# survivalContour: visualizing predicted survival via colored contour plots

## TL;DR

This paper introduces a new visualization tool called survivalContour to show how continuous factors affect survival predictions over time.

## Contribution

The novelty lies in using colored contour plots to visualize predicted survival probabilities from various models.

## Key findings

- Colored contour plots effectively show predicted survival probabilities over time for continuous covariates.
- The method works well with both traditional and modern machine learning survival models.
- A Shiny app and R package were developed to implement the proposed visualization tool.

## Abstract

Advances in survival analysis have facilitated unprecedented flexibility in data modeling, yet there remains a lack of tools for illustrating the influence of continuous covariates on predicted survival outcomes. We propose the utilization of a colored contour plot to depict the predicted survival probabilities over time. Our approach is capable of supporting conventional models, including the Cox and Fine–Gray models. However, its capability shines when coupled with cutting-edge machine learning models such as random survival forests and deep neural networks.

We provide a Shiny app at https://biostatistics.mdanderson.org/shinyapps/survivalContour/ and an R package available at https://github.com/YushuShi/survivalContour as implementations of this tool.