- 56 views
- 41 downloads
Comparing Parameterization Methods for Loss-Based Discrete-Time Individual Survival Prediction Models
-
- Author / Creator
- Kuan, Li-Hao
-
Given a patient's description, a survival prediction model estimates that patient's survival time. We consider the challenge of learning an individual survival distribution (ISD) model from a dataset that includes censored training instances – i.e., data that provides only the lower bound of the survival time for some patients. In general, an ISD model maps each patient x to his/her survival distribution, which is the probability that patient x will survive until time t, for each t > 0. We focus on discrete-time ISD models, which partition the future time into multiple time intervals and then apply machine learned regressors to estimate the survival probability in each time interval. These discrete-time ISD models can usually use fewer parameters than continuous models to describe different shapes of survival distributions by discretizing the survival time.
We compare four survival models that represent the four parameterization methods for discrete-time survival models: simple multinomial, multi-task (MTLR), discrete hazard, and hazard multi-task models. We empirically evaluate these survival prediction models on nine real-world survival datasets. In addition, we explore the discrete hazard feature selection method, which can identify features that are important at different times in the future. The result shows no statistical difference between the four prediction models with respect to the integrated Brier score (IBS). Our feature selection methods produce models with similar IBS performance (i.e., no statistically significant differences) of the survival model but succeeded in reducing the number of features for high-dimensional datasets.
-
- Subjects / Keywords
-
- Graduation date
- Fall 2023
-
- Type of Item
- Thesis
-
- Degree
- Master of Science
-
- License
- This thesis is made available by the University of Alberta Libraries with permission of the copyright owner solely for non-commercial purposes. This thesis, or any portion thereof, may not otherwise be copied or reproduced without the written consent of the copyright owner, except to the extent permitted by Canadian copyright law.