survex1.2.0 package

Explainable Machine Learning in Survival Analysis

brier_score

Calculate Brier score

c_index

Compute the Harrell's Concordance index

cd_auc

Calculate Cumulative/Dynamic AUC

cumulative_hazard_to_survival

Transform Cumulative Hazard to Survival

explain_survival

A model-agnostic explainer for survival models

extract_predict_survshap

Extract Local SurvSHAP(t) from Global SurvSHAP(t)

integrated_brier_score

Calculate integrated Brier score

integrated_cd_auc

Calculate integrated C/D AUC

loss_adapt_mlr3proba

Adapt mlr3proba measures for use with survex

loss_integrate

Calculate integrated metrics based on time-dependent metrics.

loss_one_minus_c_index

Calculate the Concordance index loss

loss_one_minus_cd_auc

Calculate Cumulative/Dynamic AUC loss

loss_one_minus_integrated_cd_auc

Calculate integrated C/D AUC loss

model_diagnostics.surv_explainer

Dataset Level Model Diagnostics

model_parts.surv_explainer

Dataset Level Variable Importance for Survival Models

model_performance.surv_explainer

Dataset Level Performance Measures

model_profile.surv_explainer

Dataset Level Variable Profile as Partial Dependence Explanations for ...

model_profile_2d.surv_explainer

Dataset Level 2-Dimensional Variable Profile for Survival Models

model_survshap.surv_explainer

Global SHAP Values

plot.aggregated_surv_shap

Plot Aggregated SurvSHAP(t) Explanations for Survival Models

plot.model_diagnostics_survival

Plot Model Diagnostics for Survival Models

plot.model_parts_survival

Plot Model Parts for Survival Models

plot.model_performance_survival

Plot Model Performance for Survival Models

plot.model_profile_2d_survival

Plot 2-Dimensional Model Profile for Survival Models

plot.model_profile_survival

Plot Model Profile for Survival Models

plot.predict_parts_survival

Plot Predict Parts for Survival Models

plot.predict_profile_survival

Plot Predict Profile for Survival Models

plot.surv_feature_importance

Plot Permutational Feature Importance for Survival Models

plot.surv_lime

Plot SurvLIME Explanations for Survival Models

plot.surv_model_performance

Plot Model Performance Metrics for Survival Models

plot.surv_model_performance_rocs

Plot ROC Curves for Survival Models

plot.surv_shap

Plot SurvSHAP(t) Explanations for Survival Models

predict.surv_explainer

Model Predictions for Survival Models

predict_parts.surv_explainer

Instance Level Parts of Survival Model Predictions

predict_profile.surv_explainer

Instance Level Profile as Ceteris Paribus for Survival Models

risk_from_chf

Generate Risk Prediction based on the Survival Function

surv_ceteris_paribus

Helper functions for predict_profile.R

surv_feature_importance

Helper functions for model_parts.R

surv_integrated_feature_importance

Helper functions for model_parts.R

surv_lime

Helper functions for predict_parts.R

surv_model_info

Extract additional information from the model

surv_model_performance

Helper functions for model_performance.R

surv_shap

Helper functions for predict_parts.R

survival_to_cumulative_hazard

Transform Survival to Cumulative Hazard

theme_survex

Default Theme for survex plots

transform_to_stepfunction

Transform Fixed Point Prediction into a Stepfunction

Survival analysis models are commonly used in medicine and other areas. Many of them are too complex to be interpreted by human. Exploration and explanation is needed, but standard methods do not give a broad enough picture. 'survex' provides easy-to-apply methods for explaining survival models, both complex black-boxes and simpler statistical models. They include methods specific to survival analysis such as SurvSHAP(t) introduced in Krzyzinski et al., (2023) <doi:10.1016/j.knosys.2022.110234>, SurvLIME described in Kovalev et al., (2020) <doi:10.1016/j.knosys.2020.106164> as well as extensions of existing ones described in Biecek et al., (2021) <doi:10.1201/9780429027192>.

  • Maintainer: Mikołaj Spytek
  • License: GPL (>= 3)
  • Last published: 2023-10-24