Pumas 2.0 Features: Koopman Expectation

On-Demand Webinar

Pumas 2.0 Can Provide Fast Converging Algorithms to Probabilistic Estimates - Introducing the Koopman Method!

So, you want to project the probability of a clinical outcomes after different doses, for different patient-types? Pumas 2.0 can generate these in seconds. You will no longer need to perform thousands of Monte-Carlo simulations, post-process and analyze. Pumas 2.0 is pioneering the Koopman operator to generate error bounds on probabilistic quantities and composes with Bayesian Estimation.

Personalized precision dosing is about mathematically determining effective dosing strategies that optimize the probability of containing a patient's outcome within a therapeutic window. However, the common Monte Carlo approach for generating patient statistics is computationally expensive because thousands of simulations need to be computed.

In this webinar, we describe a new method which utilizes the Koopman operator to perform a direct computation of expected patient outcomes with respect to quantified uncertainties of Bayesian posteriors in a nonlinear mixed effect model framework. We detail how quantities such as the probability of being within the therapeutic window can be calculated with a choice of loss function on the Koopman expectation. We demonstrate a high performance parallelized implementation of this methodology in Pumas and showcase the ability to accelerate the computation of these expectations by 50x-200x over Monte Carlo. We showcase how dosing can be optimized with respect to probabilistic statements respecting variable uncertainties using the Koopman operator. We end by demonstrating an end-to-end workflow, from estimating variable uncertainties via Bayesian estimation to optimizing a dose with respect to parametric uncertainty.

For more information on how you can get the best out of Pumas, contact us at sales@pumas.ai


  • Dr. Christopher Rackauckas

    Director, Modeling and Simulation

  • Vaibhav Dixit

    Software Engineer

Access this Webinar for free