Research map / Time series / Foundation models for time series
HiRID-ICU-Benchmark --- A Comprehensive Machine Learning Benchmark on High-resolution ICU Data
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 hand-engineered features (ablation) | LGBM · ICU mortality | AUPRC: 54.6 ± 0.8 -> 62.6 ± 0.0 | Helped |
| add hand-engineered features (ablation) | LGBM · Patient phenotyping | B-Accuracy: 40.4 ± 0.8 -> 45.8 ± 2.0 | Helped |
| add hand-engineered features (ablation) | LGBM · Circulatory failure | AUPRC: 38.9 ± 0.3 -> 38.8 ± 0.2 | No clear effect |
| add hand-engineered features (ablation) | LGBM · Respiratory failure | AUPRC: 58.5 ± 0.1 -> 60.4 ± 0.2 | Helped |
| add hand-engineered features (ablation) | LGBM · Kidney function | MAE: 0.45 ± 0.00 -> 0.45 ± 0.00 | No clear effect |
| add balanced cross-entropy loss weights (ablation) | LGBM w. Feat. · Patient phenotyping | B-Accuracy: +4.3 | Helped |
| add balanced cross-entropy loss weights (ablation) | LGBM w. Feat. · ICU mortality | AUPRC: -1.3 | Hurt |
| add balanced cross-entropy loss weights (ablation) | LGBM w. Feat. · Circulatory failure | AUPRC: -4.2 | Hurt |
| add balanced cross-entropy loss weights (ablation) | LGBM w. Feat. · Respiratory failure | AUPRC: 0.1 | No clear effect |
| add balanced cross-entropy loss weights (ablation) | Transformer · Patient phenotyping | B-Accuracy: +4.0 | Helped |
| add balanced cross-entropy loss weights (ablation) | Transformer · ICU mortality | AUPRC: -2.6 | Hurt |
| use deep learning sequence models instead of LGBM | online failure prediction · Circulatory failure | AUPRC: 38.9 ± 0.3 -> 36.8 ± 0.5 | Hurt |
Closest papers by meaning
- Yet Another ICU Benchmark: A Flexible Multi-Center Framework for Clinical ML (ICLR 2024 · similarity 0.91)
- GARLIC: Graph Attention-based Relational Learning of Multivariate Time Series in Intensive Care (ICLR 2026 · similarity 0.86)
- ICU Mortality Prediction: A Classification Algorithm for Imbalanced Datasets (AAAI 2017 · similarity 0.85)
- CLIMB: Data Foundations for Large Scale Multimodal Clinical Foundation Models (ICML 2025 · similarity 0.82)
- Distribution-Free Uncertainty Quantification in Mechanical Ventilation Treatment: A Conformal Deep Q-Learning Framework (AAAI 2025 · similarity 0.81)
- NeuroAtlas: Benchmarking Foundation Models for Clinical EEG and Brain-Computer Interfaces (NeurIPS 2026 · 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.