Research map / Probabilistic and scientific modeling / Molecules and proteins
A Novel Approach for Longitudinal Modeling of Aging Health and Predicting Mortality Rates
Read the paperCheck your idea against 108,967 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 a stochastic differential equation model with an RNN for longitudinal forecasting of health trajectories and survival in aging, planned for evaluation on ELSA, but no results are reported.
Problem
Modeling the longitudinal health trajectories and survival (mortality) of aging individuals, where existing approaches rely on cross-sectional methods or are limited to few or binary health variables.
Approach
Combines a stochastic differential equation framework with a three-dimensional pairwise interaction network for health variables, an RNN to feed historical health data into mortality/health projections, and a VAE with missing masks for imputation, so each component contributes to the loss for interpretable longitudinal prediction.
Key results
- No experimental results are reported; the paper describes planned evaluation on ELSA with C-index, Brier score, D-calibration, and relative RMSE.
Limitations
- No experiments or results are presented; the evaluation is described as future work ('we plan to train and test').
- Possible selective attrition in the ELSA dataset may affect validity.
- No validation in a clinical setting; all tests planned on a public dataset only.
Experimental setup
Datasets: English Longitudinal Study of Aging (ELSA)
Metrics: C-index Brier score D-calibration relative RMSE
Baselines: Weighted Network Model Joint Model Stochastic Process Model DJIN
Builds on: Stochastic Process Model (Somers et al. 2009) Weighted Network Model (Zhbannikov et al. 2017) Dynamic Joint Interpretable Network (Farrell 2022)
Closest papers by meaning
- Conditional Diffusion with Ordinal Regression: Longitudinal Data Generation for Neurodegenerative Disease Studies (ICLR 2025 · similarity 0.83)
- Causal Identification for Complex Functional Longitudinal Studies (ICLR 2025 · similarity 0.82)
- Bayesian Neural Controlled Differential Equations for Treatment Effect Estimation (ICLR 2024 · similarity 0.82)
- Trajectory Flow Matching with Applications to Clinical Time Series Modelling (NeurIPS 2024 · similarity 0.82)
- MIRA: Medical Time Series Foundation Model for Real-World Health Data (NeurIPS 2025 · similarity 0.80)
- SDE Matching: Scalable and Simulation-Free Training of Latent Stochastic Differential Equations (ICML 2025 · similarity 0.80)
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.