Research map / Probabilistic and scientific modeling / Molecules and proteins
When Can We Trust Survival Model Evaluation ?
Ghanem BAHRINI, Sebastien Razakarivony, Jean-François Dupuy, Valerie Gares, Morgane Barbet-Massin
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| increase censoring rate (ablation) | survival evaluation metrics · semi-synthetic censoring (AC/IC/CDC) | normalized bias | Hurt |
| switch from independent to covariate-dependent censoring (ablation) | C-index family · semi-synthetic censoring | normalized bias: rho >= 70% to rho >= 50% | Hurt |
| use fixed-horizon concordance C(tq) instead of global C-Harrell/Antolini (ablation) | concordance metrics · semi-synthetic censoring | normalized bias | Improved |
| truncate IBS integration horizon (IBS(t25)) (ablation) | IBS · independent censoring | normalized bias | Improved |
| truncate IBS integration horizon (ablation) | IBS · covariate-dependent censoring | normalized bias | No clear effect |
| use mechanism-specific IBS-ADMIN (ablation) | IBS · administrative censoring | normalized bias | Improved |
| use Cox-based censoring model for IPCW IBS (ablation) | IBS · covariate-dependent censoring | normalized bias | No clear effect |
| switch from D-Calibration to 1-Calibration (ablation) | calibration metrics · semi-synthetic censoring | normalized bias | Improved |
| filter Top-1 comparisons to statistically significant top-two gaps (ablation) | Top-1 consistency analysis · semi-synthetic censoring | number of comparable cases: 225 -> 130 | Mixed |
| use dominance-based global agreement instead of Top-1 consistency (ablation) | ranking evaluation · non-informative censoring | ranking agreement | Improved |
| restrict to early horizon IBS(t25) and 1-CAL(t25) (ablation) | ranking evaluation · semi-synthetic censoring | global ranking agreement | Improved |
Closest papers by meaning
- Conformalized Survival Distributions: A Generic Post-Process to Increase Calibration (ICML 2024 · similarity 0.86)
- Deep Copula-Based Survival Analysis for Dependent Censoring with Identifiability Guarantees (AAAI 2024 · similarity 0.86)
- Toward Conditional Distribution Calibration in Survival Prediction (NeurIPS 2024 · similarity 0.86)
- Learning Survival Models with Right-Censored Reporting Delays (NeurIPS 2026 · similarity 0.86)
- Assessing the robustness of heterogeneous treatment effects in survival analysis under informative censoring (NeurIPS 2026 · similarity 0.86)
- Censor Dependent Variational Inference (ICML 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
