Physician scheduling for continuity: An application in pediatric intensive care

Abstract

A physician schedule that maximizes continuity (i.e., reduces instances of patients being treated by multiple physicians) could improve the efficiency of handoffs-the transfer of patients from the care of one physician to another. We present a modeling and solution approach for assigning physicians to service and call shifts in the pediatric intensive care unit (PICU) at Children's Healthcare of Atlanta at Egleston (Children's). We developed the handoff continuity score (HCS) for measuring the continuity of a schedule. We combined the HCS with a mixed-integer programming model (MIP) with the objective of maximizing the HCS, while minimizing violations of physician preferences. For a 51-week horizon and a physician pool of 16 physicians, no feasible solution to this MIP is found within 48 hours using CPLEX 12.4. However, an iterative heuristic incorporating modified versions of the MIP produces a schedule (3.42 percent optimality gap) for the scheduling instance faced by Children's for this period. Our solution approach facilitates resource optimization, and automated scheduling requires less time than manually constructing such a schedule. We generated six-month schedules that were implemented in the PICU at Children's in 2011, 2012, and 2013. Such automated schedule construction allows for creation of schedules that maximize continuity.