Thesis (Server

 Library locked


Doctoral dissertation | @PhdThesis{BogojeskaPhD2011, ... | Doktorarbeit

Bogojeska, Jasmina

Statistical Learning Methods for Bias-aware {HIV} Therapy Screening

Universität des Saarlandes, December, 2011, 135 pages
Universität des Saarlandes

The human immunodeficiency virus (HIV) is the causative agent of the acquired immunodeficiency syndrome (AIDS) which claimed nearly $30$ million lives and is arguably among the worst plagues in human history. With no cure or vaccine in sight, HIV patients are treated by administration of combinations of antiretroviral drugs. The very large number of such combinations makes the manual search for an effective therapy practically impossible, especially in advanced stages of the disease. Therapy selection can be supported by statistical methods that predict the outcomes of candidate therapies. However, these methods are based on clinical data sets that are biased in many ways. The main sources of bias are the evolving trends of treating HIV patients, the sparse, uneven therapy representation, the different treatment backgrounds of the clinical samples and the differing abundances of the various therapy-experience levels.

In this thesis we focus on the problem of devising bias-aware statistical learning methods for HIV therapy screening -- predicting the effectiveness of HIV combination therapies. For this purpose we develop five novel approaches that when predicting outcomes of HIV therapies address the aforementioned biases in the clinical data sets. Three of the approaches aim for good prediction performance for every drug combination independent of its abundance in the HIV clinical data set. To achieve this, they balance the sparse and uneven therapy representation by using different routes of sharing common knowledge among related therapies. The remaining two approaches additionally account for the bias originating from the differing treatment histories of the samples making up the HIV clinical data sets. For this purpose, both methods predict the response of an HIV combination therapy by taking not only the most recent (target) therapy but also available information from preceding therapies into account. In this way they provide good predictions for advanced patients in mid to late stages of HIV treatment, and for rare drug combinations.

All our methods use the time-oriented evaluation scenario, where models are trained on data from the less recent past while their performance is evaluated on data from the more recent past. This is the approach we adopt to account for the evolving treatment trends in the HIV clinical practice and thus offer a realistic model assessment.

HIV therapy creening, machine learning, data analysis
Prof. Dr. Dr. Thomas Lengauer
Prof. Dr. Bernt Schiele
Max-Planck-Institut für Informatik
Computational Biology and Applied Algorithmics
MPII WWW Server, MPII FTP Server, MPG publications list, university publications list, working group publication list, Fachbeirat, VG Wort

BibTeX Entry:
AUTHOR = {Bogojeska, Jasmina},
TITLE = {Statistical Learning Methods for Bias-aware {HIV} Therapy Screening},
PUBLISHER = {Universität des Saarlandes},
SCHOOL = {Universit{\"a}t des Saarlandes},
YEAR = {2011},
TYPE = {Doctoral dissertation}
PAGES = {135},
ADDRESS = {Saarbr{\"u}cken},
MONTH = {December},

Entry last modified by Anja Becker, 03/20/2012
Hide details for Edit History (please click the blue arrow to see the details)Edit History (please click the blue arrow to see the details)

12/29/2011 03:35:31 PM
Anja Becker
Stephanie Müller
Jasmina Bogojeska
Jasmina Bogojeska
Edit Dates
20.03.2012 12:05:23
10.02.2012 11:57:24
01/10/2012 06:44:37 PM
12/29/2011 03:35:31 PM