Operationalizing Machine Learning and Discrete Event Simulation Models to Improve Clinic Efficiency

项目总结 医生经常报告说，他们感到有压力去看更多的病人，以维持收入，同时减少可用资金 是照顾病人的时间了。有效调度患者的系统数据驱动方法非常重要，因为 医生们被迫去看越来越多的病人。我们提出了实时预测模型 患者就诊的时间长短、错过预约的可能性以及患者等待时间将有助于计划 患者效率更高。诊所将能够安全地超额预订，以避免因错过预约而出现空位， 为安排紧急附加患者提供指导，并在出现以下情况时为患者提供等待时间估计 就是延误。我们将开发方法来实时访问这些预测所需的数据，并 建议将这些模型集成到工作流中，以提高调度准确性、患者等待时间、 和患者满意度，同时还增加了诊疗量。

PROJECT SUMMARY Physicians often report feeling pressured to see more patients to maintain revenue, while having less available time for patient care. Systematic data-driven methods for efficiently scheduling patients are important as physicians are pressured to see more and more patients. We propose that real time prediction models of patient visit lengths, the likelihood of missing appointments, and of patient wait times will help schedule patients more efficiently. Clinics will be able to safely overbook to avoid empty slots from missed appointments, have guidance for scheduling urgent add-on patients, and provide wait time estimates for patients when there are delays. We will develop methodologies for accessing data needed for these predictions in real time and propose that the integration of these models into workflows will improve scheduling accuracy, patient wait time, and patient satisfaction, while also increasing clinic volumes.