Model censored time-to-event outcomes and predict survival risks in Python.
npx skills add https://github.com/CRAG666/dotfiles --skill scikit-survival-crag666
Please help me install this Agent Skill. Skill: scikit-survival Source: https://github.com/CRAG666/dotfiles/tree/main/skills/scikit-survival Command: npx skills add https://github.com/CRAG666/dotfiles --skill scikit-survival-crag666
scikit-survival helps you analyze time-to-event outcomes when part of your data is censored, so you can model risk and event timing without biasing results.
In your notebook, load your dataset, convert outcomes with sksurv.util.Surv, fit a CoxPHSurvivalAnalysis model, then evaluate it using concordance_index_ipcw.
High-intent search queries and answers about installing and using this skill.
To analyze time-to-event data with censored outcomes in Python, construct Surv targets and fit estimators like CoxPHSurvivalAnalysis to predict risk without biasing results from incomplete follow-up.
Evaluate survival models with censored data using censoring-aware metrics like concordance_index_ipcw, cumulative_dynamic_auc, and integrated_brier_score to accurately measure discrimination and calibration.
You can train Random Survival Forests, Gradient Boosting for survival, and Survival SVM variants to model censored time-to-event outcomes when standard Cox proportional hazards assumptions are insufficient.
Handle competing risks in survival analysis by applying cumulative incidence analysis to model the probability of specific events when patients face multiple mutually exclusive failure types.
Standard regression biases time-to-event predictions because it ignores censored data, incorrectly treating lost subjects as event-free, which skews risk estimates and survival probabilities.
scikit-survival supports penalized Cox proportional hazards models and IPCW Ridge accelerated failure time models to manage high-dimensional covariates and prevent overfitting in survival predictions.
Estrella-231Train and evaluate censored time-to-event survival models in Python using scikit-survival.
robinbarvaagFits Cox, Random Survival Forest, Gradient Boosting, and SVM survival models in Python using scikit-survival.
xjtulycEstimate time-to-event outcomes with Kaplan–Meier, log-rank, and Cox PH models.
swaruplabPerform censoring-aware survival analysis with Cox, ensemble, and SVM models in Python.
