AI/ML SIG | A deep(er) dive into Gaussian Process Flows: Flexible Bayesian Inference over mechanistic models in pharmacometrics
Includes a Live Web Event on 12/02/2026 at 12:00 PM (EST)
-
Register
- Non-member - Free!
- Member - Free!
- Guest User - Free!
Recently, NeuralODE-based approaches have emerged as promising tools to learn dynamical systems governing drug exposure and effects directly from data. However, these models are often difficult to train, prone to overfitting, and empirically show unreliable extrapolation beyond training data. To address these limitations, we propose Gaussian Process Flows (GPFlows), a method to perform Bayesian Inference over the space of mechanistic models. The result is a flexible full random effect model that naturally limits model complexity while learning subject-specific dynamics. Similarly to NeuralODEs, model components can be visualised to interpret learned effects. Adopting a Bayesian framework unlocks several additional benefits: principled uncertainty estimates, more faithful and robust model comparison, and continuous learning as new data becomes available. A unique benefit of GPFlows is that it compresses data into a set of inducing points, which can be safely shared without risks of patient re-identification.
Alexander Janssen
Alexander is a postdoctoral researcher and university lecturer working at the intersection of AI and Health at the AmsterdamUMC and ErasmusMC. He is also a use-case leader in the PHEMS consortium, an EU Horizon project that is developing the "Paediatric Health Data Space". This platform utilizes federated learning to enable partners to train ML methods using health record data obtained from all participating centres; all while maintaining strict patient privacy.
His past research has focussed on causal inference, generative AI, and bringing reliable AI methods to pharmacometrics. His current research focus is on de novo drug design, where he is working on fast-tracking in silico design candidates for experimental validation. He is the author of the Deep Compartment Models Julia package, which is an open-source project that provides a flexible environment to define and train novel ML-based models such as NeuralODEs within pharmacometrics.
Key:
Complete
Next
Failed
Available
Locked