Understanding nurses' preferences to improve scheduling optimization models for chemotherapy clinics

Abstract: Intelligently scheduling patients in chemotherapy clinics is an important factor in improving the clinic's workflow. By using an integer programming model, feasible schedules can be easily determined in short periods of time. Also these schedules ensure that all required resources are available at the required time. But, the schedules produced by the optimization model may not reflect what nurses perceive as optimal schedules, since the weight factors are all initially determined by researchers. First, it is important to understand what nurses consider as a good schedule, and this has to be done before it is possible to create optimal schedules for the nurses to follow. By using an inverse optimization model nurses' preferences can be determined. With the new parameters they can be used in the forward problem to create better schedules that satisfy the nurses as well