scikit-survival

Fit survival models and evaluate censored time-to-event data in Python.

Updated Aug 23, 2026

Search Tags:#machine learning #statistics #survival analysis #predictive modeling #time-to-event #censored data

Ready to run

npx skills add https://github.com/jacketlong23/skills --skill scikit-survival-jacketlong23

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: scikit-survival
Source: https://github.com/jacketlong23/skills/tree/main/scikit-survival
Command: npx skills add https://github.com/jacketlong23/skills --skill scikit-survival-jacketlong23

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a comprehensive toolkit for survival analysis and time-to-event modeling in Python, enabling users to analyze censored data and build predictive models for time-based outcomes.

Core Features & Use Cases

Model Fitting: Supports CoxPH, CoxNet, Random Survival Forests, Gradient Boosting, and Survival SVMs.
Data Handling: Includes utilities for creating survival outcomes, preprocessing, and validation.
Evaluation: Offers metrics like C-index, time-dependent AUC, and Brier score.
Use Case: Analyze patient data to predict time to disease recurrence, accounting for censored observations, and evaluate model performance using robust metrics.

Quick Start

Use the scikit-survival skill to fit a Cox proportional hazards model to the provided dataset.

Frequently Asked Questions about scikit-survival

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I perform survival analysis on censored data in Python?▼

Perform survival analysis on censored data in Python by fitting models like Cox proportional hazards or Random Survival Forests to time-to-event datasets, enabling predictive modeling for outcomes where the event has not yet occurred for all subjects.

What is the best way to evaluate time-to-event model performance?▼

Evaluate time-to-event model performance using metrics like the concordance index, time-dependent AUC, and Brier score to measure predictive accuracy and calibration for survival models handling censored observations.

Can I use Random Survival Forests and Gradient Boosting for predictive modeling?▼

Random Survival Forests and Gradient Boosting can be used for predictive modeling of time-to-event data, offering robust methods to handle censored observations and predict disease recurrence or failure times effectively.

Does this approach support Cox models for time-to-event analysis?▼

Cox models, including CoxPH and CoxNet, are fully supported for time-to-event analysis, allowing you to fit proportional hazards models to survival datasets and handle censored data efficiently.

How do I handle censored data when predicting time to disease recurrence?▼

Handle censored data when predicting disease recurrence by creating structured survival outcomes using provided utilities, fitting appropriate survival models, and evaluating predictions with metrics designed for incomplete time-to-event observations.

What are the limitations of using Survival SVMs for time-to-event modeling?▼

Survival SVMs for time-to-event modeling may face limitations with very large datasets or complex censoring patterns, requiring careful preprocessing and validation to ensure reliable predictive performance compared to tree-based survival methods.