Research map / Probabilistic and scientific modeling / Molecules and proteins
Learning the Joint Representation of Heterogeneous Temporal Events for Clinical Endpoint Prediction
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 the event filter to phase-gated HE-LSTM (ablation) | HE-LSTM · MIMIC-III death prediction | AP: 0.7467 -> 0.7687 | Helped |
| Add the event filter to phase-gated HE-LSTM (ablation) | HE-LSTM · MIMIC-III abnormal lab test prediction | AUC: 0.7945 -> 0.7987 | Helped |
| Add the phase gate to event-filter HE-LSTM (ablation) | HE-LSTM · MIMIC-III abnormal lab test prediction | AP: 0.3410 -> 0.3914 | Helped |
| Replace the full event gate with phase gate only (ablation) | HE-LSTM · MIMIC-III death prediction | AP: 0.7687 -> 0.7467 | Hurt |
| Replace the full event gate with event filter only (ablation) | HE-LSTM · MIMIC-III abnormal lab test prediction | AUC: 0.7987 -> 0.7559 | Hurt |
| Use the full event gate instead of the strongest baseline | Clinical endpoint prediction · MIMIC-III death prediction | AUC: 0.9466 $\pm$ 0.0002 -> 0.9516 $\pm$ 0.0003 | Helped |
| Use the full event gate instead of the strongest baseline | Clinical endpoint prediction · MIMIC-III death prediction | AP: 0.7181 $\pm$ 0.0003 -> 0.7687 $\pm$ 0.0011 | Helped |
| Use the full event gate instead of the strongest baseline | Clinical endpoint prediction · MIMIC-III abnormal lab test prediction | AUC: 0.7722 $\pm$ 0.0007 -> 0.7987 $\pm$ 0.0008 | Helped |
| Use the full event gate instead of the strongest baseline | Clinical endpoint prediction · MIMIC-III abnormal lab test prediction | AP: 0.3575 $\pm$ 0.0026 -> 0.3914 $\pm$ 0.0013 | Helped |
| Add the event filter to the phase gate (ablation) | HE-LSTM · MIMIC-III death prediction | AUC: 0.9471 -> 0.9516 | No clear effect |
| Add the event filter to the phase gate (ablation) | HE-LSTM · MIMIC-III abnormal lab test prediction | cross entropy: 0.3019 -> 0.3003 | Helped |
| Use longer event sequences as input (ablation) | HE-LSTM · MIMIC-III death prediction | AP: 0.7551 -> 0.7687 | Helped |
Closest papers by meaning
- XTSFormer: Cross-Temporal-Scale Transformer for Irregular-Time Event Prediction in Clinical Applications (AAAI 2025 · similarity 0.86)
- One Loss to Rule Them All: Marked Time-to-Event for Structured EHR Foundation Models (NeurIPS 2026 · similarity 0.86)
- Risk Horizons: Structured Hypothesis Spaces for Longitudinal Clinical Prediction (NeurIPS 2026 · similarity 0.85)
- Integrating Sequence and Image Modeling in Irregular Medical Time Series Through Self-Supervised Learning (AAAI 2025 · similarity 0.84)
- Automated Multi-Task Learning for Joint Disease Prediction on Electronic Health Records (NeurIPS 2024 · similarity 0.83)
- MOTOR: A Time-to-Event Foundation Model For Structured Medical Records (ICLR 2024 · 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.