Machine learning for prediction of postoperative complications after hepato-biliary and pancreatic surgery

Decision making in Hepatobiliary and Pancreatic Surgery is challenging, not least because of the significant complications that may occur following surgery and the complexity of interventions to treat them. Machine Learning (ML) relates to the use of computer derived algorithms and systems to enhance knowledge in order to facilitate decision making and could be of great benefit to surgical patients. ML could be employed pre- or perioperatively to shape treatment choices prospectively, or could be utilised in the post-hoc analysis of complications in order to inform future practice. ML could reduce errors by drawing attention to known risks of complications through supervised learning, and gain greater insights by identifying previously under-appreciated aspects of care through unsupervised learning. Accuracy, validity and integrity of data are of fundamental importance if predictive models generated by ML are to be successfully integrated into surgical practice. The choice of appropriate ML models and the interface between ML, traditional statistical methodologies and human expertise will also impact the potential to incorporate data science techniques into daily clinical practice.