Research map / Label-efficient and robust learning / Recognition and long-tail
ICU Mortality Prediction: A Classification Algorithm for Imbalanced Datasets
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 new CDF approximation instead of Press' approximation (ablation) | CHISQ · ICU Mortality | mean AUC: 0.837 -> 0.867 | Helped |
| use new CDF approximation instead of Press' approximation (ablation) | CHISQ · ICU Mortality | challenge score: 0.55 -> 0.60 | Helped |
| add imbalance-handling preprocessing (CSL, UNS, SMOTE) to standard classifiers | SVM, RF, LR, LDA, QDA, Adaboost · ICU Mortality | mean AUC: SVM 0.568 -> 0.668; QDA 0.66 -> 0.66 | Mixed |
| use skewness-based chi-square classifier rather than RF | CHISQ-NEW · ICU Mortality (6 features) | mean AUC: 0.644 -> 0.867 | Helped |
| use 7 RF-important features instead of 6 least-missing features (ablation) | CHISQ-NEW · ICU Mortality | accuracy: 90% -> 85% | Hurt |
| add remaining 11 continuous features to the 6 selected features (ablation) | CHISQ-NEW · ICU Mortality | accuracy | No clear effect |
| use CHISQ-NEW at zero class overlap | CHISQ-NEW · Simulated Gaussian data | AUC | No clear effect |
| use CHISQ-NEW at low to high overlap | CHISQ-NEW · Simulated Gaussian data | AUC | Helped |
Closest papers by meaning
- Predicting ICU Mortality Risk by Grouping Temporal Trends from a Multivariate Panel of Physiologic Measurements (AAAI 2016 · similarity 0.88)
- Yet Another ICU Benchmark: A Flexible Multi-Center Framework for Clinical ML (ICLR 2024 · similarity 0.87)
- Learning Implicit Tasks for Patient-Specific Risk Modeling in ICU (AAAI 2017 · similarity 0.87)
- ForecastICU: A Prognostic Decision Support System for Timely Prediction of Intensive Care Unit Admission (ICML 2016 · similarity 0.85)
- HiRID-ICU-Benchmark --- A Comprehensive Machine Learning Benchmark on High-resolution ICU Data (NeurIPS 2021 · similarity 0.85)
- Distribution-Free Uncertainty Quantification in Mechanical Ventilation Treatment: A Conformal Deep Q-Learning Framework (AAAI 2025 · 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.