Order sets are a critical component in hospital information systems and expected to reduce physical and cognitive physician workload, substantially. Order sets represent clustered order items such as medications prescribed at hospital admission which are administered to patients during their hospital stay. In this paper, we develop a mathematical program and a Tabu Search (TS) based heuristic solution procedure to generate order sets, assign patients' order items to order sets or, if workload cannot be minimized by using order sets, items are selected individually. We show theoretical properties of the problem when physical or cognitive workload reduction are pursued. As a consequence, the model can be simplified for the minimization of physical instead of cognitive workload. In a case study using order data on three moderate clinical conditions from a major pediatric hospital, we compare the hospital's current solution with the solutions of the optimization approaches on a variety of performance metrics and level of detail. Our computational results reveal that the MIP-based physical and cognitive workload models cannot solve test instances to optimality within a 10 minute time limit. However, our TS heuristic improves the MIP-based solution of the physical workload model by 3.6% to 44.6%. In terms of the cognitive workload objective, the MIP is more competitive while, overall, the current order set configuration of the hospital can be improved, substantially. We finally develop a graphical user interface which allows practitioners to compare current order set usage with order set optimization.
Current 2019 2018 2017 2016 2015 2014 2013 2012 2011 2010 2009 2008 2007 2006 2005 2004 2003 2002 2001 2000 1999 1998 1997 1996
