Start Date
12-13-2015
Description
Order sets are a critical component in hospital information systems and expected to reduce physician workload, substantially. Order sets represent time interval-clustered order items (e.g. medications prescribed at hospital admission) which are administered to patients during their hospital stay. We develop a mathematical programming model, an exact and a heuristic solution procedure with the objective to minimize physician workload associated with prescribing order sets. In a case study using order data on Asthma patients with severe conditions from a major pediatric hospital, we compare the hospital’s current solution with our approaches on a variety of performance metrics. Our computational results reveal that using an interval decomposition approach substantially reduces computation times while our heuristic provides quick solutions and substantially reduces current physician workload. Our exact approach can reduce physician workload from 12% to 65% simply by allowing 1 to 5 order sets in each time interval, respectively.
Recommended Citation
Gartner, Daniel; Zhang, Yiye; and Padman, Rema, "Workload Reduction Through Usability Improvement of Hospital Information Systems - The Case of Order Set Optimization" (2015). ICIS 2015 Proceedings. 13.
https://aisel.aisnet.org/icis2015/proceedings/IShealth/13
Workload Reduction Through Usability Improvement of Hospital Information Systems - The Case of Order Set Optimization
Order sets are a critical component in hospital information systems and expected to reduce physician workload, substantially. Order sets represent time interval-clustered order items (e.g. medications prescribed at hospital admission) which are administered to patients during their hospital stay. We develop a mathematical programming model, an exact and a heuristic solution procedure with the objective to minimize physician workload associated with prescribing order sets. In a case study using order data on Asthma patients with severe conditions from a major pediatric hospital, we compare the hospital’s current solution with our approaches on a variety of performance metrics. Our computational results reveal that using an interval decomposition approach substantially reduces computation times while our heuristic provides quick solutions and substantially reduces current physician workload. Our exact approach can reduce physician workload from 12% to 65% simply by allowing 1 to 5 order sets in each time interval, respectively.