Senior Scientist II
Matthew joined Metrum in 2019 as a Research Scientist. He holds an M.A. in Statistics from Boston University. Prior to Metrum, he worked for a variety of startup technology companies where he applied Bayesian methodologies in predictive models based on remote sensing data. His ongoing interests include communicating and leveraging uncertainty from a Bayesian perspective in scalable modeling and simulation projects.
December 6, 2024
Presented at ACoP 2024. A proof-of-concept was conducted using deep reinforcement learning to optimize vancomycin dosing based on predicted PK profiles. The reinforcement learner was able to produce dose recommendations that (on average) exceeded the standard-of-care recommended dose, and future opportunities for using reinforcement learning within pharmacometrics are vast with a large potential for impact through personalized dosing.
December 6, 2024
Presented at ACoP 2024. SHAP analyis, an interpretable ML technique, was applied to PopPK models with two examples: saturable PK and causal dependence in covariates. This analysis yieled insights beyond forest plots and clairified differences in different types of forest plots typically presented.
December 6, 2024
Presented at ACoP 2024. A Bayesian model of the probability of dose modification as a function of platelet and neutrophil counts was developed to characterize the dynamic and probabilistic nature of dose decisions. The dose modification model was successfully integrated into a dynamic simulation framework accounting for the impact of safety on dose.