Research map / Time series / Causal and generative time series
Deep Mixed Effect Model Using Gaussian Processes: A Personalized and Reliable Prediction for Healthcare
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 |
|---|---|---|---|
| combine a shared RNN mean function with patient-specific Gaussian Processes | DME-GP · NHIS medical checkup, task average | AUC: 0.720 -> 0.778 | Helped |
| combine a shared mean function with patient-specific Gaussian Processes | DME-GP (MLP) · Vital-Sign Dataset, heart rate | RMSE: 0.194 -> 0.150 | Helped |
| remove the shared global mean function and use an individual zero mean (ablation) | DME-GP (MLP) · Vital-Sign Dataset, heart rate | RMSE: 0.150 -> 0.243 | Hurt |
| use one rather than four global-mean experts (ablation) | DME-GP mixture of experts · NHIS medical checkup, Arrhythmia | AUC: 0.74 -> 0.823 | Hurt |
| use two rather than four global-mean experts (ablation) | DME-GP mixture of experts · NHIS medical checkup, Arrhythmia | AUC: 0.723 -> 0.823 | Hurt |
| vary the number of global-mean experts from one to four (ablation) | DME-GP mixture of experts · NHIS medical checkup, disease risk tasks | AUC | Mixed |
| use the personalized model on easy rather than hard patients | DME-GP · NHIS medical checkup, Atherosclerosis | AUC: 0.691 -> 1 | Helped |
Closest papers by meaning
- Temporal Phenotyping using Deep Predictive Clustering of Disease Progression (ICML 2020 · similarity 0.86)
- ConCare: Personalized Clinical Feature Embedding via Capturing the Healthcare Context (AAAI 2020 · similarity 0.85)
- Learning of Cluster-based Feature Importance for Electronic Health Record Time-series (ICML 2022 · similarity 0.85)
- Bayesian Inference of Individualized Treatment Effects using Multi-task Gaussian Processes (NeurIPS 2017 · similarity 0.85)
- GraphCare: Enhancing Healthcare Predictions with Personalized Knowledge Graphs (ICLR 2024 · similarity 0.84)
- MIRA: Medical Time Series Foundation Model for Real-World Health Data (NeurIPS 2025 · 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.