Metrum Research Group proudly announces the selection of the abstract titled "Hierarchical Deep Compartment Modeling: A Workflow for Leveraging Machine Learning in Hierarchical Pharmacometric Modeling" as one of the recipients of the ACoP14 Quality Award.
Through this pioneering work, Ahmed Elmokadem, Ph.D., Kiersten Utsey, Ph.D., Eric Jordie, M.S., and Timothy Knab, Ph.D., introduce an innovative approach to pop PK modeling. Integrating Deep Compartment Modeling (DCM) with Bayesian inference, the study successfully employs Hierarchical Deep Compartment Modeling to infer PK model parameters, random effects, and artificial neural network weights, all while rigorously quantifying associated uncertainties.
Matthew Riggs, Ph.D., Chief Science Officer at MetrumRG, remarked, "Innovation at the interface of data, science, and technology is integral to our mission of advancing healthcare and defeating disease. We are honored by ISoP's recognition of our research at ACoP14. The results from this work will extend methodologies and open-source tools that can be used toward this mission and to bringing our community collectively forward in applying quantitative analytics to ultimately improve patient care."
This accomplishment underscores the capability of the HDCM framework to effectively utilize deep learning in hierarchical pharmacometric compartment models. As a result, HDCM is poised to impact the landscape of advanced pharmacometric and systems pharmacology-focused analyses.
The award-winning research will be presented at ACoP14. We invite you to explore the full list of MetrumRG workshops, sessions, abstracts, and posters scheduled for ACoP14. To learn more visit ACoP14.