Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

survex: an R package for explaining machine learning survival models

Mikołaj Spytek, Mateusz Krzyziński, Sophie Hanna Langbein, Hubert Baniecki, Marvin N. Wright, Przemysław Biecek

TL;DR

The survex R package is introduced, which provides a cohesive framework for explaining any survival model by applying explainable artificial intelligence techniques, and enables the assessment of model reliability and the detection of biases.

Abstract

Due to their flexibility and superior performance, machine learning models frequently complement and outperform traditional statistical survival models. However, their widespread adoption is hindered by a lack of user-friendly tools to explain their internal operations and prediction rationales. To tackle this issue, we introduce the survex R package, which provides a cohesive framework for explaining any survival model by applying explainable artificial intelligence techniques. The capabilities of the proposed software encompass understanding and diagnosing survival models, which can lead to their improvement. By revealing insights into the decision-making process, such as variable effects and importances, survex enables the assessment of model reliability and the detection of biases. Thus, transparency and responsibility may be promoted in sensitive areas, such as biomedical research and healthcare applications.

survex: an R package for explaining machine learning survival models

TL;DR

The survex R package is introduced, which provides a cohesive framework for explaining any survival model by applying explainable artificial intelligence techniques, and enables the assessment of model reliability and the detection of biases.

Abstract

Due to their flexibility and superior performance, machine learning models frequently complement and outperform traditional statistical survival models. However, their widespread adoption is hindered by a lack of user-friendly tools to explain their internal operations and prediction rationales. To tackle this issue, we introduce the survex R package, which provides a cohesive framework for explaining any survival model by applying explainable artificial intelligence techniques. The capabilities of the proposed software encompass understanding and diagnosing survival models, which can lead to their improvement. By revealing insights into the decision-making process, such as variable effects and importances, survex enables the assessment of model reliability and the detection of biases. Thus, transparency and responsibility may be promoted in sensitive areas, such as biomedical research and healthcare applications.
Paper Structure (7 sections, 1 figure)

This paper contains 7 sections, 1 figure.

Table of Contents

  1. Introduction
  2. Related work
  3. Implementation and functionalities
  4. Explanation methods
  5. Visualizations
  6. Applications
  7. Future work

Figures (1)

  • Figure 1: Explanations and functionalities available in the survex package. The methods are divided into local (concerning individual predictions) and global (concerning the model). The diagram illustrates simplified examples of the visualizations of selected explanations in each category. A complete list of functionalities with documentation is available at https://modeloriented.github.io/survex.