The paper introduces Neural ODE-LMM, a hybrid model that integrates a Neural Ordinary Differential Equation into a linear mixed‑effects framework to flexibly learn time‑varying associations between exposures and outcomes. By encoding covariate trajectories into a continuous‑time latent state, the method preserves standard likelihood inference while capturing complex, potentially cumulative effects without pre‑specifying functional forms. Simulations demonstrate accurate recovery of instantaneous and cumulative effects, and application to the 3C cohort uncovers BMI and fasting glucose trajectories linked to cognitive decline.
arXiv:2607. 04647v1 Announce Type: cross Abstract: Scalable Bayesian inference for generalized linear mixed models (GLMMs) provides uncertainty-aware analysis of correlated longitudinal data, but existing scalable approaches largely assume low-dimensional tabular predictors and do not directly accommodate high-dimensional modalities such as images and text.
arXiv:2607. 21817v1 Announce Type: cross Abstract: Longitudinal studies often collect data at sparse, irregular, and unequally spaced time points.
arXiv:2606. 05797v1 Announce Type: new Abstract: Longitudinal treatment decisions require predicting potential outcomes under future treatment sequences in the presence of time-varying confounding, heterogeneous patient dynamics, and limited domain-specific data.
DeMMO is an interpretable framework that models longitudinal digital mobility outcomes (DMOs) across multiple diseases and outcomes using multi-task learning. It introduces a cross-disease, cross-outcome relation-learning mechanism that learns signed relationships from longitudinal DMO coefficient matrices, allowing selective information sharing even when disease cohorts lack shared participants. Evaluated on the Mobilise‑D dataset, DeMMO outperforms nine strong baselines and identifies reliable longitudinal DMO patterns for clinical validation.
arXiv:2606. 18535v1 Announce Type: cross Abstract: Multi-cause observational studies contain information about unmeasured confounding through the dependence structure among causes.
GlucoFM is a lightweight foundation model for continuous glucose monitoring that aligns irregular CGM data to a 24‑hour grid and splits glucose dynamics into slow‑varying trend and short‑term deviation streams. Pre‑trained on over 109,000 hours of unlabeled recordings, it outperforms existing CGM‑specific models on seven phenotype‑classification tasks, improving average PR‑AUC by 4.1 points and enabling strong cross‑dataset transfer and few‑shot adaptation. When combined with meal, nutrition, and subject context, its frozen encoder delivers the lowest two‑hour postprandial glycemic response errors for trajectory, incremental AUC, peak rise, and peak timing metrics.
arXiv:2606. 15784v1 Announce Type: new Abstract: Alzheimer's disease (AD) progression is often described through the amyloid-tau-neurodegeneration, or AT(N), cascade.
arXiv:2606. 29386v1 Announce Type: new Abstract: Predicting a patient's physiological trajectory under a planned treatment sequence is a prospective interventional problem, not standard time-series extrapolation.
arXiv:2603. 19186v3 Announce Type: replace Abstract: Randomized controlled trials (RCTs) are the gold standard for estimating treatment effects, yet they are often underpowered for detecting effect heterogeneity.
Alzheimer's disease (AD) progression is often described through the amyloid-tau-neurodegeneration, or AT(N), cascade. However, most longitudinal models represent this cascade either as a fixed sequence of biomarkers or as a black-box forecasting task.
arXiv:2607. 28567v1 Announce Type: cross Abstract: Longitudinal causal studies often record histories as irregular functional fragments: laboratory values, physiologic signals, sensor streams, and image-derived summaries measured at unequal and informative times.
arXiv:2607. 13984v1 Announce Type: cross Abstract: Longitudinal tumor measurements, dropout information, and genetic covariates provide complementary information about treatment response, but integrating these data sources within a single population modeling framework remains challenging.