Daniel Ramirez, Dr. Alona Kryshchenko, and Dr. Malidi Ahamadi
Abstract
The selection of optimal drug dosages is crucial to every phase of the drug development process. Central to understanding these dosages is the study of pharmacokinetics, or, how a drug is affected by the human body after consumption. Pharmacokinetic modeling is used to understand the relationship between a drug’s dosage and its consumer’s blood plasma concentration levels, but it can be challenging due to complex data and the inherent variability within and between human subjects. Pharmaceutical companies manage these challenges through the use of traditional statistical modeling to identify the covariates that could influence the dose-concentration relationship. Although this approach suits small sample sizes and sparse data sets well, it requires researchers to specify a structural pharmacokinetic model a priori, which can be cumbersome to adjust when dealing with highly variable and massive data sets. In this research we focused on utilizing neural networks as an alternative method to discover the drug dose and concentration relationship. In particular, we sought to predict the area under the concentration curve and maximum concentration given patient biometric data and initial drug dosage as input features. These desired outputs are vital in determining the extent of exposure and the highest concentration the drug will achieve in the patient’s bloodstream. Using a simulated clinical data set, we were able to train several single-layer neural networks and evaluate their predictive performance.
Presentation
Session 1 – 1:30p.m. – 2:45p.m.
Room D – Sierra 2422
