Application of a risk-averse objective function for scheduling surgeries

Traditional objective functions for scheduling surgeries, such as maximising utilisation of operating rooms, maximising throughput of surgeries, or minimising cost, can lead to inequitable outcomes for patients in terms of the time waiting for their operation. Using a simple mixed integer program and historical data from a surgical centre we compare two objective functions (a risk neutral and a risk averse objective) intended to reduce the lateness of the latest-performed operations. Further, the effects of other model parameters on the surgical schedules are compared. By applying the model to a case study at a surgical centre, it is demonstrated that, with the appropriate values of the other model parameters, the risk neutral objective can achieve similar schedules to the risk averse objective, and results in problems that are easier to solve.