Research map / Time series / Long-term forecasting
Learning Adaptive Forecasting Models from Irregularly Sampled Multivariate Clinical Data
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 adaptive (Kalman filtering) prediction to population LDS (ablation) | LDS · PCP post-surgical cardiac CBC test (100 patients, last 4 observations) | Avg-MAPE (%): 7.19 -> 2.71 | Helped |
| add MTGP residual model on top of AdaptLDS (ablation) | AdaptLDS · PCP post-surgical cardiac CBC test (100 patients, last 4 observations) | Avg-MAPE (%): 2.71 -> 2.69 | Helped |
| add per-series GP residual model on top of AdaptLDS (ablation) | AdaptLDS · PCP post-surgical cardiac CBC test (100 patients, last 4 observations) | Avg-MAPE (%): 2.71 -> 2.70 | No clear effect |
| use MTGP residual model instead of per-series GP residual (ablation) | AdaptLDS+reGP · PCP post-surgical cardiac CBC test (100 patients, last 4 observations) | Avg-MAPE (%): 2.70 -> 2.69 | No clear effect |
| model multivariate interactions with MTGP instead of independent GPs | individual patient model · PCP post-surgical cardiac CBC test (100 patients, last 4 observations) | Avg-MAPE (%): 3.45 -> 3.36 | Helped |
| use population LDS without adaptation vs individual mean | forecasting · PCP post-surgical cardiac CBC test (100 patients, last 4 observations) | Avg-MAPE (%): 4.37 -> 7.19 | Hurt |
Closest papers by meaning
- PrimeNet: Pre-training for Irregular Multivariate Time Series (AAAI 2023 · similarity 0.86)
- MIRA: Medical Time Series Foundation Model for Real-World Health Data (NeurIPS 2025 · similarity 0.85)
- Integrating Sequence and Image Modeling in Irregular Medical Time Series Through Self-Supervised Learning (AAAI 2025 · similarity 0.84)
- Irregular Multivariate Time Series Forecasting: A Transformable Patching Graph Neural Networks Approach (ICML 2024 · similarity 0.84)
- Chimera: Effectively Modeling Multivariate Time Series with 2-Dimensional State Space Models (NeurIPS 2024 · similarity 0.83)
- Physiome-ODE: A Benchmark for Irregularly Sampled Multivariate Time-Series Forecasting Based on Biological ODEs (ICLR 2025 · similarity 0.82)
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.