@phdthesis{BogojeskaPhD2011, TITLE = {Statistical Learning Methods for Bias-aware {HIV} Therapy Screening}, AUTHOR = {Bogojeska, Jasmina}, LANGUAGE = {eng}, URL = {http://scidok.sulb.uni-saarland.de/volltexte/2012/4547/; urn:nbn:de:bsz:291-scidok-45475}, DOI = {10.22028/D291-26255}, LOCALID = {Local-ID: C125673F004B2D7B-B354E6F7403CA747C1257975005027FD-BogojeskaPhD2011}, SCHOOL = {Universit{\"a}t des Saarlandes}, ADDRESS = {Saarbr{\"u}cken}, YEAR = {2011}, DATE = {2011}, ABSTRACT = {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.}, }