Ranking Biomarkers Through Mutual Information
Abstract
We study information theoretic methods for ranking biomarkers. In clinical trials there are two, closely related, types of biomarkers: predictive and prognostic, and disentangling them is a key challenge. Our first step is to phrase biomarker ranking in terms of optimizing an information theoretic quantity. This formalization of the problem will enable us to derive rankings of predictive/prognostic biomarkers, by estimating different, high dimensional, conditional mutual information terms. To estimate these terms, we suggest efficient low dimensional approximations, and we derive an empirical Bayes estimator, which is suitable for small or sparse datasets. Finally, we introduce a new visualisation tool that captures the prognostic and the predictive strength of a set of biomarkers. We believe this representation will prove to be a powerful tool in biomarker discovery.
Cite
@article{arxiv.1612.01316,
title = {Ranking Biomarkers Through Mutual Information},
author = {Konstantinos Sechidis and Emily Turner and Paul D. Metcalfe and James Weatherall and Gavin Brown},
journal= {arXiv preprint arXiv:1612.01316},
year = {2016}
}
Comments
Accepted at NIPS 2016 Workshop on Machine Learning for Health