Not Logged In

Learning Patient-Specific Cancer Survival Distributions as a Sequence of Dependent Regressors

Full Text: nips11_survival.pdf PDF
Other Attachments: survival_poster.pdf [PDF] PDF

An accurate model of patient survival time can help in the treatment and care of cancer patients. The common practice of providing survival time estimates based only on population averages for the site and stage of cancer ignores many important individual differences among patients. In this paper, we propose a local regression method for learning patient-specific survival time distribution based on patient attributes such as blood tests and clinical assessments. When tested on a cohort of more than 2000 cancer patients, our method gives survival time predictions that are much more accurate than popular survival analysis models such as the Cox and Aalen regression models. Our results also show that using patient-specific attributes can reduce the prediction error on survival time by as much as 20% when compared to using cancer site and stage only.

Citation

C. Yu, R. Greiner, H. Lin, V. Baracos. "Learning Patient-Specific Cancer Survival Distributions as a Sequence of Dependent Regressors". Neural Information Processing Systems (NIPS), December 2011.

Keywords: Survival Prediction, Multi-Task Learning, Survival Analysis, medical informatics
Category: In Conference
Web Links: Webpage

BibTeX

@incollection{Yu+al:NIPS11,
  author = {Chun-Nam Yu and Russ Greiner and Hsiu-Chin Lin and Vickie Baracos},
  title = {Learning Patient-Specific Cancer Survival Distributions as a
    Sequence of Dependent Regressors},
  booktitle = {Neural Information Processing Systems (NIPS)},
  year = 2011,
}

Last Updated: October 01, 2013
Submitted by Russ Greiner

University of Alberta Logo AICML Logo