Latent Dynamics · 2026-10-07
HyperNSDE: Personalized Neural SDEs for Joint Static-Longitudinal Clinical Data Generation
Perrine Chassat, Agathe Guilloux
AI-assisted summary based on the paper. Consult the linked source for methods and limitations. Benchmark numbers appear after editor verification.
TL;DR
HyperNSDE is a continuous-time generative model for clinical cohorts that jointly generates heterogeneous static covariates, irregularly sampled longitudinal trajectories, and informative observation times. It uses a HI-VAE for static latents, a hypernetwork-personalized Neural SDE with stochastic latent dynamics (without a trajectory encoder), and a latent-state-dependent intensity process for observation times, trained via deterministic–stochastic path decomposition and a non-adversarial signature-kernel objective.
Why it matters
The authors target a tightly coupled setting in clinical data generation: static baseline covariates, irregular longitudinal observations, and informative observation times. Their unified continuous-time design avoids discretization/resampling and aims to produce synthetic patient trajectories that match time-varying observation patterns while preserving privacy-related properties and downstream utility.
Method
- Hierarchical generation: sample static latents from HI-VAE, decode synthetic covariates, use a hypernetwork to parameterize patient-specific Neural SDE drift, simulate a latent stochastic path, then decode at sampled observation times.
- Observation times modeled jointly via a latent-state-dependent multivariate point process plus an explicit end-of-sequence (EOS) event; intensity comes from a neural network on the latent path.
- Training uses deterministic–stochastic path decomposition (latent trend as personalized Neural ODE via hypernetwork; residual stochasticity via population-shared Neural SDE) with a non-adversarial signature-kernel objective for stochastic residuals; intensity network conditioned only on the deterministic part for stability.
Abstract (from arXiv)
Synthetic patient data generation is a promising solution to the dual challenge of data scarcity and privacy constraints in healthcare machine learning. Realistic synthesis of patient-level clinical data requires jointly modeling heterogeneous static covariates, irregularly sampled longitudinal trajectories, and informative observation times - three tightly coupled components in practice yet rarely addressed together. We propose HyperNSDE, a continuous-time generative model that conditions a latent Neural SDE on static patient representations through a hypernetwork, allowing baseline characteristics to shape trajectory evolution beyond the initial condition without requiring a trajectory encoder, while stochastic latent dynamics capture realistic variability in generated paths. Observation times are modeled jointly through a latent-state-dependent intensity process, and training on irregular stochastic paths is stabilized via a deterministic-stochastic path decomposition with a non-adversarial signature-kernel objective. Experiments on simulated and real clinical datasets show improved observation-time fidelity and competitive performance, while matched-grid analyses reveal that forecasting and correlation metrics are affected by observation-grid regularity and trajectory smoothness.
Related papers
- Forecasting Patient Trajectories from the Electronic Health Records with Action-Conditioned World Models
- PatientWM: Towards Generalizable Clinical World Models via Unified Patient States
- Patient, Place, Prior (P$^3$): What Counts as Personalization in Medical World Models?
- Understanding Trajectory Heterogeneity in Federated World Model Learning
- Repeated-Measure Leakage, Distribution Shift, and Reliability under Partial Observation in Patient World Models
Publication record
Bibliographic evidence describes where and when a record appeared. It does not validate scientific claims.
First public release: 2026-10-05 · Indexed by Pub-AI: 2026-10-07 UTC
HyperNSDE: Personalized Neural SDEs for Joint Static-Longitudinal Clinical Data Generation
Preprint posted: 2026-10-05 · Original record ↗
- arxiv
- 2610.07383
Explicit source versions (1)
- v1 · 2026-10-05
- Preprint available
Source date: 2026-10-05 · First detected: 2026-10-25 UTC · Historical baseline
Source evidence (1)
- Official evidence ↗ · atom:published (official metadata)
Abstract · arxiv
Synthetic patient data generation is a promising solution to the dual challenge of data scarcity and privacy constraints in healthcare machine learning. Realistic synthesis of patient-level clinical data requires jointly modeling heterogeneous static covariates, irregularly sampled longitudinal trajectories, and informative observation times - three tightly coupled components in practice yet rarely addressed together. We propose HyperNSDE, a continuous-time generative model that conditions a latent Neural SDE on static patient representations through a hypernetwork, allowing baseline characteristics to shape trajectory evolution beyond the initial condition without requiring a trajectory encoder, while stochastic latent dynamics capture realistic variability in generated paths. Observation times are modeled jointly through a latent-state-dependent intensity process, and training on irregular stochastic paths is stabilized via a deterministic-stochastic path decomposition with a non-adversarial signature-kernel objective. Experiments on simulated and real clinical datasets show improved observation-time fidelity and competitive performance, while matched-grid analyses reveal that forecasting and correlation metrics are affected by observation-grid regularity and trajectory smoothness.