Research map / Probabilistic and scientific modeling / Molecules and proteins
Deep Recurrent Survival Analysis
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use recurrent conditional hazard prediction and the probability chain rule instead of direct event-time probability prediction | DRSA versus DeepHit · CLINIC, MUSIC, BIDDING | C-index: 0.733 -> 0.774; 0.878 -> 0.892; 0.858 -> 0.911 | Helped |
| Use recurrent conditional hazard prediction and the probability chain rule instead of direct event-time probability prediction | DRSA versus DeepHit · CLINIC, MUSIC, BIDDING | ANLP: 5.027 -> 3.337; 5.523 -> 5.132; 5.544 -> 4.774 | Helped |
| Add the censored-data loss (ablation) | DRSA · CLINIC, MUSIC, BIDDING | C-index: 0.765 -> 0.774; 0.881 -> 0.892; 0.823 -> 0.911 | Helped |
| Add the censored-data loss (ablation) | DRSA · CLINIC, MUSIC, BIDDING | ANLP: 3.441 -> 3.337; 5.412 -> 5.132; 12.255 -> 4.774 | Helped |
| Add the uncensored partial-likelihood loss (ablation) | DRSA · CLINIC, MUSIC, BIDDING | C-index: 0.760 -> 0.774; 0.882 -> 0.892; 0.900 -> 0.911 | Helped |
| Add the uncensored partial-likelihood loss (ablation) | DRSA · CLINIC, MUSIC, BIDDING | ANLP: 3.136 -> 3.337; 5.459 -> 5.132; 4.990 -> 4.774 | Mixed |
Closest papers by meaning
- Deep Copula-Based Survival Analysis for Dependent Censoring with Identifiability Guarantees (AAAI 2024 · similarity 0.88)
- Gradient-based Explanations for Deep Learning Survival Models (ICML 2025 · similarity 0.86)
- Learning Survival Models with Right-Censored Reporting Delays (NeurIPS 2026 · similarity 0.86)
- SurvivalPFN: Amortizing Survival Prediction via In-Context Bayesian Inference (NeurIPS 2026 · similarity 0.85)
- Survival Analysis via Density Estimation (ICML 2025 · similarity 0.85)
- History-Aware Conformal Prediction Sets for Censored Time-to-Event Outcomes (NeurIPS 2026 · similarity 0.84)
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.