Research map / Label-efficient and robust learning / Recognition and long-tail
ConCare: Personalized Clinical Feature Embedding via Capturing the Healthcare Context
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 ConCare’s personalized feature-context model rather than the strongest baseline for the metric | MIMIC-III mortality prediction · MIMIC-III | AUPRC: .5003 -> .5317 | Helped |
| Use ConCare’s personalized feature-context model rather than the strongest baseline for the metric | ESRD mortality prediction · ESRD | AUROC: .8101 -> .8209 | Helped |
| Use ConCare’s personalized feature-context model rather than the strongest baseline for the metric | ESRD mortality prediction · ESRD | AUPRC: .3508 -> .3606 | Helped |
| Add a multi-channel GRU encoder instead of positional encoding (ablation) | ConCare · MIMIC-III | AUROC: .8566 -> .8702 | Helped |
| Add a multi-channel GRU encoder instead of positional encoding (ablation) | ConCare · ESRD | AUROC: .8124 -> .8209 | Helped |
| Add cross-head decorrelation loss (ablation) | ConCare · MIMIC-III | AUPRC: .5231 -> .5317 | Helped |
| Add cross-head decorrelation loss (ablation) | ConCare · ESRD | AUROC: .8162 -> .8209 | Helped |
| Add multi-channel feature-sequence modeling rather than the ConCare_MC- variant (ablation) | ConCare · MIMIC-III | AUPRC: .4902 -> .5317 | Helped |
| Add multi-channel feature-sequence modeling rather than the ConCare_MC- variant (ablation) | ConCare · ESRD | AUROC: .8101 -> .8209 | Helped |
Closest papers by meaning
- DearLLM: Enhancing Personalized Healthcare via Large Language Models-Deduced Feature Correlations (AAAI 2025 · similarity 0.86)
- GraphCare: Enhancing Healthcare Predictions with Personalized Knowledge Graphs (ICLR 2024 · similarity 0.85)
- SMART: Towards Pre-trained Missing-Aware Model for Patient Health Status Prediction (NeurIPS 2024 · similarity 0.85)
- NeuralCohort: Cohort-aware Neural Representation Learning for Healthcare Analytics (ICML 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)
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.