A Bayesian framework to quantify survival uncertainty
Published in ESMO MAP, 2019
This paper provides a Bayesian framework for quantifying survival uncertainity using deep esembles. The input to network is PAM50 gene set and clinical variables. Several methods like Cox-Propotional Hazard Model, Multi-Task Linear Reression and their Bayesian extension are compared.
Citation
‘Loya H, Anand D, Kumar N, Sethi A. (2019). "A Bayesian framework to quantify survival uncertainty." Proceedings of ESMO’s The Molecular Analysis for Personalised Therapy Congress; 2019 Nov 7-9; London, UK.’