TY - JOUR
T1 - Disentangling Prognostic and Predictive Biomarkers Through Mutual Information
AU - Sechidis, Konstantinos
AU - Turner, Emily
AU - Metcalfe, Paul
AU - Weatherall, James
AU - Brown, Gavin
PY - 2017
Y1 - 2017
N2 - 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. 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.
AB - 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. 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.
KW - mutual information
KW - Predictive biomarkers
KW - prognostic biomarkers
UR - http://www.scopus.com/inward/record.url?scp=85018798586&partnerID=8YFLogxK
U2 - 10.3233/978-1-61499-753-5-141
DO - 10.3233/978-1-61499-753-5-141
M3 - Article
AN - SCOPUS:85018798586
SN - 0926-9630
VL - 235
SP - 141
EP - 145
JO - Studies in Health Technology and Informatics
JF - Studies in Health Technology and Informatics
ER -