History-alignment models for bias-aware prediction of virological response to HIV combination therapy

Jasmina Bogojeska, Daniel Stockel, Maurizio Zazzi, Rolf Kaiser, Francesca Incardona, Michal Rosen-Zvi, Thomas Lengauer
Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, PMLR 22:118-126, 2012.

Abstract

The relevant HIV data sets used for predicting outcomes of HIV combination therapies suffer from several problems: uneven therapy representation, different treatment backgrounds of the samples and uneven representation with respect to the level of therapy experience. 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.

Cite this Paper


BibTeX
@InProceedings{pmlr-v22-bogojeska12, title = {History-alignment models for bias-aware prediction of virological response to HIV combination therapy}, author = {Bogojeska, Jasmina and Stockel, Daniel and Zazzi, Maurizio and Kaiser, Rolf and Incardona, Francesca and Rosen-Zvi, Michal and Lengauer, Thomas}, booktitle = {Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics}, pages = {118--126}, year = {2012}, editor = {Lawrence, Neil D. and Girolami, Mark}, volume = {22}, series = {Proceedings of Machine Learning Research}, address = {La Palma, Canary Islands}, month = {21--23 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v22/bogojeska12/bogojeska12.pdf}, url = {https://proceedings.mlr.press/v22/bogojeska12.html}, abstract = {The relevant HIV data sets used for predicting outcomes of HIV combination therapies suffer from several problems: uneven therapy representation, different treatment backgrounds of the samples and uneven representation with respect to the level of therapy experience. 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.} }
Endnote
%0 Conference Paper %T History-alignment models for bias-aware prediction of virological response to HIV combination therapy %A Jasmina Bogojeska %A Daniel Stockel %A Maurizio Zazzi %A Rolf Kaiser %A Francesca Incardona %A Michal Rosen-Zvi %A Thomas Lengauer %B Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2012 %E Neil D. Lawrence %E Mark Girolami %F pmlr-v22-bogojeska12 %I PMLR %P 118--126 %U https://proceedings.mlr.press/v22/bogojeska12.html %V 22 %X The relevant HIV data sets used for predicting outcomes of HIV combination therapies suffer from several problems: uneven therapy representation, different treatment backgrounds of the samples and uneven representation with respect to the level of therapy experience. 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.
RIS
TY - CPAPER TI - History-alignment models for bias-aware prediction of virological response to HIV combination therapy AU - Jasmina Bogojeska AU - Daniel Stockel AU - Maurizio Zazzi AU - Rolf Kaiser AU - Francesca Incardona AU - Michal Rosen-Zvi AU - Thomas Lengauer BT - Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics DA - 2012/03/21 ED - Neil D. Lawrence ED - Mark Girolami ID - pmlr-v22-bogojeska12 PB - PMLR DP - Proceedings of Machine Learning Research VL - 22 SP - 118 EP - 126 L1 - http://proceedings.mlr.press/v22/bogojeska12/bogojeska12.pdf UR - https://proceedings.mlr.press/v22/bogojeska12.html AB - The relevant HIV data sets used for predicting outcomes of HIV combination therapies suffer from several problems: uneven therapy representation, different treatment backgrounds of the samples and uneven representation with respect to the level of therapy experience. 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. ER -
APA
Bogojeska, J., Stockel, D., Zazzi, M., Kaiser, R., Incardona, F., Rosen-Zvi, M. & Lengauer, T.. (2012). History-alignment models for bias-aware prediction of virological response to HIV combination therapy. Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 22:118-126 Available from https://proceedings.mlr.press/v22/bogojeska12.html.

Related Material