Corpus ID: 53821750

Effective Ways to Build and Evaluate Individual Survival Distributions

@article{Haider2020EffectiveWT,
  title={Effective Ways to Build and Evaluate Individual Survival Distributions},
  author={Humza Haider and B. Hoehn and Sarah Davis and R. Greiner},
  journal={ArXiv},
  year={2020},
  volume={abs/1811.11347}
}
An accurate model of a patient's individual survival distribution can help determine the appropriate treatment for terminal patients. Unfortunately, risk scores (e.g., from Cox Proportional Hazard models) do not provide survival probabilities, single-time probability models (e.g., the Gail model, predicting 5 year probability) only provide for a single time point, and standard Kaplan-Meier survival curves provide only population averages for a large class of patients meaning they are not… Expand
Simultaneous Prediction Intervals for Patient-Specific Survival Curves
X-CAL: Explicit Calibration for Survival Analysis
Gene expression based survival prediction for cancer patients—A topic modeling approach
Sample Efficient Learning of Image-Based Diagnostic Classifiers Using Probabilistic Labels

References

SHOWING 1-10 OF 73 REFERENCES
Individual Survival Distributions: A More Effective Tool for Survival Prediction
Random survival forests
Evaluation of the Performance of Survival Analysis Models: Discrimination and Calibration Measures
A Multi-Task Learning Formulation for Survival Analysis
Individual survival time prediction using statistical models
Deep Survival Analysis
Nonparametric survival analysis using Bayesian Additive Regression Trees (BART).
Survival model predictive accuracy and ROC curves.
Machine Learning for Survival Analysis: A Survey
...
1
2
3
4
5
...