Research map / Probabilistic and scientific modeling / Molecules and proteins
Early Prediction of Diabetes Complications from Electronic Health Records: A Multi-Task Survival Analysis Approach
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 |
|---|---|---|---|
| add ranking loss to log-normal regression (RankSvx vs regression) (ablation) | Log-normal regression · T2DM complications avg | concordance index: 0.5156 -> 0.6041 | Helped |
| add ranking loss to log-normal regression (ablation) | Log-normal regression · T2DM complications avg | MAE: 6.3643 -> 6.1102 | Helped |
| RankSvx Log-normal vs Cox model | survival modeling · T2DM complications avg | MAE: 13.749 -> 6.1102 | Helped |
| RankSvx Log-normal vs Cox model | survival modeling · T2DM complications avg | concordance index: 0.5860 -> 0.6041 | Helped |
| squared loss RankSvx vs Cox | survival modeling · T2DM complications avg | concordance index: 0.5860 -> 0.5859 | No clear effect |
| add ranking loss to Poisson regression (ablation) | Poisson regression · T2DM complications avg | concordance index: 0.5137 -> 0.5999 | Helped |
| add ranking loss to Poisson regression (ablation) | Poisson regression · T2DM complications avg | MAE: 6.4710 -> 6.7683 | Hurt |
| multi-task learning over complications vs single-task, full data (ablation) | RankSvx Log-normal · T2DM complications avg | concordance index: 0.6041 -> 0.6080 | Helped |
| multi-task learning with only 25% training data (ablation) | RankSvx Log-normal · T2DM complications avg | concordance index: 0.5712 -> 0.5767 | Helped |
| multi-task learning (ablation) | RankSvx Log-normal · T2DM complications avg | MAE: 6.1102 -> 6.1161 | No clear effect |
| multi-task learning on HYPER with 25% data (ablation) | RankSvx Log-normal · HYPER | concordance index: 0.5406 -> 0.5517 | Helped |
Closest papers by meaning
- XTSFormer: Cross-Temporal-Scale Transformer for Irregular-Time Event Prediction in Clinical Applications (AAAI 2025 · similarity 0.83)
- Context Clues: Evaluating Long Context Models for Clinical Prediction Tasks on EHR Data (ICLR 2025 · similarity 0.83)
- Risk Horizons: Structured Hypothesis Spaces for Longitudinal Clinical Prediction (NeurIPS 2026 · similarity 0.83)
- Automated Multi-Task Learning for Joint Disease Prediction on Electronic Health Records (NeurIPS 2024 · similarity 0.82)
- ACES: Automatic Cohort Extraction System for Event-Stream Datasets (ICLR 2025 · similarity 0.82)
- Learning Survival Models with Right-Censored Reporting Delays (NeurIPS 2026 · similarity 0.82)
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.