MPI-INF Logo
Publications

Server    domino.mpi-inf.mpg.de

Proceedings Article, Paper
@InProceedings
Beitrag in Tagungsband, Workshop

Author, Editor
Author(s):
Bogojeska, Jasmina
Stöckel, Daniel
Zazzi, Maurizio
Kaiser, Rolf
Incardona, Francesca
Rosen-Zvi, Michal
Lengauer, Thomas		dblp
dblp
dblp
dblp
dblp
dblp
dblp
Not MPG Author(s):
Stöckel, Daniel
Zazzi, Maurizio
Kaiser, Rolf
Incardona, Francesca
Rosen-Zvi, Michal
Editor(s):
Lawrence, Neil
Girolami, Mark		dblp
dblp
Not MPII Editor(s):
Lawrence, Neil
Girolami, Mark
BibTeX cite key*:
Bogojeska2012b
Title, Booktitle
Title*:
History-alignment models for bias-aware prediction of virological response to HIV combination therapy
Booktitle*:
Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics (AISTATS 2012)
Event, URLs
Conference URL::
http://www.cs.utexas.edu/~aistats/aistats2012/
Downloading URL:
http://jmlr.csail.mit.edu/proceedings/papers/v22/bogojeska12/bogojeska12.pdf
Event Address*:
La Palma, Canary Islands, Spain
Language:
English
Event Date*
(no longer used):
Organization:
Event Start Date:
21 April 2012
Event End Date:
23 April 2012
Publisher
Name*:
Journal of Machine Learning Research
URL:
http://jmlr.csail.mit.edu/
Address*:
Brookline, USA
Type:
Vol, No, Year, pp.
Series:
JMLR Workshop and Conference Proceedings
Volume:
22
Number:
Month:
April
Pages:
118-126
Year*:
2012
VG Wort Pages:
ISBN/ISSN:
Sequence Number:
DOI:
Note, Abstract, ©
(LaTeX) Abstract:
The relevant HIV data sets used for predicting
outcomes of HIV combination therapies
suffer from several problems: different treatment
backgrounds of the samples, uneven
representation with respect to the level of
therapy experience and uneven therapy representation.
Also, they comprise only viral
strain(s) that can be detected in the patients’
blood serum. The approach presented in this
paper tackles these issues by considering not
only the most recent therapies but also the
different treatment backgrounds of the samples
making up the clinical data sets when
predicting the outcomes of HIV therapies.
For this purpose, we introduce a similarity measure for sequences of therapies and use
it for training separate linear models for predicting
therapy outcome for each target sample.
Compared to the most commonly used
approach that encodes all available treatment
information only by specific input features
our approach has the advantage of delivering
significantly more accurate predictions
for therapy-experienced patients and for rare
therapies. Additionally, the sample-specific
models are more interpretable which is very
important in medical applications.
Download
Access Level:
Internal

Correlation
MPG Unit:
Max-Planck-Institut für Informatik
MPG Subunit:
Computational Biology and Applied Algorithmics
Appearance:
MPII WWW Server, MPII FTP Server, MPG publications list, university publications list, working group publication list, Fachbeirat, VG Wort



BibTeX Entry:

@INPROCEEDINGS{Bogojeska2012b,
AUTHOR = {Bogojeska, Jasmina and St{\"o}ckel, Daniel and Zazzi, Maurizio and Kaiser, Rolf and Incardona, Francesca and Rosen-Zvi, Michal and Lengauer, Thomas},
 EDITOR = {Lawrence, Neil and Girolami, Mark},
 TITLE = {History-alignment models for bias-aware prediction of virological response to {HIV} combination therapy},
 BOOKTITLE = {Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics (AISTATS 2012)},
 PUBLISHER = {Journal of Machine Learning Research},
 YEAR = {2012},
 VOLUME = {22},
 PAGES = {118--126},
 SERIES = {JMLR Workshop and Conference Proceedings},
 ADDRESS = {La Palma, Canary Islands, Spain},
 MONTH = {April},
 ISBN = {1532-4435},
}

Entry last modified by Uwe Brahm, 02/15/2013
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)

Editor(s)
[Library]		Created
12/12/2012 13:51:29
Revisions
4.
3.
2.
1.
0.		Editor(s)
Uwe Brahm
Anja Becker
Ruth Schneppen-Christmann
Ruth Schneppen-Christmann
Ruth Schneppen-Christmann		Edit Dates
02/15/2013 04:14:27 PM
11.02.2013 14:47:20
10.01.2013 11:43:54
10.01.2013 11:09:13
12/12/2012 01:51:29 PM