University of Twente Student Theses

Login

Predicting the length of stay of day care patients of Medisch Spectrum Twent

Gietema, N (2014) Predicting the length of stay of day care patients of Medisch Spectrum Twent.

[img]
Preview
PDF
4MB
Abstract:Medisch Spectrum Twente hospital will gradually decrease its general bed capacity in the next few years. A substantial reduction is expected for the day care and short stay ward. During daytime the average bed utilization of this ward is around 65 percent. By increasing this utilization the required bed capacity decreases, which could be realized by using a more efficient surgical scheduling method. Therefore, the post-surgery length of stay on the ward must be predictable. Because this is currently not the case, the goal of this project is to formulate a prediction model. We use an univariate general linear model. Surgery type, surgery time, patient’s gender and the number of surgeries performed per surgeon were found as significant in predicting the post-surgery length of stay. The fraction of explained variance is 0.212. The model predicts average values of the post-surgery length of stay on the ward well, but overestimates for values less than two and underestimate for values greater than four. Although it is difficult to estimate, we expect a bed capacity reduction of 48 percent when this approach is implemented, resulting in 17 beds needed instead of the current 33 at the day care and short stay ward.
Item Type:Essay (Bachelor)
Faculty:BMS: Behavioural, Management and Social Sciences
Subject:01 general works
Programme:Industrial Engineering and Management BSc (56994)
Link to this item:http://purl.utwente.nl/essays/64468
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page