Patients' satisfaction with an appointment system when they attempt to book a nonurgent appointment is affected by their ability to book with a doctor of choice and to book an appointment at a convenient time of day. For medical conditions requiring urgent attention, patients want quick access to a familiar physician. For such instances, it is important for clinics to have open slots that allow same-day (urgent) access. A major challenge when designing outpatient appointment systems is the difficulty of matching randomly arriving patients' booking requests with physicians' available slots in a manner that maximizes patients' satisfaction as well as clinics' revenues. What makes this problem difficult is that booking preferences are not tracked, may differ from one patient to another, and may change over time. This paper describes a framework for the design of the next generation of appointment systems that dynamically learn and update patients' preferences and use this information to improve booking decisions. Analytical results leading to a partial characterization of an optimal booking policy are presented. Examples show that heuristic decision rules, based on this characterization, perform well and reveal insights about trade-offs among a variety of performance metrics important to clinic managers.
- Appointment scheduling
- Health care
- Stochastic model applications