Statistical Bioinformatics Webinar: Kumar -- Learning Individual Survival Models from PanCancer Whole Transcriptome Data - A Step Towards Personalized Medicine

Presented by Dr.  Neeraj Kumar (University of Alberta, Canada) 

Personalized medical oncology aims to provide individualized cancer treatments by
acknowledging that every cancer patient is unique, in terms of prognosis, treatment
tolerance, and survival outcome due in part to each individual tumor’s distinctive
molecular profile.  It is clearly useful to accurately estimate a patient’s survival
time, as that could help in making end-of-life decisions, and in assessing
patient-specific benefits of personalized medicine.  A novel type of survival prediction
model that estimates individual survival distributions (ISDs) - survival probabilities
at several time points for an individual - can play a significant role in the future
of personalized oncology.  Specifically, this talk will show how to fit accurate ISDs
from pan-cancer whole transcriptome data and how these ISDs could be used to accurately
assess a cancer patient’s survival likelihood in comparison to other models, including
the ubiquitous Kaplan-Meier and Cox proportional hazard estimates.