<p>Predicting case complexity preoperatively for Mohs micrographic surgery (MMS) is challenging. Development of a scheduling tool to predict case complexity could contribute to appropriate triage of surgical cases. This paper aims to illustrate how a machine learning based algorithm can aid in improving dermatologic surgery scheduling. The University of California– San Francisco (UCSF) Mohs Preoperative Scheduling System (UMPreSS) is a machine learning based algorithm developed to predict surgical complexity for individual MMS cases. Following development and validation, a study phase was performed to analyze its effect on surgical day characteristics. The UMPreSS tool was applied in our scheduling workflow to limit each surgery day to 3 or less complex cases per day. Surgical day characteristics in a pre- and post-intervention phase were compared. In the post-intervention phase, there were fewer complex cases, tissue sections, and cases requiring advanced reconstruction techniques per clinic day. The intervention was also associated with decreased variability in the proportion of complex cases per day. UMPreSS is a validated machine learning based algorithm developed to predict surgical complexity, with the goal of implementation in the clinical setting to optimize surgical scheduling. This algorithm was implemented in a large academic Dermatologic surgery department and led to decreased variability in the proportion of complex cases per day, resulting in more consistent scheduling. With the growth of the presence of machine learning and artificial intelligence in medicine, this study showcases the utility and impact of a machine learning based algorithm within dermatologic surgery.</p>