Setting patient and family expectations for postoperative outcomes is an important aspect of care, a cornerstone of which is accurate, personalized, and explainable risk estimation. Modern machine learning offers a plethora of models that can effectively capture the complex, nonlinear contributions of preoperative risk factors to the surgical patient's overall risk. However, most of these models produce risk estimates that are not interpretable, which compromises trust in these systems, renders them unaccountable, and limits their widespread adoption. Recent developments in machine learning have been successful at creating risk calculators that address this gap, producing explainable risk estimates without compromising accuracy. In this work, we describe how the state of the art in postoperative risk estimation addresses the shortcomings of older methods, and how they have been applied in a clinical setting. We conclude with a discussion of the potential of machine learning models to be systematically integrated in health care more broadly and future prospects beyond passive risk prediction.
Copyright © 2020 Elsevier Inc. All rights reserved.