Clinical data based optimal STI strategies for HIV: a reinforcement learning approach
Add to your list(s)
Download to your calendar using vCal
If you have a question about this talk, please contact Carl Edward Rasmussen.
This research addresses the problem of computing optimal structured treatment interruption strategies (STI) for HIV infected patients.
STI represent a class of treatments in which patients are cycled on and off drug therapy at specific time instants. The problem that we consider consists in designing efficient drug-scheduling strategies, i.e. strategies which bring the immune system into a state that allows it to independently (without help from any drug) maintain immune control over the virus. Also, this transfer to a drug-independent viral control situation should be done with as low as possible drug-related systemic effects for the patients.
In this presentation, we show that reinforcement learning may be useful to extract (close-to) optimal STI strategies directly from clinical data, without the need of identifying a mathematical model of HIV infection dynamics. To support our claims, we report simulation results obtained by running a recently proposed batch-mode reinforcement learning algorithm, known as fitted Q iteration, on numerically generated data.
The corresponding paper can be found at http://www.montefiore.ulg.ac.be/~stan/CDC_2006.pdf
This talk is part of the Machine Learning @ CUED series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
|