Ahmed Elmokadem, Ph.D.

Senior Scientist II

Ahmed earned his PhD in Biomedical Sciences from the University of Connecticut. His thesis work revolved around building statistical models to solve problems with super-resolution imaging. Other fields of experience include systems biology and pharmacokinetics. More recently, he focused on developing physiologically-based pharmacokinetic (PBPK) models to get a better mechanistic understanding of drugs’ pharmacokinetics.

Recent publications by this scientist

UDE Know It If UDE Saw It: Leveraging Deep Machine Learning for QSP Model Development and Evaluation

November 14, 2023

Roller Coaster Talk presented at ACoP14. A workflow was introduced that integrates QSP modeling and machine learning in the form of UDEs. The workflow utilizes machine learning to learn missing parts in our knowledge of a QSP system while quantifying the uncertainty around the learned dynamics using Bayesian analysis.

Download PDF

Deep QSP Modeling: Leveraging Machine Learning for QSP Model Development and Evaluation

November 14, 2023

Presented at ACoP14. DQSP framework successfully implemented a UDE that characterized the PK of remoxipride and its effect on PRL release from lactotrophs to plasma. The model also characterized the positive feedback effect of plasma PRL on lactotroph PRL stimulation using an ANN.

Download PDF

Hierarchical Deep Compartment Modeling: A Workflow to Leverage Machine Learning for Hierarchical Pharmacometric Modeling

January 30, 2024

Oral presentation for ACoP14 Abstract Quality Award winner. The Hierarchical Deep Compartment Modeling (HDCM) framework introduced in this abstract was developed using open-source tools in the Julia Programming Language and integrated Bayesian inference to quantify the uncertainty around the model parameters. It provides a convenient, readily accessible HDCM framework to the pharmacometrics community interested in applying deep learning to hierarchical compartmental models.

Download PDF