Research map / Probabilistic and scientific modeling / Variational and generative sampling
ELPAC: Endpoint-Anchored Latent Progression with Stage-Varying Multimodal Coordination
Shengxian DING, Yifei Zhang, Xinyuan Tian, Yuanshuang Guo, Zhao
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes ELPAC, a method for jointly inferring latent disease stage, progression subtype, and stage-varying multimodal coordination from partially observed cross-sectional aging cohort data (imaging, plasma, cognition).
Problem
Aging cohorts with imaging, plasma, and cognitive measurements usually give only partially observed cross-sectional snapshots, so latent stage, progression subtype, and how modalities coordinate across stages must be inferred jointly.
Approach
Endpoint-anchored latent progression model with stage-varying multimodal coordination, as described by the title; the abstract is truncated so the precise mechanism is not stated.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add endpoint anchors (ablation) | ELPAC · Synthetic cohorts (N=1,000) | subtype BAcc: 48.9 -> 95.4 | Improved |
| add endpoint anchors (ablation) | ELPAC · Synthetic cohorts (N=1,000) | stage Spearman rho: 92.4 -> 96.2 | No clear effect |
| add endpoint anchors (ablation) | ELPAC · Synthetic cohorts (N=1,000) | |Cog r|: 76.1 -> 97.9 | Improved |
| use factor covariance instead of diagonal (ablation) | ELPAC · Synthetic cohorts (N=1,000) | held-out NLL: 23.97 -> 19.27 | Improved |
| use factor covariance instead of diagonal (ablation) | ELPAC · Synthetic cohorts (N=1,000) | subtype BAcc: 68.7 -> 95.4 | Improved |
| make factor activations stage-varying instead of static (ablation) | ELPAC · Synthetic cohorts (N=1,000) | stage-binned PPC: 78.7 -> 82.8 | Improved |
| make factor activations stage-varying instead of static (ablation) | ELPAC · Synthetic cohorts (N=1,000) | subtype BAcc: 95.5 -> 95.4 | No clear effect |
| add endpoint anchors (ablation) | ELPAC · ADNI+NACC/SCAN cohort | subtype BAcc: 64.2 -> 68.5 | Improved |
| use stage-varying factors instead of static (ablation) | ELPAC · ADNI+NACC/SCAN cohort | subtype BAcc: 58.7 -> 68.5 | Improved |
| use factor covariance instead of diagonal (ablation) | ELPAC · ADNI+NACC/SCAN cohort | held-out NLL: 12.83 -> 11.01 | Improved |
| add supervised classification head (HEALNet) vs ELPAC | HEALNet · ADNI+NACC/SCAN cohort | AUC AD/(CN+MCI): 86.4 -> 87.8 | Hurt |
| increase anchor mislabeling to 20% (ablation) | ELPAC · Synthetic and real cohorts | BAcc / stage rho: 3.4 and 5.7 pp drops; real BAcc 7.0 pp | Hurt |
Closest papers by meaning
- Multimodal Disease Progression Modeling via Spatiotemporal Disentanglement and Multiscale Alignment (NeurIPS 2025 · similarity 0.86)
- Adaptive Shrinkage Estimation for Personalized Deep Kernel Regression in Modeling Brain Trajectories (ICLR 2025 · similarity 0.85)
- Risk Horizons: Structured Hypothesis Spaces for Longitudinal Clinical Prediction (NeurIPS 2026 · similarity 0.85)
- Unscrambling disease progression at scale: fast inference of event permutations with optimal transport (NeurIPS 2024 · similarity 0.84)
- Causal Identification for Complex Functional Longitudinal Studies (ICLR 2025 · similarity 0.84)
- B-CALM: Bias-Limited Bayesian Borrowing for RCT-Anchored Treatment Effects under Covariate Mismatch (NeurIPS 2026 · 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.
