Background: Anastomotic insufficiency (AI) is a relatively common but grave complication after colorectal surgery. This study aims to determine whether AI can be predicted from simple preoperative data using machine learning (ML) algorithms.
Methods: In this retrospective analysis, patients undergoing colorectal surgery with creation of a bowel anastomosis from the University Hospital of Basel were included. Data was split into a training set (80%) and a test set (20%). The group of patients with AI was oversampled to a ratio of 50:50 in the training set and missing values were imputed. Known predictors of AI were included as inputs: age, gender, BMI, smoking status, alcohol abuse, prior abdominal surgery, leukocytosis, haemoglobin and albumin levels, steroid use, the Charlson Comorbidity Index, the American Society of Anesthesiologists score, and renal function.
Results: Of the 593 included patients, 88 experienced AI. At internal validation on unseen patients from the test set, area under the curve (AUC) was 0.64 (95% confidence interval [CI]: 0.44-0.82), calibration slope was 0.21 (95% CI: -0.02-0.46) and calibration intercept was 0.06 (95% CI: 0.01-0.1). We observed a specificity of 0.76 (95% CI: 0.68-0.84), sensitivity of 0.36 (95% CI: 0.08-0.7), and accuracy of 0.72 (95% CI: 0.65-0.8).
Conclusion: By using 13 patient-related risk factors associated with AI, we demonstrate the feasibility of ML-based prediction of AI after colorectal surgery. Nevertheless, it is crucial to include multicenter data and higher sample sizes to develop a robust and generalizable model, which will subsequently allow for deployment of the algorithm in a web-based application.