skills.rest
silverstein
silversteinCOMMUNITY
Explore all skills by this author →
Website𝕏@matsilversteinGitHub

scikit-survival

Fit scikit-survival models for Cox, penalized Cox, survival trees, and survival SVMs.

21|2|Updated Dec 8, 2025
Search Tags:#python#machine learning#survival analysis#time-to-event#censored data#evaluation metrics#competing risks
One-click install
npx skills add https://github.com/silverstein/claude-scientific-skills-desktop --skill scikit-survival-silverstein
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: scikit-survival
Source: https://github.com/silverstein/claude-scientific-skills-desktop/tree/main/corpus/scikit-survival
Command: npx skills add https://github.com/silverstein/claude-scientific-skills-desktop --skill scikit-survival-silverstein

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Helps you analyze time-to-event outcomes with right-censored (and other) data so you can model risk, estimate survival curves, and evaluate predictions reliably even when not all event times are observed.

Core Features & Use Cases

  • Survival & time-to-event modeling: Build Cox models, penalized Cox, accelerated failure time (AFT) style models, Random Survival Forests, Gradient Boosting survival models, and Survival SVM variants.
  • Proper evaluation under censoring: Compute discrimination and calibration metrics such as concordance index (Harrell/Uno), time-dependent AUC, and (integrated) Brier scores.
  • Competing risks support: Estimate cumulative incidence functions for multiple event types and avoid treating competing events as simple censoring.
  • Practical workflows: Create Surv outcomes, preprocess features (encoding, standardization, missing-data handling), fit models, and compare approaches across scenarios.

Quick Start

Use this skill to model a dataset with censored survival times by asking: "Summarize the best scikit-survival model choice and evaluation metrics for my right-censored time-to-event dataset with moderate censoring, and show a concise workflow from Surv creation through risk prediction and Uno’s C-index."

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 with right-censored time-to-event data in Python?▼

Survival analysis with right-censored data requires constructing Surv outcomes and fitting models like Cox proportional hazards or Random Survival Forests to estimate risk and survival functions. The skill uses scikit-survival to model time-to-event outcomes even when not all event times are observed.

What's the best way to evaluate survival model predictions under censoring?▼

Evaluating survival model predictions under censoring involves computing discrimination and calibration metrics like Harrell's or Uno's concordance index, time-dependent AUC, and integrated Brier scores. The skill supports censoring-aware metrics to properly validate risk prediction models.

Can I estimate cumulative incidence functions for competing risks using Python?▼

Estimating cumulative incidence functions for competing risks in Python avoids treating competing events as simple censoring. The skill provides scikit-survival workflows for multiple event types, fitting survival models to clinical and biomedical studies with competing-risks cumulative incidence analysis.

How do I choose between Cox models, survival SVMs, and ensemble survival trees for my dataset?▼

Choosing between Cox models, survival SVMs, and ensemble survival trees depends on your dataset's dimensionality and nonlinearity. The skill guides selection across scikit-survival model families, including penalized Cox and Gradient Boosting survival models, aligning model choice to data characteristics.

Does scikit-survival support accelerated failure time models and penalized Cox regression?▼

Scikit-survival supports accelerated failure time (AFT) style models and penalized Cox regression for survival modeling. The skill fits these scikit-survival model families alongside Random Survival Forests and Survival SVMs for risk prediction and survival-function estimation.

Why should I not treat competing events as simple censoring in time-to-event analysis?▼

Treating competing events as simple censoring in time-to-event analysis biases survival estimates by assuming competing events are independent. The skill uses scikit-survival to estimate cumulative incidence functions for multiple event types, properly handling competing risks in clinical studies.

Related Skills

Explore More Education & Research Skills→
shushuznshushuzn
4

scikit-survival

Build censored-data survival models with scikit-survival for Cox, ensemble, and SVM approaches.

Community
Intermediate
LeonChaoXLeonChaoX
783

scikit-survival

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

Community
Advanced
mkurmanmkurman
321

scikit-survival

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

Community
Advanced
kjgarzakjgarza
3

scikit-survival

Model time-to-event data with censoring using scikit-survival in Python.

Community
Advanced