Research map / Architectures and efficiency / Attention and transformers
A Composite Multi-Attention Framework for Intraoperative Hypotension Early Warning
Feng Lu, Wei Li, Zhiqiang Zhou, Cheng Song, Yifei Sun, Yuwei Zhang, Yufei Ren, Xiaofei Liao, Hai Jin, Ailin Luo, Albert Y. Zomaya
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 |
|---|---|---|---|
| predict short-term MAP with CMA rather than the listed MAP prediction baselines | CMA · Tongji and VitalDB validation, 3–15min horizons | MAE (mm Hg): Tongji: 2.56 vs 2.64 (3min), 3.95 vs 4.00 (10min), 4.50 vs 4.55 (15min); VitalDB: 4.11 vs 4.34 (3min), 5.97 vs 6.23 (10m | Improved |
| use the composite input including demographic characteristics rather than dynamic indicators only (ablation) | CMA · MAP prediction, Tongji and VitalDB | MAE (mm Hg): Tongji: 2.56 vs 2.61 (3min), 3.95 vs 3.982 (10min), 4.50 vs 4.54 (15min); VitalDB: 4.11 vs 4.31 (3min), 5.97 vs 6.12 (10 | Improved |
| use only MAP, age, sex, and BMI instead of all seven indicators (ablation) | CMA · MAP prediction | MAE (mm Hg): 5.8 mm Hg | Hurt |
| reduce sampling frequency from 30 seconds to 1 minute (ablation) | CMA · MAP prediction | MAE | No clear effect |
| reduce sampling frequency from 30 seconds to 2 minutes (ablation) | CMA · MAP prediction | MAE: +12.9% | Hurt |
| reduce sampling frequency from 30 seconds to 1 minute using dynamic indicators only (ablation) | CMA-Dynamic Only · MAP prediction | MAE: 6% | Hurt |
| change the IOH definition from MAP below 65 mm Hg for 1 minute to below 65 mm Hg for 2 minutes without retraining (ablation) | CMA · Tongji IOH early warning | AUC: 0.912 and 0.941 | Mixed |
Closest papers by meaning
- Cross-Sample Augmented Test-Time Adaptation for Personalized Intraoperative Hypotension Prediction (AAAI 2026 · similarity 0.89)
- Early Warning of Intraoperative Adverse Events via Transformer-Driven Multi-Label Learning (AAAI 2026 · similarity 0.83)
- Yet Another ICU Benchmark: A Flexible Multi-Center Framework for Clinical ML (ICLR 2024 · similarity 0.81)
- Constraint Latent Space Matters: An Anti-anomalous Waveform Transformation Solution from Photoplethysmography to Arterial Blood Pressure (AAAI 2024 · similarity 0.80)
- XTSFormer: Cross-Temporal-Scale Transformer for Irregular-Time Event Prediction in Clinical Applications (AAAI 2025 · similarity 0.79)
- Surgical Workflow Recognition and Blocking Effectiveness Detection in Laparoscopic Liver Resection with Pringle Maneuver (AAAI 2025 · similarity 0.79)
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.
