Research map / Label-efficient and robust learning / Recognition and long-tail
Early Warning of Intraoperative Adverse Events via Transformer-Driven Multi-Label Learning
Xueyao Wang, Xiuding Cai, Honglin Shang, Yaoyao Zhu, Yu Yao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| IAENet vs best baseline (iTransformer/Crossformer) | IAENet · MuAE 5-min | Micro F1: 60.31 -> 65.36 | Improved |
| IAENet vs iTransformer | IAENet · MuAE 15-min | Micro F1: 42.95 -> 50.52 | Improved |
| replace ASL with LCRLoss (ablation) | IAENet · MuAE mean | F1: 64.87 -> 65.36 | Improved |
| add LCRLoss to baselines (ablation) | Informer, Crossformer, SegRNN, iTransformer · MuAE mean | AUC and F1: iTransformer 60.06 -> 61.34; AUC 71.84 -> 77.99 | Improved |
| add LCRLoss to baselines (ablation) | Crossformer · MuAE mean | precision: 73.03 -> 57.88 | Hurt |
| add TAFiLM instead of FiLM (ablation) | iTransformer · MuAE mean | F1: 61.07 -> 64.03 | Improved |
| add FiLM to baseline (ablation) | Crossformer · MuAE mean | F1: 60.31 -> 59.99 | No clear effect |
| batch-wise vs global sqrt-inverse reweighting (ablation) | IAENet · MuAE mean | F1: 59.51 -> 65.36 | Improved |
| add reweighting vs none (ablation) | IAENet · MuAE mean | F1: 63.97 -> 65.36 | Improved |
| tune lambda away from 0.02 (ablation) | IAENet · MuAE mean | F1: 65.36 -> 62.28 (0.001) | Hurt |
| increase batch size for co-occurrence estimate (ablation) | IAENet · MuAE mean | F1: 65.21 -> 64.78 (256) | No clear effect |
Closest papers by meaning
- DeepAlerts: Deep Learning Based Multi-Horizon Alerts for Clinical Deterioration on Oncology Hospital Wards (AAAI 2020 · similarity 0.83)
- XTSFormer: Cross-Temporal-Scale Transformer for Irregular-Time Event Prediction in Clinical Applications (AAAI 2025 · similarity 0.83)
- Yet Another ICU Benchmark: A Flexible Multi-Center Framework for Clinical ML (ICLR 2024 · similarity 0.81)
- Entity Only vs. Inline Approaches: Evaluating LLMs for Adverse Drug Event Detection in Clinical Text (Student Abstract) (AAAI 2025 · similarity 0.80)
- Diagnosing Transformers: Illuminating Feature Spaces for Clinical Decision-Making (ICLR 2024 · similarity 0.80)
- SAFER: A Calibrated Risk-Aware Multimodal Recommendation Model for Dynamic Treatment Regimes (ICML 2025 · 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.
