Welcome to SuperSurv! | Step 1: Install the Core Package | Step 2: Install Base Learners (Optional but Recommended) | Specialized Packages | Step 3: You're Ready! | References

Introduction | 1. Load Data & Prepare Matrices | 2. Define the Ensemble Library | 3. Train the SuperSurv Metalearner | The Data Inputs | The Model Libraries | The Meta-Learner & Tuning | 4. Package Object Interface | 5. Compare the Fitting Objectives | 6. Generating Predictions on New Data | Understanding the Output Matrix: | 7. Visualizing Patient-Specific Predictions | 8. Next Steps

Introduction | 1. Data Preparation & The Extrapolation Rule | 2. Train the Benchmark Ensemble | 3. Extracting Integrated Metrics | 4. Visualizing Longitudinal Benchmarks | Interpreting the Curves: | 5. Assessing Clinical Calibration

Introduction | 1. Prepare the Data | 2. Fit Both Super Learners | 3. Inspecting the Weights | 4. Evaluate and Compare Performance

Introduction | 1. Simulating High-Dimensional Data | 2. Defining the Screening Algorithms | 3. Training with Embedded Screening | 4. Evaluating the Screened Ensemble | 5. Identifying the Selected Features

Introduction | 1. Prepare the Data | 2. Defining the Search Space | 3. Generating the Tuning Grid | 4. Fitting the Tuned Ensemble

Introduction | 1. Prepare the Data | 2. Standalone Machine Learning | 3. Evaluating the Standalone Model | 4. Train the Benchmark Ensemble | 5. Visualizing Ensemble vs. Base Learners

Introduction | 1. Setup and Model Fitting | 2. Global Explanations (Kernel SHAP) | Global Importance Bar Plot | SHAP Beeswarm Summary Plot | 3. Local (Patient-Level) Explanations | 4. Feature Dependence Plots | 5. Patient Risk Trajectories (Survival Heatmap) | 6. Time-Dependent Explanations (survex Integration) | A. Dynamic Feature Importance | B. Time-Dependent Partial Dependence Profiles | C. SurvSHAP(t): Local Explanations Over Time | D. Ecosystem Compatibility: Global Model Performance

Moving Beyond the Hazard Ratio | Philosophy: "Causal Effect" vs. "Marginal Contrast" | Estimating the Effect with SuperSurv | 1. Train the Super Learner | 2. Estimate the Adjusted Marginal RMST Contrast | 3. Visualizing the Effect Over Time | 4. Diagnostic: Predicted RMST vs. Observed Time

How Learners Are Found | Learner Wrapper Contract | Prediction Method Contract | Direct Survival Curves vs Risk Scores | Optional Additional Learners | Minimal Custom Learner | Screening Method Contract | Development Checklist

Introducrtion | 1. Installation | 2. Explore with an example data | Overview of the data | Data pre-process and visulization with Seurat | UMAP separated by Study | UMAP separated by cell type | Try different data integration methods | Run Seurat CCA | Run Harmony | UMAP figures for all integrated data | 3. Applying SCIntRuler to example data | Calculate SCIntRuler and and an associated visualization | SessionInfo

Introduction | 1. Setup and Library Definition | 2. Fitting the Parametric Ensemble | 3. Evaluating the "Safety Net" | Interpretation