Date of Degree
PhD (Doctor of Philosophy)
First Committee Member
Second Committee Member
Third Committee Member
Fourth Committee Member
Healthcare associated infections are a considerable burden to the health care system. The affected patients have their prognosis worsened and demand more resources from hospitals. Furthermore, the bacteria causing these infections are becoming increasingly resistant to antibiotics while also becoming more deadly and contagious. Contributing with knowledge for stopping these infections is, therefore, important.
This thesis reports on two projects centered on data collected at the University of Iowa Hospital and Clinics. The first project consisted in analyzing data collected by sensors that reported the location and hand washing behavior of health care workers. After extracting meaning from these radio signals, I studied two socially and epidemiologically relevant tasks: the inference of contact networks, which can be used to study the spread of infections in the hospital, and the study of associations between social pressure and hand washing, learning that effectively workers in proximity to others wash their hands more, but also that not all workers are as influential.
In the second project, I developed a data mining method for analyzing medical records aimed at tackling the problems of class imbalance and high dimensionality, and applied it to predicting Clostridium Difficile infection. The learnt models performed better than the state of the art and even improved prediction as the onset of symptoms approached. The main contribution, however, was in the information discovered: certain events in certain orders increased the risk of developing the infection, suggesting that reversing these orders could improve prognosis.
Every day, patients get admitted to hospitals for medical attention, but sometimes they get something else: a bacterial infection. As a result, the affected patients become less healthy and require more resources from the hospital. Furthermore, the bacteria causing these infections are becoming increasingly resistant to antibiotics while also becoming deadlier, more contagious, and increasingly harder to kill, making most prevention efforts fall short. I analyzed data collected at the University of Iowa Hospital and Clinics to discover knowledge that can help health care workers understand and contain these infections. More precisely, I used computational methods for discovering information that would be difficult to elucidate otherwise. I report two projects in this thesis. In the first, I analyzed data collected through a network of wireless sensors on movement and hygienic habits of workers in a hospital unit. I learned information for building "contact networks", which can help study the spread of infections, and found evidence that workers wash their hands more when coworkers are nearby. In the second project, I developed a method for analyzing medical records for predicting whether patients will develop the infection caused by the Clostridium Difficile bacterium, while also learning which clinical events (for example, operations, prescriptions) put patients at risk. I discovered that some events increase risk if they occur in a specific order, and that high risk patients can be identified on admission.
publicabstract, Computational Epidemiology, Data Mining, Electronic Medical Records, Wireless Sensor Networks
xii, 94 pages
Includes bibliographical references (pages 79-94).
Copyright 2015 Mauricio Nivaldo Andres Monsalve