Research map / Label-efficient and robust learning / Recognition and long-tail
DeepAlerts: Deep Learning Based Multi-Horizon Alerts for Clinical Deterioration on Oncology Hospital Wards
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 graph-Laplacian prior knowledge regularization over task-specific layers (ablation) | deep multi-task network (DMNN) · 24-hour alert, oncology EHR | sensitivity: .4944 -> .5400 | Helped |
| add graph-Laplacian prior knowledge regularization (ablation) | deep multi-task network (DMNN) · Alert sequence concordance | sequence concordance: .9542 -> .9814 | Helped |
| add graph-Laplacian prior knowledge regularization (ablation) | deep multi-task network (DMNN) · 6-hour alert | AUROC: .9144 -> .9142 | No clear effect |
| add task-specific loss balancing (ablation) | deep multi-task network (DMNN) · 24-hour alert | sensitivity: .4944 -> .5215 | Helped |
| add task-specific loss balancing (ablation) | deep multi-task network (DMNN) · 48-hour alert | precision: .6220 -> .6566 | Helped |
| add loss balancing on top of prior knowledge regularization (ablation) | DMNNp · 24-hour alert | sensitivity: .5400 -> .5419 | No clear effect |
| add loss balancing on top of prior knowledge regularization (ablation) | DMNNp · Alert sequence concordance | sequence concordance: .9814 -> .9817 | No clear effect |
| use multi-task network instead of single-task DNN | deep network · 24-hour alert | AUROC: .9263 -> .9478 | Helped |
| use multi-task network instead of single-task DNN | deep network · Alert sequence concordance | sequence concordance: .7548 -> .9542 | Helped |
| use DMNNpb instead of gradient boosted trees | oncology deterioration alert · 24-hour alert | precision: .6668 -> .7062 | Helped |
Closest papers by meaning
- Not to Cry Wolf: Distantly Supervised Multitask Learning in Critical Care (ICML 2018 · similarity 0.86)
- Learning the Joint Representation of Heterogeneous Temporal Events for Clinical Endpoint Prediction (AAAI 2018 · similarity 0.85)
- Clinical Risk Prediction with Temporal Probabilistic Asymmetric Multi-Task Learning (AAAI 2021 · similarity 0.85)
- XTSFormer: Cross-Temporal-Scale Transformer for Irregular-Time Event Prediction in Clinical Applications (AAAI 2025 · similarity 0.84)
- Yet Another ICU Benchmark: A Flexible Multi-Center Framework for Clinical ML (ICLR 2024 · 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.