Patients undergoing anesthetic surgery are treated postoperatively in a Post-Anesthesia Care Unit (PACU). Traditional planning methods often fail to account for the complexity of patient data. This study aims to develop a machine learning (ML) tool to predict PACU-care times and to improve patient throughput. By integrating local-explanation models, we seek to gain clinical acceptance by providing insights into individual predictions. The project utilizes data from over 84,000 patients, including more than 170 variables.