skills.rest
LeonChaoX
LeonChaoXCOMMUNITY
Explore all skills by this author →
GitHub

scikit-survival

Build censored time-to-event survival models with scikit-survival estimators.

783|65|Updated Feb 27, 2026
Search Tags:#survival analysis#cox model#time-to-event#censored data#evaluation metrics#competing risks#python scikit-learn ecosystem
One-click install
npx skills add https://github.com/LeonChaoX/qinyan-academic-skills --skill scikit-survival-leonchaox
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: scikit-survival
Source: https://github.com/LeonChaoX/qinyan-academic-skills/tree/main/skills/09-%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0%E4%B8%8E%E4%BA%BA%E5%B7%A5%E6%99%BA%E8%83%BD/scikit-survival
Command: npx skills add https://github.com/LeonChaoX/qinyan-academic-skills --skill scikit-survival-leonchaox

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps you perform survival analysis for time-to-event outcomes when observations may be censored, so you can quantify risk over time and evaluate model performance correctly.

Core Features & Use Cases

  • Model time-to-event outcomes with censoring: build and compare Cox models, penalized Cox (Coxnet), accelerated failure time via IPC Ridge, and ensemble survival methods.
  • Fit powerful non-linear predictors: use Random Survival Forests, Gradient Boosting for survival, and Survival SVM variants for ranking-based risk modeling.
  • Evaluate with censoring-aware metrics: compute Harrell’s and Uno’s concordance indices, time-dependent AUC, and Brier score / integrated Brier score.
  • Handle competing risks: estimate cumulative incidence functions using competing-risks methods and avoid treating competing events as simple censoring.

Quick Start

Use the scikit-survival skill to fit a competing-risks survival workflow on your censored dataset and report Uno’s C-index plus time-dependent AUC at clinically relevant time points.

Frequently Asked Questions about scikit-survival

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

FAQPage Schema
How do I model time-to-event data with right censoring in Python?▼

To model right-censored time-to-event data, use scikit-survival to construct outcomes with sksurv.util.Surv and fit estimators like Cox or penalized Cox models to quantify risk over time.

What is the best way to evaluate survival analysis models when data is censored?▼

The best way to evaluate censored survival models is using censoring-aware metrics like Uno’s concordance index, cumulative dynamic AUC, and integrated Brier score instead of standard regression metrics.

Can I estimate cumulative incidence functions for competing risks without treating events as censored?▼

Yes, you can estimate cumulative incidence functions for competing risks using specialized competing-risks methods, ensuring competing events are not incorrectly treated as simple right censoring.

How do I fit non-linear survival models for high-dimensional datasets?▼

To fit non-linear survival models for high-dimensional datasets, apply Random Survival Forests, Gradient Boosting for survival, or Survival SVM variants to capture complex ranking-based risk patterns.

Does scikit-survival work within the standard scikit-learn ecosystem?▼

Yes, scikit-survival works within the standard scikit-learn ecosystem, allowing you to use familiar preprocessing pipelines and model selection techniques on censored time-to-event datasets.

Related Skills

Explore More Data & Analytics Skills→
Estrella-231Estrella-231

scikit-survival

Train and evaluate censored time-to-event survival models in Python using scikit-survival.

Community
Advanced
ovachieverovachiever
52

scikit-survival

Perform survival analysis on censored data with Cox models and ensemble methods.

Community
Advanced
mkurmanmkurman
321

scikit-survival

Analyze censored survival data and build time-to-event models with scikit-survival.

Community
Advanced
xjtulycxjtulyc
33

survival-analysis

Fit Kaplan-Meier, Cox, and AFT models to right-censored time-to-event data.

Community
Advanced