You are here
History-alignment models for bias-aware prediction of virological response to HIV combination therapy
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.
AISTATS Proceedings 2012
21 Apr 2012
[BDZ+12] Bogojeska, J., Stöckel, D., Zazzi, Z., Rolf, K., Francesca, I., Michal, R-Z., Lengauer, T. History-alignment models for bias-aware prediction of virological response to HIV combination therapy. AISTATS 2012.