Research map / Label-efficient and robust learning / Recognition and long-tail
AdaCare: Explainable Clinical Health Status Representation Learning via Scale-Adaptive Feature Extraction and Recalibration
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 AdaCare instead of the strongest baseline, T-LSTM | ESRD mortality prediction · ESRD | AUPRC: 27.84% (.019) -> 31.79% (.020) | Helped |
| Use AdaCare instead of the strongest baseline, GRU | MIMIC-III decompensation prediction · MIMIC-III | AUPRC: 27.84% (.003) -> 30.37% (.004) | Helped |
| Add multi-scale dilated convolution (ablation) | AdaCare with sigmoid recalibration · ESRD | AUPRC: 27.66% (.025) -> 31.79% (.020) | Helped |
| Add multi-scale dilated convolution (ablation) | AdaCare with sigmoid recalibration · MIMIC-III | AUPRC: 28.11% (.002) -> 30.37% (.004) | Helped |
| Add sigmoid feature recalibration (ablation) | AdaCare with multi-scale dilated convolution · ESRD | AUPRC: 30.77% (.021) -> 31.79% (.020) | Helped |
| Add sigmoid feature recalibration (ablation) | AdaCare with multi-scale dilated convolution · MIMIC-III | AUPRC: 28.37% (.003) -> 30.37% (.004) | Helped |
| Replace sigmoid with sparsemax for raw-feature recalibration (ablation) | AdaCare with multi-scale convolution · ESRD | AUPRC: 31.79% (.020) -> 30.98% (.025) | Hurt |
| Replace sigmoid with sparsemax for raw-feature recalibration (ablation) | AdaCare with multi-scale convolution · MIMIC-III | AUPRC: 30.37% (.004) -> 28.95% (.004) | Hurt |
Closest papers by meaning
- GRASP: Generic Framework for Health Status Representation Learning Based on Incorporating Knowledge from Similar Patients (AAAI 2021 · similarity 0.85)
- SMART: Towards Pre-trained Missing-Aware Model for Patient Health Status Prediction (NeurIPS 2024 · similarity 0.83)
- DearLLM: Enhancing Personalized Healthcare via Large Language Models-Deduced Feature Correlations (AAAI 2025 · similarity 0.82)
- ACES: Automatic Cohort Extraction System for Event-Stream Datasets (ICLR 2025 · similarity 0.81)
- Contrastive Learning for Clinical Outcome Prediction with Partial Data Sources (ICML 2024 · similarity 0.81)
- GV-Rep: A Large-Scale Dataset for Genetic Variant Representation Learning (NeurIPS 2024 · similarity 0.81)
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.