Research map / Label-efficient and robust learning / Recognition and long-tail
GRASP: Generic Framework for Health Status Representation Learning Based on Incorporating Knowledge from Similar Patients
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 similar-patient cohort information with adaptive fusion to ConCare* | ConCare* · Cardiology sepsis prediction | AUPRC: 0.7770 (0.02) -> 0.8014 (0.02) | Helped |
| Add similar-patient cohort information with adaptive fusion to ConCare* | ConCare* · Cardiology sepsis prediction | min(Se, P+): 0.7010 (0.02) -> 0.7210 (0.02) | Helped |
| Add similar-patient cohort information with adaptive fusion to ConCare* | ConCare* · Cardiology sepsis prediction | F1-Score: 0.7056 (0.01) -> 0.7234 (0.01) | Helped |
| Add similar-patient cohort information with adaptive fusion to ConCare* | ConCare* · CKD mortality prediction | AUPRC: 0.7368 (0.02) -> 0.7597 (0.02) | Helped |
| Add similar-patient cohort information with adaptive fusion to TimeNet* | TimeNet* · CKD mortality prediction | min(Se, P+): 0.6819 (0.01) -> 0.7013 (0.02) | Helped |
| Add similar-patient cohort information with adaptive fusion to ConCare* | ConCare* · CKD mortality prediction | F1-Score: 0.6600 (0.01) -> 0.6945 (0.01) | Helped |
| Add graph-based modeling of interactions between cohorts (ablation) | GRASP+ConCare* · Cardiology sepsis prediction | AUPRC: 0.7881 (0.02) -> 0.8014 (0.02) | Helped |
| Add graph-based modeling of interactions between cohorts (ablation) | GRASP+ConCare* · CKD mortality prediction | AUPRC: 0.7493 (0.02) -> 0.7597 (0.02) | Helped |
| Add Gumbel sampling for cohort assignment (ablation) | GRASP+ConCare* · Cardiology sepsis prediction | AUPRC: 0.7925 (0.01) -> 0.8014 (0.02) | Helped |
| Add Gumbel sampling for cohort assignment (ablation) | GRASP+ConCare* · CKD mortality prediction | AUPRC: 0.7488 (0.02) -> 0.7597 (0.02) | Helped |
Closest papers by meaning
- SMART: Towards Pre-trained Missing-Aware Model for Patient Health Status Prediction (NeurIPS 2024 · similarity 0.85)
- DearLLM: Enhancing Personalized Healthcare via Large Language Models-Deduced Feature Correlations (AAAI 2025 · similarity 0.85)
- ACES: Automatic Cohort Extraction System for Event-Stream Datasets (ICLR 2025 · similarity 0.84)
- NeuralCohort: Cohort-aware Neural Representation Learning for Healthcare Analytics (ICML 2025 · similarity 0.84)
- Contrastive Learning for Clinical Outcome Prediction with Partial Data Sources (ICML 2024 · similarity 0.83)
- VILA-M3: Enhancing Vision-Language Models with Medical Expert Knowledge (CVPR 2025 · 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.