Predicting Surgical Complications in Colonic Neoplasia Patients Using Machine Learning

A study investigated the utility of machine learning algorithms in predicting complications for patients undergoing colectomy for colonic neoplasia. The three machine learning models successfully identified patients who developed complications, with the neural network scoring highest in predicting anastomotic leak, prolonged length of stay, and inpatient mortality. Although differences in model performance were largely insignificant, these machine learning tools show great promise in assisting surgeons with perioperative risk-stratification and improving postoperative outcomes.