Abstract
Purpose
Anastomotic leaks greatly increase both morbidity and mortality amongst colorectal patients. Earlier detection of leaks leads to improved patient outcomes; however, diagnosis often proves difficult due to heterogeneous presentation and varied differential diagnosis. The purpose of the study was to create an artificial neural network (ANN) capable of accurately identifying patients at risk of developing a post-operative colorectal anastomotic leak.
Methods
A genetic ANN was trained and validated on a retrospective patient cohort. Two comparative groups were identified: those with anastomotic leaks confirmed at re-operation with a control group of patients with a post-operative delayed recovery, but in whom leak was excluded and no re-operation required.
Results
Seventy-six patients were identified: 20 confirmed leaks and 56 controls. No significant difference in the baseline features between leak and control groups in terms of age (leaks 65.9 years [SD 9.29] controls 58.3 years [SD 17.0)], P = 0.054). Utilising backwards variable selection, ANN maintained 19 input variables.
Internal validation of the ANN produced a sensitivity of 85.0 %, specificity of 82.1 %, and AUC of 0.89 for correct identification of clinical anastomotic leaks. Of the 20 confirmed leaks, the model correctly identified 17 and misclassified 10 control patients in the clinical leak category. External validation on 12 consecutive pilot prospective patients produced a specificity of 83.3 %.
Conclusions
ANNs can be created to accurately detect clinical anastomotic leaks in the early post-operative period using routinely available clinical data. Further prospective ANN testing is required to confirm generalisability. ANNs may provide useful real-world tools for improving patient safety and outcomes.
Similar content being viewed by others
References
Ortega-Deballon P, Radais F, Facy O et al (2010) C-reactive protein is an early predictor of septic complications after elective colorectal surgery. World J Surg 34:808–814
Snijders HS, Wouters M, Leersum NJ et al (2012) Meta-analysis of the risk for anastomotic leakage, the postoperative mortality caused by leakage in relation to the overall postoperative mortality. J Cancer Surg 38:1013–1019
Buchs NC, Gervaz P, Secic M, Bucher P, Mugnier-Konrad B, Morel P (2008) Incidence, consequences, and risk factors for anastomotic dehiscence after colorectal surgery: a prospective monocentric study. Int J Color Dis 23:265–270
Khan AA, Wheeler JM, Cunningham C, George B, Kettlewell M, Mortensen NJ (2008) The management and outcome of anastomotic leaks in colorectal surgery. Color Dis 10:587–592
Sauven P, Playforth MJ, Evans M, Pollock AV (1989) Early infective complications and late recurrent cancer in stapled colonic anastomoses. Dis Colon Rectum 32:33–35
Murray BW, Huerta S, Dineen S, Anthony T (2010) Surgical site infection in colorectal surgery: a review of the nonpharmacologic tools of prevention. J Am Coll Surg 211:812–822
Thornton M, Joshi H, Vimalachandran C et al (2011) Management and outcome of colorectal anastomotic leaks. Int J Color Dis 26:313–320
Hallbook O, Sjodahl R (1996) Anastomotic leakage and functional outcome after anterior resection of the rectum. Br J Surg 83:60–62
Alves A, Panis Y, Pocard M, Regimbeau JM, Valleur P (1999) Management of anastomotic leakage after nondiverted large bowel resection. J Am Coll Surg 189:554–559
Hyman N, Manchester TL, Osler T, Burns B, Cataldo PA (2007) Anastomotic leaks after intestinal anastomosis; it's later than you think. Ann Surg 245:254–258
Branagan G, Finnis D, Wessex Colorectal Cancer Audit Working G (2005) Prognosis after anastomotic leakage in colorectal surgery. Dis Colon Rectum 48:1021–1026
Paun BC, Cassie S, MacLean AR, Dixon E, Buie WD (2010) Postoperative complications following surgery for rectal cancer. Ann Surg 251:807–818
Jung SH, Yu CS, Choi PW et al (2008) Risk factors and oncologic impact of anastomotic leakage after rectal cancer surgery. Dis Colon Rectum 51:902–908
Bruce J, Krukowski ZH, Al-Khairy G, Russell EM, Park KG (2001) Systematic review of the definition and measurement of anastomotic leak after gastrointestinal surgery. Br J Surg 88:1157–1168
Rahbari NN, Weitz J, Hohenberger W et al (2010) Definition and grading of anastomotic leakage following anterior resection of the rectum: a proposal by the International Study Group of Rectal Cancer. Surgery 147:339–351
Dybowski R, Weller P, Chang R, Gant V (1996) Prediction of outcome in critically ill patients using artificial neural network synthesised by genetic algorithm. Lancet 347:1146–1150
McCulloch WS, Pitts WH (1943) A logical calculus of the ideas immanent in nervous activity. Bull Math Biophys 5:115–133
Dybowski R (2007) Clinical applications of artificial neural networks. Cambridge University Press, Cambridge
Adams K, Papagrigoriadis S (2013) Little consensus in either definition or diagnosis of a lower gastro-intestinal anastomotic leak amongst colorectal surgeons. Int J Color Dis 28:967–971
Mofidi R, Duff MD, Madhavan KK, Garden OJ, Parks RW (2007) Identification of severe acute pancreatitis using an artificial neural network. Surgery 141:59–66
MacKay GJ, Molloy RG, O'Dwyer PJ (2011) C-reactive protein as a predictor of postoperative infective complications following elective colorectal resection. Color Dis 13:583–587
Welsch T, Muller SA, Ulrich A et al (2007) C-reactive protein as early predictor for infectious postoperative complications in rectal surgery. Int J Color Dis 22:1499–1507
Karliczek A, Harlaar NJ, Zeebregts CJ, Wiggers T, Baas PC, van Dam GM (2009) Surgeons lack predictive accuracy for anastomotic leakage in gastrointestinal surgery. Int J Color Dis 24:569–576
Prabhudesai SG, Gould S, Rekhraj S, Tekkis PP, Glazer G, Ziprin P (2008) Artificial neural networks: useful aid in diagnosing acute appendicitis. World J Surg 32:305–309, discussion 310–1
Isariyawongse BK, Kattan MW (2012) Prediction tools in surgical oncology. Surg Oncol Clin N Am 21:439–447
Shi HY, Lee KT, Lee HH et al (2012) Comparison of artificial neural network and logistic regression models for predicting in-hospital mortality after primary liver cancer surgery. PLoS ONE [Electronic Resource] 7:e35781
Gohari MR, Biglarian A, Bakhshi E, Pourhoseingholi MA (2011) Use of an artificial neural network to determine prognostic factors in colorectal cancer patients. Asian Pac J Cancer Prev: Apjcp 12:1469–1472
Platt JJ, Ramanathan ML, Crosbie RA, Anderson JH, McKee RF, Horgan PG, McMillan DC (2012) C-reactive protein as a predictor of postoperative infective complications after curative resection in patients with colorectal cancer. Ann Surg Oncol 19:4168–4177
Garcia-Granero A, Frasson M, Flor-Lorente B, Blanco F, Puga R, Carratala A, Garcia-Granero E (2013) Procalcitonin and C-reactive protein as early predictors of anastomotic leak in colorectal surgery: a prospective observational study. Dis Colon Rectum 56:475–483
Role of funding source
There were no sources of outside funding to declare.
Conflicts of interest
There are no conflicts of interest to declare.
Authorship statement
Each of the listed authors has made a substantial contribution to the study concept and design, acquisition of data or analysis and interpretation of data. The listed authors have all approved the final version of the manuscript.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Adams, K., Papagrigoriadis, S. Creation of an effective colorectal anastomotic leak early detection tool using an artificial neural network. Int J Colorectal Dis 29, 437–443 (2014). https://doi.org/10.1007/s00384-013-1812-8
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00384-013-1812-8