Research map / Probabilistic and scientific modeling / Molecules and proteins
Learning Implicit Tasks for Patient-Specific Risk Modeling in ICU
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 the full collection of diseases per patient instead of main disease only (ablation) | Proposed latent-task model · ICU in-hospital mortality (hospital dataset, 296 patients) | AUC: 0.724 ±0.001 -> 0.764 ±0.001 | Helped |
| add population-level regularization (single-task model prior) (ablation) | Proposed latent-task model · ICU in-hospital mortality (hospital dataset, 296 patients) | AUC: 0.733 ±0.001 -> 0.764 ±0.001 | Helped |
| use latent basis tasks over disease collections instead of one common model | STL (common) · ICU in-hospital mortality (hospital dataset, 296 patients) | AUC: 0.754 ±0.001 -> 0.764 ±0.001 | Helped |
| use latent basis tasks over disease collections instead of MTL-DM | MTL-DM · ICU in-hospital mortality (hospital dataset, 296 patients) | AUC: 0.757 ±0.001 -> 0.764 ±0.001 | Helped |
| train per-disease separate models instead of one common model | Single-task logistic regression · ICU in-hospital mortality (hospital dataset, 296 patients) | AUC: 0.754 ±0.001 -> 0.720 ±0.001 | Hurt |
| add more alternating optimization iterations (update L) (ablation) | Proposed latent-task model · ICU in-hospital mortality (hospital dataset, 296 patients) | AUC | No clear effect |
Closest papers by meaning
- ICU Mortality Prediction: A Classification Algorithm for Imbalanced Datasets (AAAI 2017 · similarity 0.87)
- Clinical Risk Prediction with Temporal Probabilistic Asymmetric Multi-Task Learning (AAAI 2021 · similarity 0.87)
- Not to Cry Wolf: Distantly Supervised Multitask Learning in Critical Care (ICML 2018 · similarity 0.86)
- Predicting ICU Mortality Risk by Grouping Temporal Trends from a Multivariate Panel of Physiologic Measurements (AAAI 2016 · similarity 0.86)
- Yet Another ICU Benchmark: A Flexible Multi-Center Framework for Clinical ML (ICLR 2024 · similarity 0.85)
- Automated Multi-Task Learning for Joint Disease Prediction on Electronic Health Records (NeurIPS 2024 · similarity 0.80)
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.