From 116020915d098a7f262ab8130ddbc4a6e5a827c7 Mon Sep 17 00:00:00 2001 From: Vincent Maladiere Date: Tue, 14 Jan 2025 16:07:30 +0100 Subject: [PATCH] some rephrasing --- doc/index.rst | 46 ++++++++++++++++++++++------------------------ 1 file changed, 22 insertions(+), 24 deletions(-) diff --git a/doc/index.rst b/doc/index.rst index a8b6c18..fe120fa 100644 --- a/doc/index.rst +++ b/doc/index.rst @@ -17,24 +17,22 @@ Gradient-boosting Survival Analysis and Competing Risks * scalable gradient boosting -**hazardous** is a Python library for **survival analysis - i.e. time-to-event prediction - -and competing risks** predictions. The model proposed in this library is -a **scalable** gradient-boosting called **SurvivalBoost**. - -With a **scikit-learn compatible API**, we also provide different useful -metrics for the evaluation of the model such as the **Integrated Brier Score** -or the **C-index** adapted for competing risks setting. - +**hazardous** is a Python library for **survival analysis** -i.e. time-to-event prediction- +and **competing risks** modeling. It introduces **SurvivalBoost**, a **scalable** +gradient-boosting model designed for this task. +With a scikit-learn-compatible API, the library also offers various metrics +for model evaluation, including the **Integrated Brier Score** and the **C-index**, +both adapted for the competing risks setting. What is the difference between Survival Analysis and the Competing risks setting? -------------------------------------- -Compared to the Survival Analysis setting, the Competing Risks setting -considers that the event of interest is not the only event of interest -that may happen. -Predicting which event will happen first, and when, from data where some -events have not yet been observed: +--------------------------------------------------------------------------------- +In contrast to the Survival Analysis setting, the Competing Risks setting accounts +for the possibility that multiple types of events of interest may occur, +not just a single event. +It focuses on predicting which event will occur first and when, based on data where +some events have not yet been observed. .. image:: competing_risk_diagram.svg What is SurvivalBoost? @@ -49,23 +47,23 @@ cumulative incidence function and the survival function at any horizon. SurvivalBoost puts a focus on predictive the accuracy -defined as the ability to predict the observed event- rather than on inference. -More information about the theory behind the model is described in `Survival Models: +Additional theoretical details about the model can be found in `Survival Models: Proper Scoring Rule and Stochastic Optimization with Competing Risks `_. .. seealso:: - The library depends on `lifelines `_ - for the Kaplan-Meier estimator used in SurvivalBoost. We thank the authors of - lifelines for their work and their contribution to the community of survival analysis - with the implementation of models -e.g. Kaplan-Meier, Cox model, Aalen-Johansen- and - metrics -e.g. C-index, Brier Score-. - + The library relies on `lifelines `_ + for the Kaplan-Meier estimator used in SurvivalBoost. We extend our gratitude to + the authors of lifelines for their significant contributions to the survival + analysis community, including the implementation of models such as + the Kaplan-Meier, Cox model, and Aalen-Johansen, as well as metrics + like the C-index and Brier Score. .. note:: - Quantifying the statistical association or causal effect of covariates with/on - the cumulated event incidence or instantaneous hazard rate is not in the scope - of this library at this time. + Quantifying the statistical association or causal effect of covariates on the + cumulative event incidence or instantaneous hazard rate is currently beyond + the scope of this library. - License: MIT - GitHub repository: https://github.com/soda-inria/hazardous