Document Type
Thesis
Date of Award
2018
Keywords
Communication and the arts, Applied sciences, Health and environmental sciences, Ensemble learning, Gynecological cancer, Surgical site infection
Degree Name
Master of Science (MS)
Department
Systems Science and Industrial Engineering
First Advisor
Dr. Mohammad T. Khasawneh
Subject Heading(s)
Communication and the arts; Applied sciences; Health and environmental sciences; Ensemble learning; Gynecological cancer; Surgical site infection; Engineering; Operations Research, Systems Engineering and Industrial Engineering
Abstract
Surgical site infections are costly to both patients and hospitals, increase patient mortality, and are the most common form of a hospital acquired infection. Gynecological cancer surgery patients are already at higher risk of developing an infection due to the suppression of their immune system. This research leverages popular data mining techniques to create a prediction model to identify high risk patients. Implemented techniques include logistic regression, naive Bayes, recursive partitioning and regression trees, random forest, feed forward neural network, k-nearest neighbor, and support vector machines with linear kernel. Weighted stacked generalization was implemented to improve upon the individual base level model’s performance. The chosen meta level classifiers were support vector machines with linear kernel, logistic regression, and k-nearest neighbor. The result is a model that identifies high-risk patients immediately following a surgical procedure with an AUC of 0.6864, accuracy of 0.6744, sensitivity of 0.7, and specificity of 0.6728.
Recommended Citation
McDonough, John R., "Utilizing data mining techniques and ensemble learning to predict development of surgical site infections in gynecologic cancer patients" (2018). Graduate Dissertations and Theses. 33.
https://orb.binghamton.edu/dissertation_and_theses/33
