Cardoen, Brecht; Beliën, Jeroen; Vanhoucke, Mario (2015)
A custom pack combines medical disposable items into a single sterile package that is used for surgical procedures. Although custom packs are gaining importance in hospitals due to their potential benefits in reducing surgery setup times, little is known on methodologies to configure them, especially if the number of medical items, procedure types and surgeons is large. In this paper, we propose a mathematical programming approach to guide hospitals in developing or reconfiguring their custom packs. In particular, we are interested in minimising points of touch, which we define as a measure for physical contact between staff and medical materials. Starting from an integer non-linear programming model, we develop both an exact linear programming (LP) solution approach and an LP-based heuristic. Next, we also describe a simulated annealing approach to benchmark the mathematical programming methods. A computational experiment, based on real data of a medium-sized Belgian hospital, compares the optimised results with the performance of the hospital's current configuration settings and indicates how to improve future usage. Next to this base case, we introduce scenarios in which we examine to what extent the results are sensitive for waste, i.e. adding more items to the custom pack than is technically required for some of the custom pack's procedures, since this can increase its applicability towards other procedures. We point at some interesting insights that can be taken up by the hospital management to guide the configuration and accompanying negotiation processes.
Support Vector Machines are methods that stem from Artificial Intelligence and attempt to learn the relation between data inputs and one or multiple output values. However, the application of these methods has barely been explored in a project control context. In this paper, a forecasting analysis is presented that compares the proposed Support Vector Regression model with the best performing Earned Value and Earned Schedule methods. The parameters of the SVM are tuned using a cross-validation and grid search procedure, after which a large computational experiment is conducted. The results show that the Support Vector Machine Regression outperforms the currently available forecasting methods. Additionally, a robustness experiment has been set up to investigate the performance of the proposed method when the discrepancy between training and test set becomes larger.
The export option will allow you to export the current search results of the entered query to a file. Different
formats are available for download. To export the items, click on the button corresponding with the preferred download format.
By default, clicking on the export buttons will result in a download of the allowed maximum amount of items.
To select a subset of the search results, click "Selective Export" button and make a selection of the items you want to export.
The amount of items that can be exported at once is similarly restricted as the full export.
After making a selection, click one of the export format buttons. The amount of items that will be exported is indicated in the bubble next to export format.