Research map / Probabilistic and scientific modeling / Molecules and proteins
Integrative Analysis using Coupled Latent Variable Models for Individualizing Prognoses
Peter Schulam, Suchi Saria
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 |
|---|---|---|---|
| add auxiliary marker coupling (C-LTM instead of LTM) | LTM · PFVC, 1 year of data, horizon (1, 2] | MAE: 5.70 -> 5.12 | Improved |
| add auxiliary marker coupling (C-LTM instead of LTM) | LTM · PFVC, 1 year of data, horizon (2, 4] | MAE: 8.02 -> 6.88 | Improved |
| add auxiliary marker coupling (C-LTM instead of LTM) | LTM · PFVC, 2 years of data, horizon (2, 4] | MAE: 5.74 -> 5.58 | No clear effect |
| add auxiliary marker coupling (C-LTM instead of LTM) | LTM · PFVC, 4 years of data, horizon (4, 8] | MAE: 4.88 -> 5.04 | Hurt |
| add auxiliary marker coupling (C-LTM instead of LTM) | LTM · PFVC, 4 years of data, horizon (8, 25] | MAE: 8.65 -> 8.07 | Improved |
| add latent subtypes and individual adjustments (C-LTM instead of static baseline features) | B-spline with baseline features · PFVC, 1 year of data, horizon (1, 2] | MAE: 13.17 -> 5.12 | Improved |
| add subpopulation trajectories (B-spline mixture instead of B-spline + GP) | B-spline + GP · PFVC, 1 year of data, horizon (4, 8] | MAE: 10.88 -> 9.82 | Improved |
| add subpopulation trajectories (B-spline mixture instead of B-spline + GP) | B-spline + GP · PFVC, 1 year of data, horizon (8, 25] | MAE: 11.74 -> 13.77 | Hurt |
| add individual-specific adjustments (LTM instead of B-spline mixture) | B-spline Mixture · PFVC, 4 years of data, horizon (4, 8] | MAE: 6.00 -> 4.88 | Improved |
| use C-LTM prediction scores instead of baselines to detect rapidly declining individuals | B-spline + GP, B-spline mixture, LTM · Declining individual detection (AUC) | AUC: AUC 0.87 for C-LTM after four years of data | Improved |
Closest papers by meaning
- Adaptive Shrinkage Estimation for Personalized Deep Kernel Regression in Modeling Brain Trajectories (ICLR 2025 · similarity 0.86)
- Uncertainty-Calibrated Prediction of Randomly-Timed Biomarker Trajectories with Conformal Bands (NeurIPS 2025 · similarity 0.85)
- Unscrambling disease progression at scale: fast inference of event permutations with optimal transport (NeurIPS 2024 · similarity 0.85)
- Multimodal Disease Progression Modeling via Spatiotemporal Disentanglement and Multiscale Alignment (NeurIPS 2025 · similarity 0.84)
- Risk Horizons: Structured Hypothesis Spaces for Longitudinal Clinical Prediction (NeurIPS 2026 · similarity 0.84)
- Causal Identification for Complex Functional Longitudinal Studies (ICLR 2025 · similarity 0.84)
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.
