Deep dynamic modeling with just two time points: Can we still allow for individual trajectories?

  title={Deep dynamic modeling with just two time points: Can we still allow for individual trajectories?},
  author={Maren Hackenberg and Philipp Harms and Thorsten Schmidt and Harald Binder},
  journal={Biometrical journal. Biometrische Zeitschrift},
Longitudinal biomedical data are often characterized by a sparse time grid and individual-specific development patterns. Specifically, in epidemiological cohort studies and clinical registries we are facing the question of what can be learned from the data in an early phase of the study, when only a baseline characterization and one follow-up measurement are available. Inspired by recent advances that allow to combine deep learning with dynamic modeling, we investigate whether such approaches… 

Figures and Tables from this paper


Neural Ordinary Differential Equations
This work shows how to scalably backpropagate through any ODE solver, without access to its internal operations, which allows end-to-end training of ODEs within larger models.
Variational Inference: A Review for Statisticians
Variational inference (VI), a method from machine learning that approximates probability densities through optimization, is reviewed and a variant that uses stochastic optimization to scale up to massive data is derived.
GRU-ODE-Bayes: Continuous modeling of sporadically-observed time series
Empirical evaluation shows that the proposed GRU-ODE-Bayes method outperforms the state of the art on both synthetic data and real-world data with applications in healthcare and climate forecast and the continuity prior is shown to be well suited for low number of samples settings.
SMArtCARE - A platform to collect real-life outcome data of patients with spinal muscular atrophy
A prospective monitoring of all SMA patients will lead to a better understanding of the natural history of SMA and the influence of drug treatment, which is crucial to improve the care of Sma patients.
Universal Differential Equations for Scientific Machine Learning
The UDE model augments scientific models with machine-learnable structures for scientifically-based learning and shows how UDEs can be utilized to discover previously unknown governing equations, accurately extrapolate beyond the original data, and accelerate model simulation, all in a time and data-efficient manner.
A Differentiable Programming System to Bridge Machine Learning and Scientific Computing
Zygote is described, a Differentiable Programming system that is able to take gradients of general program structures and supports almost all language constructs and compiles high-performance code without requiring any user intervention or refactoring to stage computations.
Neural ordinary differential equations, in ‘Advances in Neural Information Processing Systems
  • Inference in hidden Markov models
  • 2018
Julia: A Fresh Approach to Numerical Computing
The Julia programming language and its design is introduced---a dance between specialization and abstraction, which recognizes what remains the same after computation, and which is best left untouched as they have been built by the experts.
Revised upper limb module for spinal muscular atrophy: Development of a new module
The development of the Revised Upper Limb Module (RULM), an assessment specifically designed for upper limb function in SMA patients, is reported.
Auto-encoding variational Bayes, in Y
  • 2014