 Nov;176(5):1550-1551. doi: 10.1016/j.surg.2024.06.030.
24. Ryu S, Goto K, Imaizumi Y, Nakabayashi Y. Laparoscopic Colorectal Surgery with Anatomical Recognition with Artificial Intelligence Assistance for Nerves and Dissection Layers. Ann Surg Oncol. 2024 Mar;31(3):1690-1691. doi: 10.1245/s10434-023-14633-7.
