Prediction of surgical operation durations using supervised machine learning techniques

Download

index.pdf

Date

2017

Author

Zabardast, Ehsan

Metadata

Show full item record

Item Usage Stats

209
views

65
downloads

There’s an ever increasing number of patients referred to healthcare facilities and hospitals. The healthcare facilities have two main options to deal with this situation. They have to either employ and acquire more resources or they should use the existing staff and resources more efficiently and effectively. The first option is not always feasible due to the fact that the healthcare facilities have limitations on both the staff they can employ and the resources they can acquire. Given the fact that these resources are expensive and extra resources provide diminishing returns, it is important to make the best use of resources available. Operating rooms and surgeons are the most expensive and scarce resources in hospitals; so it is crucial to optimize their performance and avoid under and over utilized operating rooms. The aim of this study is to employ supervised machine learning techniques and probabilistic graphical models to predict the duration of surgical operations using historical data. We have used a wide spectrum of different models ranging from regression methods, classification methods, and Bayesian Networks to predict the surgical operation durations. The models built based on Bayesian Networks, in general, produce more accurate results with lower errors. Naive Bayes, however, outperforms the other Bayesian-Network based models with an average accuracy of 66.9% and root mean square error of 998 seconds (16.6 minutes) from the true duration of the operation. Provided with accurate estimation of surgical operation durations, it is possible to build optimization models to utilize healthcare facility resources. This allows healthcare facilities’ managers to create tactical (medium term) plans and to increase efficient utilization of operating rooms and surgeons.

Subject Keywords

Surgery., Probabilities., Machine learning., Graphic methods.

URI

http://etd.lib.metu.edu.tr/upload/12621247/index.pdf
https://hdl.handle.net/11511/26913

Collections

Graduate School of Informatics, Thesis

Suggestions

OpenMETU
Core

Understanding the Role of Polymer Surface Nanoscale Topography on Inhibiting Bacteria Adhesion and Growth Liu, Luting; Ercan, Batur; Sun, Linlin; Ziemer, Katherine S.; Webster, Thomas J. (2016-01-01) Catheter-associated infections, most of which are caused by microbial biofilms, are still a serious issue in healthcare and are associated with significant morbidity, mortality, and excessive medical costs. Currently, the use of nanostructured materials, especially materials with nano featured topographies, which have more surface area, altered surface energy, enhanced select protein adsorption, and selectively increased desirable cell functions while simultaneously decreasing competitive cell functions, se...
IMPLEMENTATION OF A PATIENT EMPOWERMENT PLATFORM FOR INTEGRATED CARE Sarıgül, Bünyamin; Aydın Son, Yeşim; Laleci Ertürkmen, Gökçe Banu; Department of Bioinformatics (2022-2-11) While the number of chronic disease patients are increasing with the aging population, their complex treatments are a burden in today’s healthcare systems both economically and technically. Integrated care systems are one of the most powerful modern technologies to overcome these difficulties and provide more efficient treatments. Integrated care enables planning the chronic disease treatments in a sustainable and collaborative way for healthcare professionals from various disciplinaries. It also helps care...
Predictive Maintenance in Healthcare Services with Big Data Technologies Coban, Selin; Gökalp, Mert Onuralp; Gökalp, Ebru; Eren, Pekin Erhan; Koçyiğit, Altan (2018-11-22) Advances in medical technology is not sufficient alone to satisfy the growing and emerging needs such as improving quality of life, providing healthcare services tailored to each individual, ensuring efficient management of care and creating sustainable social healthcare. There is a potential for substantially enhancing healthcare services by integrating information technologies, social networking technologies, digitization and control of biomedical devices, and utilization of big data technologies as well ...
Towards an Evidence-Based Decision Support Tool for Management of Musculoskeletal Conditions Yet, Barbaros; Morrissey, Dylan (2018-01-01) Musculoskeletal (MSK) problems present an increasing burden for the healthcare sector, particularly in ageing populations. Advances in evidence are often slow to influence clinical decisions, suggesting decision support would be beneficial. We propose a Bayesian network (BN) for providing evidence-based decision support as it can explicitly represent domain knowledge as causal relations and allows both domain knowledge and clinical data to be combined to create a usable decision model. We make a preliminary...
Prevention of postoperative late kyphosis in Pott's disease by anterior decompression and intervertebral grafting Korkusuz, Feza; Islam, C; Korkusuz, Z (Springer Science and Business Media LLC, 1997-06-01) A total of 185 patients with Pott's disease were operated on between 1973 and 1992. Anterior decompression by preserving the pleura (extrapleural approach) was the preferred method in the thoracic spine. In the lumbar spine the approach was retroperitoneal, and interbody fusion was performed in both for the thoracic and the Lumbar regions. Anterior decompression and intervertebral grafting comprised the treatment. In five patients, internal fixation accompanied anterior decompression and intervertebral graf...

Citation Formats

E. Zabardast, “Prediction of surgical operation durations using supervised machine learning techniques,” M.S. - Master of Science, Middle East Technical University, 2017.